To see the other types of publications on this topic, follow the link: Human Motion Prediction.
Dissertations / Theses on the topic 'Human Motion Prediction'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 38 dissertations / theses for your research on the topic 'Human Motion Prediction.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Lasota, Przemyslaw A. (Przemyslaw Andrzej). "Robust human motion prediction for safe and efficient human-robot interaction." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/122497.
Full textAbstract:
Thesis: Ph. D. in Autonomous Systems, Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2019Cataloged from PDF version of thesis.
Includes bibliographical references (pages 175-188).
From robotic co-workers in factories to assistive robots in homes, human-robot interaction (HRI) has the potential to revolutionize a large array of domains by enabling robotic assistance where it was previously not possible. Introducing robots into human-occupied domains, however, requires strong consideration for the safety and efficiency of the interaction. One particularly effective method of supporting safe an efficient human-robot interaction is through the use of human motion prediction. By predicting where a person might reach or walk toward in the upcoming moments, a robot can adjust its motions to proactively resolve motion conflicts and avoid impeding the person's movements. Current approaches to human motion prediction, however, often lack the robustness required for real-world deployment. Many methods are designed for predicting specific types of tasks and motions, and do not necessarily generalize well to other domains.
It is also possible that no single predictor is suitable for predicting motion in a given scenario, and that multiple predictors are needed. Due to these drawbacks, without expert knowledge in the field of human motion prediction, it is difficult to deploy prediction on real robotic systems. Another key limitation of current human motion prediction approaches lies in deficiencies in partial trajectory alignment. Alignment of partially executed motions to a representative trajectory for a motion is a key enabling technology for many goal-based prediction methods. Current approaches of partial trajectory alignment, however, do not provide satisfactory alignments for many real-world trajectories. Specifically, due to reliance on Euclidean distance metrics, overlapping trajectory regions and temporary stops lead to large alignment errors.
In this thesis, I introduce two frameworks designed to improve the robustness of human motion prediction in order to facilitate its use for safe and efficient human-robot interaction. First, I introduce the Multiple-Predictor System (MPS), a datadriven approach that uses given task and motion data in order to synthesize a high performing predictor by automatically identifying informative prediction features and combining the strengths of complementary prediction methods. With the use of three distinct human motion datasets, I show that using the MPS leads to lower prediction error in a variety of HRI scenarios, and allows for accurate prediction for a range of time horizons. Second, in order to address the drawbacks of prior alignment techniques, I introduce the Bayesian ESTimator for Partial Trajectory Alignment (BEST-PTA).
This Bayesian estimation framework uses a combination of optimization, supervised learning, and unsupervised learning components that are trained and synthesized based on a given set of example trajectories. Through an evaluation on three human motion datasets, I show that BEST-PTA reduces alignment error when compared to state-of-the-art baselines. Furthermore, I demonstrate that this improved alignment reduces human motion prediction error. Lastly, in order to assess the utility of the developed methods for improving safety and efficiency in HRI, I introduce an integrated framework combining prediction with robot planning in time. I describe an implementation and evaluation of this framework on a real physical system. Through this demonstration, I show that the developed approach leads to automatically derived adaptive robot behavior. I show that the developed framework leads to improvements in quantitative metrics of safety and efficiency with the use of a simulated evaluation.
"Funded by the NASA Space Technology Research Fellowship Program and the National Science Foundation"--Page 6
by Przemyslaw A. Lasota.
Ph. D. in Autonomous Systems
Ph.D.inAutonomousSystems Massachusetts Institute of Technology, Department of Aeronautics and Astronautics
2
Conte, Dean Edward. "Autonomous Robotic Escort Incorporating Motion Prediction with Human Intention." Thesis, Virginia Tech, 2021. http://hdl.handle.net/10919/102581.
Full textAbstract:
This thesis presents a framework for a mobile robot to escort a human to their destination successfully and efficiently. The proposed technique uses accurate path prediction incorporating human intention to locate the robot in front of the human while walking. Human intention is inferred by the head pose, an effective past-proven implicit indicator of intention, and fused with conventional physics-based motion prediction. The human trajectory is estimated and predicted using a particle filter because of the human's nonlinear and non-Gaussian behavior, and the robot control action is determined from the predicted human pose allowing for anticipative autonomous escorting. Experimental analysis shows that the incorporation of the proposed human intention model reduces human position prediction error by approximately 35% when turning. Furthermore, experimental validation with an omnidirectional mobile robotic platform shows escorting up to 50% more accurate compared to the conventional techniques, while achieving 97% success rate.Master of Science
This thesis presents a method for a mobile robot to escort a human to their destination successfully and efficiently. The proposed technique uses human intention to predict the walk path allowing the robot to be in front of the human while walking. Human intention is inferred by the head direction, an effective past-proven indicator of intention, and is combined with conventional motion prediction. The robot motion is then determined from the predicted human position allowing for anticipative autonomous escorting. Experimental analysis shows that the incorporation of the proposed human intention reduces human position prediction error by approximately 35% when turning. Furthermore, experimental validation with an mobile robotic platform shows escorting up to 50% more accurate compared to the conventional techniques, while achieving 97% success rate. The unique escorting interaction method proposed has applications such as touch-less shopping cart robots, exercise companions, collaborative rescue robots, and sanitary transportation for hospitals.
3
Bataineh, Mohammad Hindi. "New neural network for real-time human dynamic motion prediction." Thesis, The University of Iowa, 2015. http://pqdtopen.proquest.com/#viewpdf?dispub=3711174.
Full textAbstract:
Artificial neural networks (ANNs) have been used successfully in various practical problems. Though extensive improvements on different types of ANNs have been made to improve their performance, each ANN design still experiences its own limitations. The existing digital human models are mature enough to provide accurate and useful results for different tasks and scenarios under various conditions. There is, however, a critical need for these models to run in real time, especially those with large-scale problems like motion prediction which can be computationally demanding. For even small changes to the task conditions, the motion simulation needs to run for a relatively long time (minutes to tens of minutes). Thus, there can be a limited number of training cases due to the computational time and cost associated with collecting training data. In addition, the motion problem is relatively large with respect to the number of outputs, where there are hundreds of outputs (between 500-700 outputs) to predict for a single problem. Therefore, the aforementioned necessities in motion problems lead to the use of tools like the ANN in this work.
This work introduces new algorithms for the design of the radial-basis network (RBN) for problems with minimal available training data. The new RBN design incorporates new training stages with approaches to facilitate proper setting of necessary network parameters. The use of training algorithms with minimal heuristics allows the new RBN design to produce results with quality that none of the competing methods have achieved. The new RBN design, called Opt_RBN, is tested on experimental and practical problems, and the results outperform those produced from standard regression and ANN models. In general, the Opt_RBN shows stable and robust performance for a given set of training cases.
When the Opt_RBN is applied on the large-scale motion prediction application, the network experiences a CPU memory issue when performing the optimization step in the training process. Therefore, new algorithms are introduced to modify some steps of the new Opt_RBN training process to address the memory issue. The modified steps should only be used for large-scale applications similar to the motion problem. The new RBN design proposes an ANN that is capable of improved learning without needing more training data. Although the new design is driven by its use with motion prediction problems, the consequent ANN design can be used with a broad range of large-scale problems in various engineering and industrial fields that experience delay issues when running computational tools that require a massive number of procedures and a great deal of CPU memory.
The results of evaluating the modified Opt_RBN design on two motion problems are promising, with relatively small errors obtained when predicting approximately 500-700 outputs. In addition, new methods for constraint implementation within the new RBN design are introduced. Moreover, the new RBN design and its associated parameters are used as a tool for simulated task analysis. This work initiates the idea that output weights (W) can be used to determine the most critical basis functions that cause the greatest reduction in the network test error. Then, the critical basis functions can specify the most significant training cases that are responsible for the proper performance achieved by the network. The inputs with the most change in value can be extracted from the basis function centers (U) in order to determine the dominant inputs. The outputs with the most change in value and their corresponding key body degrees-of-freedom for a motion task can also be specified using the training cases that are used to create the network's basis functions.
4
Matsangas, Panagiotis. "A linear physiological visual-vestibular interaction model for the prediction of motion sickness incidence." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2004. http://library.nps.navy.mil/uhtbin/hyperion/04Sep%5FMatsangas.pdf.
Full textAbstract:
Thesis (M.S. in Operations Research and M.S. in Modeling, Virtual Environments and Simulation)--Naval Postgraduate School, Sept. 2004.Thesis Advisor(s): Michael McCauley, Nita Miller. Includes bibliographical references (p. 149-162). Also available online.
5
Wang, Anqi. "Prediction of Human Hand Motions based on Surface Electromyography." Thesis, Virginia Tech, 2017. http://hdl.handle.net/10919/78289.
Full textAbstract:
Tracking human hand motions has raised more attention due to the recent advancements of virtual reality (Rheingold, 1991) and prosthesis control (Antfolk et al., 2010). Surface electromyography (sEMG) has been the predominant method for sensing electrical activity in biomechanical studies, and has also been applied to motion tracking in recent years. While most studies focus on the classification of human hand motions within a predefined motion set, the prediction of continuous finger joint angles and wrist angles remains a challenging endeavor. In this research, a biomechanical knowledge-driven data fusion strategy is proposed to predict finger joint angles and wrist angles. This strategy combines time series data of sEMG signals and simulated muscle features, which can be extracted from a biomechanical model available in OpenSim (Delp et al., 2007). A support vector regression (SVR) model is used to firstly predict muscle features from sEMG signals and then to predict joint angles from the estimated muscle features. A set of motion data containing 10 types of motions from 12 participants was collected from an institutional review board approved experiment. A hypothesis was tested to validate whether adding the simulated muscle features would significantly improve the prediction performance. The study indicates that the biomechanical knowledge-driven data fusion strategy will improve the prediction of new types of human hand motions. The results indicate that the proposed strategy significantly outperforms the benchmark date-driven model especially when the users were performing unknown types of motions from the model training stage. The proposed model provides a possible approach to integrate the simulation models and data fusion models in human factors and ergonomics.Master of Science
6
Kelling, Nicholas J. "An investigation of human capability to predict the future location of objects in motion." Diss., Atlanta, Ga. : Georgia Institute of Technology, 2009. http://hdl.handle.net/1853/28103.
Full textAbstract:
Thesis (M. S.)--Psychology, Georgia Institute of Technology, 2009.Committee Chair: Dr. Gregory M. Corso; Committee Member: Dr. Arthur D. Fisk; Committee Member: Dr. Bruce Walker; Committee Member: Dr. Lawrence R. James; Committee Member: Dr. Paul Corballis; Committee Member: Dr. Robert Gregor
7
Fan, Zheyu Jerry. "Kalman Filter Based Approach : Real-time Control-based Human Motion Prediction in Teleoperation." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-189210.
Full textAbstract:
This work is to investigate the performance of two Kalman Filter Algorithms, namely Linear Kalman Filter and Extended Kalman Filter on control-based human motion prediction in a real-time teleoperation. The Kalman Filter Algorithm has been widely used in research areas of motion tracking and GPS-navigation. However, the potential of human motion prediction by utilizing this algorithm is rarely being mentioned. Combine with the known issue - the delay issue in today’s teleoperation services, the author decided to build a prototype of simple teleoperation model based on the Kalman Filter Algorithm with the aim of eliminated the unsynchronization between the user’s inputs and the visual frames, where all the data were transferred over the network. In the first part of the thesis, two types of Kalman Filter Algorithm are applied on the prototype to predict the movement of the robotic arm based on the user’s motion applied on a Haptic Device. The comparisons in performance among the Kalman Filters have also been focused. In the second part, the thesis focuses on optimizing the motion prediction which based on the results of Kalman filtering by using the smoothing algorithm. The last part of the thesis examines the limitation of the prototype, such as how much the delays are accepted and how fast the movement speed of the Phantom Haptic can be, to still be able to obtain reasonable predations with acceptable error rate. The results show that the Extended Kalman Filter has achieved more advantages in motion prediction than the Linear Kalman Filter during the experiments. The unsynchronization issue has been effectively improved by applying the Kalman Filter Algorithm on both state and measurement models when the latency is set to below 200 milliseconds. The additional smoothing algorithm further increases the accuracy. More important, it also solves shaking issue on the visual frames on robotic arm which is caused by the wavy property of the Kalman Filter Algorithm. Furthermore, the optimization method effectively synchronizes the timing when robotic arm touches the interactable object in the prediction. The method which is utilized in this research can be a good reference for the future researches in control-based human motion tracking and prediction.Detta arbete fokuserar på att undersöka prestandan hos två Kalman Filter Algoritmer, nämligen Linear Kalman Filter och Extended Kalman Filter som används i realtids uppskattningar av kontrollbaserad mänsklig rörelse i teleoperationen. Dessa Kalman Filter Algoritmer har används i stor utsträckning forskningsområden i rörelsespårning och GPS-navigering. Emellertid är potentialen i uppskattning av mänsklig rörelse genom att utnyttja denna algoritm sällan nämnas. Genom att kombinera med det kända problemet – fördröjningsproblem i dagens teleoperation tjänster beslutar författaren att bygga en prototyp av en enkel teleoperation modell vilket är baserad på Kalman Filter algoritmen i syftet att eliminera icke-synkronisering mellan användarens inmatningssignaler och visuella information, där alla data överfördes via nätverket. I den första delen av avhandlingen appliceras både Kalman Filter Algoritmer på prototypen för att uppskatta rörelsen av robotarmen baserat på användarens rörelse som anbringas på en haptik enhet. Jämförelserna i prestandan bland de Kalman Filter Algoritmerna har också fokuserats. I den andra delen fokuserar avhandlingen på att optimera uppskattningar av rörelsen som baserat på resultaten av Kalman-filtrering med hjälp av en utjämningsalgoritm. Den sista delen av avhandlingen undersökes begräsning av prototypen, som till exempel hur mycket fördröjningar accepteras och hur snabbt den haptik enheten kan vara, för att kunna erhålla skäliga uppskattningar med acceptabel felfrekvens. Resultaten visar att den Extended Kalman Filter har bättre prestandan i rörelse uppskattningarna än den Linear Kalman Filter under experimenten. Det icke-synkroniseringsproblemet har förbättrats genom att tillämpa de Kalman Filter Algoritmerna på både statliga och värderingsmodeller när latensen är inställd på under 200 millisekunder. Den extra utjämningsalgoritmen ökar ytterligare noggrannheten. Denna algoritm löser också det skakande problem hos de visuella bilder på robotarmen som orsakas av den vågiga egenskapen hos Kalman Filter Algoritmen. Dessutom effektivt synkroniserar den optimeringsmetoden tidpunkten när robotarmen berör objekten i uppskattningarna. Den metod som används i denna forskning kan vara en god referens för framtida undersökningar i kontrollbaserad rörelse- spåning och uppskattning.
8
Verveniotis, Christos S. "Prediction of motion sickness on high-speed passenger vessels : a human-oriented approach." Thesis, University of Strathclyde, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.415297.
Full text
9
Boonpratatong, Amaraporn. "Motion prediction and dynamic stability analysis of human walking : the effect of leg property." Thesis, University of Manchester, 2013. https://www.research.manchester.ac.uk/portal/en/theses/motion-prediction-and-dynamic-stability-analysis-of-human-walking-the-effect-of-leg-property(f36922af-1231-4dac-a92f-a16cbed8d701).html.
Full textAbstract:
The objective of this thesis is to develop and validate a computational framework based on mathematical models for the motion prediction and dynamic stability quantification of human walking, which can differentiate the dynamic stability of human walking with different mechanical properties of the leg. Firstly, a large measurement database of human walking motion was created. It contains walking measurement data of 8 subjects on 3 self-selected walking speeds, which 10 trials were recorded at each walking speed. The motion of whole-body centre of mass and the leg were calculated from the kinetic-kinematic measurement data. The fundamentals of leg property have been presented, and the parameters of leg property were extracted from the measurement data of human walking where the effects of walking speed and condition of foot-ground contact were investigated. Three different leg property definitions comprising linear axial elastic leg property, nonlinear axial elastic leg property and linear axial-tangential elastic leg property were used to extracted leg property parameters. The concept of posture-dependent leg property has been proposed, and the leg property parameters were extracted from the measurement data of human walking motion where the effects of walking speed and condition of foot-ground contact were also investigated. The compliant leg model with axial elastic property (CAE) was used for the dynamic stability analysis of human walking with linear and nonlinear axial elastic leg property. The compliant leg model with axial and tangential elastic property (CATE) was used for that with linear axial-tangential elastic leg property. The posture - dependent elastic leg model (PDE) was used for that with posture-dependent leg property. It was found that, with linear axial elastic leg property, the global stability of human walking improves with the bigger touchdown contact angle. The average leg property obtained from the measurement data of all participants allows the maximum global stability of human walking. With nonlinear axial elastic leg property, the global stability decreases with the stronger nonlinearity of leg stiffness. The incorporation of the tangential elasticity improves the global stability and shifts the stable walking velocity close to that of human walking at self-selected low speed (1.1-1.25 m/s).By the PDE model, the human walking motions were better predicted than by the CATE model. The effective range of walking prediction was enlarged to 1.12 – 1.8 m/s. However, represented by PDE model, only 1-2 walking steps can be achieved. In addition, the profiles of mechanical energies represented by the PDE model are different from that of the orbital stable walking represented by CATE model. Finally, the minimal requirements of the human walking measurements and the flexibility of simple walking models with deliberate leg property definitions allow the computational framework to be applicable in the dynamic stability analysis of the walking motion with a wide variety of mechanical property of the leg.
10
Bataineh, Mohammad Hindi. "Artificial neural network for studying human performance." Thesis, University of Iowa, 2012. https://ir.uiowa.edu/etd/3259.
Full textAbstract:
The vast majority of products and processes in industry and academia require human interaction. Thus, digital human models (DHMs) are becoming critical for improved designs, injury prevention, and a better understanding of human behavior. Although many capabilities in the DHM field continue to mature, there are still many opportunities for improvement, especially with respect to posture- and motion-prediction. Thus, this thesis investigates the use of artificial neural network (ANN) for improving predictive capabilities and for better understanding how and why human behave the way they do.
With respect to motion prediction, one of the most challenging opportunities for improvement concerns computation speed. Especially, when considering dynamic motion prediction, the underlying optimization problems can be large and computationally complex. Even though the current optimization-based tools for predicting human posture are relatively fast and accurate and thus do not require as much improvement, posture prediction in general is a more tractable problem than motion prediction and can provide a test bead that can shed light on potential issues with motion prediction. Thus, we investigate the use of ANN with posture prediction in order to discover potential issues. In addition, directly using ANN with posture prediction provides a preliminary step towards using ANN to predict the most appropriate combination of performance measures (PMs) - what drives human behavior. The PMs, which are the cost functions that are minimized in the posture prediction problem, are typically selected manually depending on the task. This is perhaps the most significant impediment when using posture prediction. How does the user know which PMs should be used? Neural networks provide tools for solving this problem.
This thesis hypothesizes that the ANN can be trained to predict human motion quickly and accurately, to predict human posture (while considering external forces), and to determine the most appropriate combination of PM(s) for posture prediction. Such capabilities will in turn provide a new tool for studying human behavior. Based on initial experimentation, the general regression neural network (GRNN) was found to be the most effective type of ANN for DHM applications. A semi-automated methodology was developed to ease network construction, training and testing processes, and network parameters. This in turn facilitates use with DHM applications.
With regards to motion prediction, use of ANN was successful. The results showed that the calculation time was reduced from 1 to 40 minutes, to a fraction of a second without reducing accuracy. With regards to posture prediction, ANN was again found to be effective. However, potential issues with certain motion-prediction tasks were discovered and shed light on necessary future development with ANNs. Finally, a decision engine was developed using GRNN for automatically selecting four human PMs, and was shown to be very effective. In order to train this new approach, a novel optimization formulation was used to extract PM weights from pre-existing motion-capture data. Eventually, this work will lead to automatically and realistically driving predictive DHMs in a general virtual environment.
11
Sheth, Katha Janak. "Model predictive control for adaptive digital human modeling." Thesis, University of Iowa, 2010. https://ir.uiowa.edu/etd/884.
Full textAbstract:
We consider a new approach to digital human simulation, using Model Predictive Control (MPC). This approach permits a virtual human to react online to unanticipated disturbances that occur in the course of performing a task. In particular, we predict the motion of a virtual human in response to two different types of real world disturbances: impulsive and sustained. This stands in contrast to prior approaches where all such disturbances need to be known a priori and the optimal reactions must be computed off line. We validate this approach using a planar 3 degrees of freedom serial chain mechanism to imitate the human upper limb. The response of the virtual human upper limb to various inputs and external disturbances is determined by solving the Equations of Motion (EOM). The control input is determined by the MPC Controller using only the current and the desired states of the system. MPC replaces the closed loop optimization problem with an open loop optimization allowing the ease of implementation of control law. Results presented in this thesis show that the proposed controller can produce physically realistic adaptive simulations of a planar upper limb of digital human in presence of impulsive and sustained disturbances.
12
Dong, Minjing. "Modelling Skeleton-based Human Dynamics via Retrospection." Thesis, The University of Sydney, 2019. http://hdl.handle.net/2123/21089.
Full textAbstract:
Human motion prediction is one of the key problems in computer vision and robotic vision and has received increasing attention in recent years. The target is to generate the future continuous, realistic human poses given a seed sequence, which can further assist human motion analysis. However, due to the high-uncertainty, it is difficult and challenging to model human dynamics which not only requires spatial information including complicated joint correlations, but also temporal information including periodic properties. Recently, deep recurrent neural networks (RNNs) have achieved impressive success in forecasting human motion with a sequence-to-sequence architecture. However, forecasting in longer time horizons often leads to implausible human poses or converges to mean poses, because of error accumulation and difficulties in keeping track of longer-term information. Based on these observations, in this study, we propose to retrospect human dynamics with attention. A retrospection module is designed upon RNN to regularly retrospect past frames and correct mistakes in time. This significantly improves the memory of RNN and provides sufficient information for the decoder networks to generate longer-term predictions. Moreover, we present a spatial attention module to explore cooperation among joints in performing a particular motion as well as a temporal attention module to exploit the level of importance among observed frames. Residual connections are also included to guarantee the performance of short-term prediction. We evaluate the proposed algorithm on the largest and most challenging Human 3.6M dataset in the field. Experimental results demonstrate the necessity of investigating motion prediction in a self-audit manner and the effectiveness of the proposed algorithm in both short-term and long-term predictions.
13
Sierra, Gonzalez David. "Towards Human-Like Prediction and Decision-Making for Automated Vehicles in Highway Scenarios." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAM012/document.
Full textAbstract:
Au cours des dernières décennies, les constructeurs automobiles ont constamment introduit des innovations technologiques visant à rendre les véhicules plus sûrs. Le niveau de sophistication de ces systèmes avancés d’aide à la conduite s’est accru parallèlement aux progrès de la technologie des capteurs et de la puissance informatique intégrée. Plus récemment, une grande partie de la recherche effectuée par l'industrie et les institutions s'est concentrée sur l'obtention d'une conduite entièrement automatisée. Les avantages sociétaux potentiels de cette technologie sont nombreux, notamment des routes plus sûres, des flux de trafic améliorés et une mobilité accrue pour les personnes âgées et les handicapés. Toutefois, avant que les véhicules autonomes puissent être commercialisés, ils doivent pouvoir partager la route en toute sécurité avec d’autres véhicules conduits par des conducteurs humains. En d'autres termes, ils doivent pouvoir déduire l'état et les intentions du trafic environnant à partir des données brutes fournies par divers capteurs embarqués, et les utiliser afin de pouvoir prendre les bonnes décisions de conduite sécurisée. Malgré la complexité apparente de cette tâche, les conducteurs humains ont la capacité de prédire correctement l’évolution du trafic environnant dans la plupart des situations. Cette capacité de prédiction est rendu plus simple grâce aux règles imposées par le code de la route qui limitent le nombre d’hypothèses; elle repose aussi sur l’expérience du conducteur en matière d’évaluation et de réduction du risque. L'absence de cette capacité à comprendre naturellement une scène de trafic constitue peut-être, le principal défi qui freine le déploiement à grande échelle de véhicules véritablement autonomes sur les routes.Dans cette thèse, nous abordons les problèmes de modélisation du comportement du conducteur, d'inférence sur le comportement des autres véhicules, et de la prise de décision pour la navigation sûre. En premier lieu, nous modélisons automatiquement le comportement d'un conducteur générique à partir de données de conduite démontrées, évitant ainsi le réglage manuel traditionnel des paramètres du modèle. Ce modèle codant les préférences d’un conducteur par rapport au réseau routier (par exemple, voie ou vitesse préférées) et aux autres usagers de la route (par exemple, distance préférée au véhicule de devant). Deuxièmement, nous décrivons une méthode qui utilise le modèle appris pour prédire la séquence des actions à long terme de tout conducteur dans une scène de trafic. Cette méthode de prédiction suppose que tous les acteurs du trafic se comportent de manière aversive au risque, et donc ne peut pas prévoir les manœuvres dangereux ou les accidents. Pour pouvoir traiter de tels cas, nous proposons un modèle probabiliste plus sophistiqué, qui estime l'état et les intentions du trafic environnant en combinant la prédiction basée sur le modèle avec les preuves dynamiques fournies par les capteurs. Le modèle proposé imite ainsi en quelque sorte le processus de raisonnement des humains. Nous humains, savons ce qu’un véhicule est susceptible de faire compte tenu de la situation (ceci est donné par le modèle), mais nous surveillerons sa dynamique pour en détecter les écarts par rapport au comportement attendu. En pratique, la combinaison de ces deux sources d’informations se traduit par une robustesse accrue des estimations de l’intention par rapport aux approches reposant uniquement sur des preuves dynamiques. En dernière partie, les deux modèles présentés (comportemental et prédictif) sont intégrés dans le cadre d´une approche décisionnel probabiliste. Les méthodes proposées se sont vues évalués avec des données réelles collectées avec un véhicule instrumenté, attestant de leur efficacité dans le cadre de la conduite autonome sur autoroute. Bien que centré sur les autoroutes, ce travail pourrait être facilement adapté pour gérer des scénarios de trafic alternatifsDuring the past few decades automakers have consistently introduced technological innovations aimed to make road vehicles safer. The level of sophistication of these advanced driver assistance systems has increased parallel to developments in sensor technology and embedded computing power. More recently, a lot of the research made both by industry and institutions has concentrated on achieving fully automated driving. The potential societal benefits of this technology are numerous, including safer roads, improved traffic flows, increased mobility for the elderly and the disabled, and optimized human productivity. However, before autonomous vehicles can be commercialized they should be able to safely share the road with human drivers. In other words, they should be capable of inferring the state and intentions of surrounding traffic from the raw data provided by a variety of onboard sensors, and to use this information to make safe navigation decisions. Moreover, in order to truly navigate safely they should also consider potential obstacles not observed by the sensors (such as occluded vehicles or pedestrians). Despite the apparent complexity of the task, humans are extremely good at predicting the development of traffic situations. After all, the actions of any traffic participant are constrained by the road network, by the traffic rules, and by a risk-aversive common sense. The lack of this ability to naturally understand a traffic scene constitutes perhaps the major challenge holding back the large-scale deployment of truly autonomous vehicles in the roads.In this thesis, we address the full pipeline from driver behavior modeling and inference to decision-making for navigation. In the first place, we model the behavior of a generic driver automatically from demonstrated driving data, avoiding thus the traditional hand-tuning of the model parameters. This model encodes the preferences of a driver with respect to the road network (e.g. preferred lane or speed) and also with respect to other road users (e.g. preferred distance to the leading vehicle). Secondly, we describe a method that exploits the learned model to predict the future sequence of actions of any driver in a traffic scene up to the distant future. This model-based prediction method assumes that all traffic participants behave in a risk-aware manner and can therefore fail to predict dangerous maneuvers or accidents. To be able to handle such cases, we propose a more sophisticated probabilistic model that estimates the state and intentions of surrounding traffic by combining the model-based prediction with the dynamic evidence provided by the sensors. In a way, the proposed model mimics the reasoning process of human drivers: we know what a given vehicle is likely to do given the situation (this is given by the model), but we closely monitor its dynamics to detect deviations from the expected behavior. In practice, combining both sources of information results in an increased robustness of the intention estimates in comparison with approaches relying only on dynamic evidence. Finally, the learned driver behavioral model and the prediction model are integrated within a probabilistic decision-making framework. The proposed methods are validated with real-world data collected with an instrumented vehicle. Although focused on highway environments, this work could be easily adapted to handle alternative traffic scenarios
14
Roach, Jeffrey Wayne. "Predicting Realistic Standing Postures in a Real-Time Environment." NSUWorks, 2013. http://nsuworks.nova.edu/gscis_etd/291.
Full textAbstract:
Procedural human motion generation is still an open area of research. Most research into procedural human motion focus on two problem areas: the realism of the generated motion and the computation time required to generate the motion. Realism is a problem because humans are very adept at spotting the subtle nuances of human motion and so the computer generated motion tends to look mechanical. Computation time is a problem because the complexity of the motion generation algorithms results in lengthy processing times for greater levels of realism.
The balancing human problem poses the question of how to procedurally generate, in real-time, realistic standing poses of an articulated human body. This report presents the balancing human algorithm that addresses both concerns: realism and computation time. Realism was addressed by integrating two existing algorithms. One algorithm addressed the physics of the human motion and the second addressed the prediction of the next pose in the animation sequence. Computation time was addressed by identifying techniques to simplify or constrain the algorithms so that the real-time goal can be met.
The research methodology involved three tasks: developing and implementing the balancing human algorithm, devising a real-time simulation graphics engine, and then evaluating the algorithm with the engine. An object-oriented approach was used to model the balancing human as an articulated body consisting of systems of rigid-bodies connected together with joints. The attributes and operations of the object-oriented model were derived from existing published algorithms.
15
Nitz, Pettersson Hannes, and Samuel Vikström. "VISION-BASED ROBOT CONTROLLER FOR HUMAN-ROBOT INTERACTION USING PREDICTIVE ALGORITHMS." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-54609.
Full textAbstract:
The demand for robots to work in environments together with humans is growing. This calls for new requirements on robots systems, such as the need to be perceived as responsive and accurate in human interactions. This thesis explores the possibility of using AI methods to predict the movement of a human and evaluating if that information can assist a robot with human interactions. The AI methods that were used is a Long Short Term Memory(LSTM) network and an artificial neural network(ANN). Both networks were trained on data from a motion capture dataset and on four different prediction times: 1/2, 1/4, 1/8 and a 1/16 second. The evaluation was performed directly on the dataset to determine the prediction error. The neural networks were also evaluated on a robotic arm in a simulated environment, to show if the prediction methods would be suitable for a real-life system. Both methods show promising results when comparing the prediction error. From the simulated system, it could be concluded that with the LSTM prediction the robotic arm would generally precede the actual position. The results indicate that the methods described in this thesis report could be used as a stepping stone for a human-robot interactive system.
16
Zecha, Dan [Verfasser], and Rainer [Akademischer Betreuer] Lienhart. "Motion Kinematics and Dynamics Prediction Using Human Pose Estimation in Videos - Towards Automated, Kinematical Profiling of Swimmers and Ski Jumpers / Dan Zecha ; Betreuer: Rainer Lienhart." Augsburg : Universität Augsburg, 2020. http://d-nb.info/1215500424/34.
Full text
17
Edvardsson, Andreas, and Lucas Grönlund. "Online Predictions of Human Motion." Thesis, KTH, Skolan för teknikvetenskap (SCI), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210845.
Full textAbstract:
Collaboration between humans and robots is becoming an increasingly commonoccurrence in both industry and homes, more so with every forthcomingtechnological advance. This paper examines the possibilities of performinghuman hand movement predictions on the fly, e.g. by only using informationup to the specific moment in time of which the prediction is carried out.Specifically, data will be collected using a Kinect (v.1).The model used for the predictor developed is the Minimum Jerk model,which states that certain multi-joint reaching movements are planned in sucha way that the hand is to follow a straight path while maximizing smoothness.Extent, direction and duration of the motion are main objectives for thepredictor to determine, with a Kalman filter and curve fitting as the mainconstituents. Another assumption in this work is that a reliable start detectoris available. An experiment where five volunteers were to perform differentreaching movements was conducted.This study shows that the approach is feasible in some cases, namelyusable predictions is acquired for long movements. In the case of shortmovements the alternative of not doing any prediction was by all meansbetter.
18
Dariush, Behzad. "Predictive and measurement-oriented analysis and synthesis of human motion /." The Ohio State University, 1998. http://rave.ohiolink.edu/etdc/view?acc_num=osu1487949836206347.
Full text
19
Silva, Marco Jorge Tome da. "Simulation of human motion data using short-horizon model-predictive control." Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/43041.
Full textAbstract:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.Includes bibliographical references (p. 52-56).
Many data-driven animation techniques are capable of producing high quality motions of human characters. Few techniques, however, are capable of generating motions that are consistent with physically simulated environments. Physically simulated characters, in contrast, are automatically consistent with the environment, but their motions are often unnatural because they are difficult to control. We present a model-predictive controller that yields natural motions by guiding simulated humans toward real motion data. During simulation, the predictive component of the controller solves a quadratic program to compute the forces for a short window of time into the future. These forces are then applied by a low-gain proportional-derivative component, which makes minor adjustments until the next planning cycle. The controller is fast enough for interactive systems such as games and training simulations. It requires no precomputation and little manual tuning. The controller is resilient to mismatches between the character dynamics and the input motion, which allows it to track motion capture data even where the real dynamics are not known precisely. The same principled formulation can generate natural walks, runs, and jumps in a number of different physically simulated surroundings.
by Marco da Silva.
S.M.
20
Karst, Gregory Mark. "Multijoint arm movements: Predictions and observations regarding initial muscle activity at the shoulder and elbow." Diss., The University of Arizona, 1989. http://hdl.handle.net/10150/184920.
Full textAbstract:
Understanding the control strategies that underlie multijoint limb movements is important to researchers in motor control, robotics, and medicine. Due to dynamic interactions between limb segments, choosing appropriate muscle activations for initiating multijoint arm movements is a complex problem, and the rules by which the nervous system makes such choices are not yet understood. The aim of the dissertation studies was to evaluate some proposed initiation rules based on their ability to correctly predict which shoulder and elbow muscles initiated planar, two-joint arm movements in various directions. Kinematic and electromyographic data were collected from thirteen subjects during pointing movements involving shoulder and elbow rotations in the horizontal plane. One of the rules tested, which is based on statics, predicted that the initial muscle activity at each joint is chosen such that the hand exerts an initial force in the direction of the target, while another rule, based on dynamics, predicted initial muscle activity such that the initial acceleration of the hand is directed toward the target. For both rules, the data contradict the predicted initial shoulder muscle activity for certain movement directions. Moreover, the effects of added inertial loads predicted by the latter rule were not observed when a 1.8 kg mass was added to the limb. The results indicated, however, that empirically derived rules, based on ψ, the target direction relative to the distal segment, could predict which muscles would be chosen to initiate movement in a given direction. Furthermore, the relative timing and magnitude of initial muscle activity at the shoulder and elbow varied systematically with ψ. Thus, the target direction relative to the forearm may be an important variable in determining initial muscle activations for multijoint arm movements. These findings suggest a control scheme for movement initiation in which simple rules suffice to launch the hand in the approximate direction of the target by first specifying a basic motor output pattern, then modulating the relative timing and magnitude of that pattern.
21
Hagnell, Fredrik. "Predicting Human Movement Patterns in an Office Environment." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-188787.
Full textAbstract:
This project is built on the idea of predicting future human movement in an area. The algorithm’s predictions are based on previous movements in the area which has to be recorded somehow. For this a device with a motion sensor was setup to monitor the movement in a hallway in an office. This data was then used to test and evaluate the prediction algorithm. To give feedback about the movement and how it is changing to the people working in the office the setup device shows sentences on a monitor which describes the movement. The project resulted in a fully working application which measures people walking by, both when and how fast, and predicts future movement. Due to time constraints of the project the device was only up and running for two weeks. This is enough time to get some understanding of how well the prediction algorithm works, but a longer experiment time would have further helped the evaluation. The results showed that the algorithm can predict most of the events during the day, but is bad at predicting sudden spikes or other unusual behavior.Projektet är baserat på idén att förutse framtida mänsklig rörelse i ett område. För att noggrant kunna förutse framtida rörelse så behöver man kunna mäta tidigare rörelse. För detta så sattes en anordning upp med en rörelse detektor för att mäta rörelsen i en korridor i ett kontor. Data som samlades in användes sedan för att testa och utvärdera förutsägelse algoritmen. För att ge feed-back om rörelsen och hur den ändras till människorna som jobbade i kontoret så visade anordningen meningar på en skärm som beskrev rörelsen. Projektet resulterade i en fullt fungerade applikation som mäter folk som går förbi, både när och hur snabbt, och förutser framtida rörelse. På grund av tids begränsningar i projektet så var anordningen bara uppe och mätte data i två veckor. Detta är tillräckligt mycket tid för att få någon förståelse över hur bra förutsägelse algoritmen fungerar, men en längre experiment tid skulle ha hjälpt utvärderingen. Resultaten visade att algoritmen kan förutse de flesta händelserna under dagen, men är dålig på att förutse plötsliga spikar eller annat ovanligt beteende.
22
Lura, Derek James. "The Creation of a Robotics Based Human Upper Body Model for Predictive Simulation of Prostheses Performance." Scholar Commons, 2012. http://scholarcommons.usf.edu/etd/4133.
Full textAbstract:
This work focuses on the use of 3D motion capture data to create and optimize a robotic human body model (RHBM) to predict the inverse kinematics of the upper body. The RHBM is a 25 degrees of freedom (DoFs) upper body model with subject specific kinematic parameters. The model was developed to predict the inverse kinematics of the upper body in the simulation of a virtual person, including persons with functional limitations such as a transradial or transhumeral amputation. Motion data were collected from 14 subjects: 10 non-amputees control subjects, 1 person with a transradial amputation, and 3 persons with a transhumeral amputation, in the University of South Florida's (USF) motion analysis laboratory.
Motion capture for each subject consisted of the repetition of a series of range of motion (RoM) tasks and activities of daily living (ADLs), which were recorded using an eight camera Vicon (Oxford, UK) motion analysis system. The control subjects were also asked to repeat the motions while wearing a brace on their dominant arm. The RoM tasks consisted of elbow flexion & extension, forearm pronation & supination, shoulder flexion & extension, shoulder abduction & adduction, shoulder rotation, torso flexion & extension, torso lateral flexion, and torso rotation. The ADLs evaluated were brushing one's hair, drinking from a cup, eating with a knife and fork, lifting a laundry basket, and opening a door. The impact of bracing and prosthetic devices on the subjects' RoM, and their motion during ADLs was analyzed.
The segment geometries of the subjects' upper body were extracted directly from the motion analysis data using a functional joint center method. With this method there are no conventional or segment length differences between recorded data segments and the RHBM. This ensures the accuracy of the RHBM when reconstructing a recorded task, as the model has the same geometry as the recorded data. A detailed investigation of the weighted least norm, probability density gradient projection method, artificial neural networks was performed to optimize the redundancy RHBM inverse kinematics. The selected control algorithm consisted of a combination of the weighted least norm method and the gradient projection of the null space, minimizing the inverse of the probability density function. This method increases the accuracy of the RHBM while being suitable for a wide range of tasks and observing the required subject constraint inputs.
23
Chen, Zhuo, and 陈卓. "A methodology for trajectory based learning and prediction of human motions in visual surveillance." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2011. http://hub.hku.hk/bib/B47145985.
Full text
24
Hariri, Mahdiar. "A study of optimization-based predictive dynamics method for digital human modeling." Diss., University of Iowa, 2012. https://ir.uiowa.edu/etd/2886.
Full textAbstract:
This study develops theorems which generalize or improve the existing predictive dynamics method and implements them to simulate several motion tasks of a human model. Specifically, the problem of determination of contact forces (non-adhesive) between the environment and the digital human model is addressed. Determination of accurate contact forces is used in the calculation of joint torques and is important to account for human strength limitations in simulation of various tasks. It is shown that calculation of the contact forces based on the distance of the contact areas from the Zero Moment Point (ZMP) leads to unrealistic values for some of the forces. This is the approach that has been used in the past. In this work, necessary and sufficient constraints for modeling the non-adhesiveness of a contact area are presented through the definition of NCM (Normal Contact Moment) concepts. NCM point, constraints and stability margins are the new theoretical concepts introduced. When there is only one contact area between the body and the environment, the ZMP and the NCM point coincide. In this case, the contact forces and moments are deterministic. When there are more than one contact areas, the contact forces and moments are indeterminate. In this case, an optimization problem is defined based on the NCM constraints where contact forces and moments are treated as the unknown design variables. Here, kinematics of the motion is assumed to be known. It is shown that this approach leads to more realistic values for the contact forces and moments for a human motion task as opposed to the ZMP based approach. The proposed approach appears to be quite promising and needs to be fully integrated into the predictive dynamics approach of human motion simulation. Some other insights are obtained for the predictive dynamics approach of human motion simulation. For example, it is mathematically proved and also validated that there is a need for an individual constraint to ensure that the normal component of the resultant global forces remains compressive for non-adhesive contacts between the body and the environment. Also, the ZMP constraints and stability margins are applicable for the problems where all the contacts between the environment and the body are in one plane; however, the NCM constraints and stability margins are applicable for all types of arbitrary contacts between the body and the environment. The ZMP and NCM methods are used to model the motion of a human (soldier) performing several military tasks: Aiming, Kneeling, Going Prone and Aiming in Prone Position. New collision avoidance theorems are also presented and used in these simulations.
25
Seth, Ajay. "A Predictive Control Method for Human Upper-Limb Motion: Graph-Theoretic Modelling, Dynamic Optimization, and Experimental Investigations." Thesis, University of Waterloo, 2000. http://hdl.handle.net/10012/787.
Full textAbstract:
Optimal control methods are applied to mechanical models in order to predict the control strategies in human arm movements. Optimality criteria are used to determine unique controls for a biomechanical model of the human upper-limb with redundant actuators. The motivation for this thesis is to provide a non-task-specific method of motion prediction as a tool for movement researchers and for controlling human models within virtual prototyping environments. The current strategy is based on determining the muscle activation levels (control signals) necessary to perform a task that optimizes several physical determinants of the model such as muscular and joint stresses, as well as performance timing. Currently, the initial and final location, orientation, and velocity of the hand define the desired task. Several models of the human arm were generated using a graph-theoretical method in order to take advantage of similar system topology through the evolution of arm models. Within this framework, muscles were modelled as non-linear actuator components acting between origin and insertion points on rigid body segments. Activation levels of the muscle actuators are considered the control inputs to the arm model. Optimization of the activation levels is performed via a hybrid genetic algorithm (GA) and a sequential quadratic programming (SQP) technique, which provides a globally optimal solution without sacrificing numerical precision, unlike traditional genetic algorithms. Advantages of the underlying genetic algorithm approach are that it does not require any prior knowledge of what might be a 'good' approximation in order for the method to converge, and it enables several objectives to be included in the evaluation of the fitness function. Results indicate that this approach can predict optimal strategies when compared to benchmark minimum-time maneuvers of a robot manipulator. The formulation and integration of the aforementioned components into a working model and the simulation of reaching and lifting tasks represents the bulk of the thesis. Results are compared to motion data collected in the laboratory from a test subject performing the same tasks. Discrepancies in the results are primarily due to model fidelity. However, more complex models are not evaluated due to the additional computational time required. The theoretical approach provides an excellent foundation, but further work is required to increase the computational efficiency of the numerical implementation before proceeding to more complex models.
26
Wangerin, Spencer D. "Development and validation of a human knee joint finite element model for tissue stress and strain predictions during exercise." DigitalCommons@CalPoly, 2013. https://digitalcommons.calpoly.edu/theses/1129.
Full textAbstract:
Osteoarthritis (OA) is a degenerative condition of cartilage and is the leading cost of disability in the United States. Motion analysis experiments in combination with knee-joint finite element (FE) analysis may be used to identify exercises that maintain knee-joint osteochondral (OC) loading at safe levels for patients at high-risk for knee OA, individuals with modest OC defects, or patients rehabilitating after surgical interventions. Therefore, a detailed total knee-joint FE model was developed by modifying open-source knee-joint geometries in order to predict OC tissue stress and strain during the stance phase of gait. The model was partially validated for predicting the timing and locations of maximum contact parameters (contact pressure, contact area, and principal Green-Lagrangian strain), but over-estimated contact parameters compared with both published in vivo studies and other FE analyses of the stance phase of gait. This suggests that the model geometry and kinematic boundary conditions utilized in this FE model are appropriate, but limitations in the material properties used, as well as potentially the loading boundary conditions represent primary areas for improvement.
27
Desmet, François-Olivier. "Bioinformatique et épissage dans les pathologies humaines." Thesis, Montpellier 1, 2010. http://www.theses.fr/2010MON1T017.
Full textAbstract:
Découvert en 1977, l'épissage est une étape de maturation post-transcriptionnelle consistant à rabouter les exons et éliminer les introns d'un ARN pré-messager. Pour que l'épissage soit correctement pris en charge par l'épisome et ses protéines auxiliaires, différents signaux sont présents le long de la séquence de l'ARN pré-messager. Il est maintenant reconnu que près de la moitié des mutations pathogènes chez l'homme impactent l'épissage, aboutissant à un dysfonctionnement du gène. Il est ainsi indispensable pour les biologistes d'être capables de détecter ces signaux sur une séquence génomique.Cette thèse a donc pour but de concevoir de nouveaux algorithmes permettant d'apporter la puissance de calcul des ordinateurs au service de la biologie de l'épissage. La solution proposée, Human Splicing Finder (HSF), est capable de prédire les trois types de signaux d'épissage à partir d'une séquence quelconque extraite du génome humain. Nous avons évalué l'efficacité de prédiction d'HSF dans l'ensemble des situations associées à des mutations pathogènes pour lesquelles il a été démontré expérimentalement leur impact sur l'épissage et par rapport aux autres algorithmes de prédiction. Parallèlement à ces apports directs tant pour la connaissance des processus biologiques de l'épissage que pour le diagnostic, les nouvelles approches thérapeutiques génotype-spécifiques peuvent également bénéficier de ces nouveaux algorithmes. Ainsi HSF permet de mieux cibler les oligonucléotides anti-sens utilisés pour induire le saut d'exon dans la myopathie de Duchenne et les dysferlinopathies.La reconnaissance récente de l'intérêt majeur de l'épissage dans des domaines aussi variés que la recherche fondamentale, la thérapeutique et le diagnostic nécessitaient un point central d'accès aux signaux d'épissage. HSF a pour objet de remplir ce rôle, en étant régulièrement mis à jour pour intégrer de nouvelles connaissances, et est d'ores et déjà reconnu comme un outil de référenceDiscovered in 1977, splicing is a post-transcriptional maturation process that consists in link-ing exons together and removing introns from a pre-messanger RNA. For splicing to be cor-rectly undertaken by the spliceosome and its auxiliary proteins, several signals are located along the pre-messanger RNA sequence. Nearly half of pathogenous mutations in humans are now recognized to impact splicing and leading to a gene dysfunction. Therefore it is es-sential for biologists to detect those signals in any genomic sequence.Thus, the goals of this thesis were to conceive new algorithms: i) to identify splicing signals; ii) to predict the impact of mutations on these signals and iii) to give access to this information to researchers thanks to the power of bioinformatics. The proposed solution, Human Splicing Finder (HSF), is a web application able to predict all types of splicing signals hidden in any sequence extracted from the human genome. We demonstrated the prediction's efficiency of HSF for all situations associated with pathogenous mutations for which an impact on splicing has been experimentally demonstrated. Along with these direct benefits for the knowledge of biological processes for splicing and diagnosis, new genotype-specific therapeutic approaches can also benefit from these new algorithms. Thus, HSF allows to better target antisense olignucleotides used to induce exon skipping in Duchenne myopathy and dysferlinopathies.The recent recognition of the major interest of splicing in various domains such as fundamen-tal research, therapeutics and diagnosis needed a one stop shop for splicing signals. HSF has for object to fulfill this need, being regularly updated to integrate new knowledge and is already recognized as an international reference tool
28
Makkar, Guneet. "The Role of conventional sperm parameters, quantitative motile characteristics and acrosome reaction of spermatozoa in predicting successful outcome following artificial insemination." Hong Kong : University of Hong Kong, 2000. http://sunzi.lib.hku.hk/hkuto/record.jsp?B22505507.
Full text
29
Rengifo, cadavid Carolina. "Contrôle plateforme pour la validation du véhicule autonome sur simulateur dynamique à hautes performances." Thesis, Paris, HESAM, 2020. http://www.theses.fr/2020HESAE023.
Full textAbstract:
Les travaux présentés dans ce manuscrit s'inscrivent dans le contexte de la simulation de conduite et plus concrètement dans celui des simulateurs de conduite dynamique a hautes performances utilises pour la validation des systèmes avances et du véhicule autonome. Afin de répondre aux enjeux de performance et de perception du mouvement, nous présentons différentes approches d’amélioration des algorithmes de restitution de mouvement (MCA). L'ensemble de nos études montre que la stratégie de contrôle prédictif est le meilleur choix pour contrôler les mouvements des nouveaux simulateurs a hautes performances. Cependant, dans ce MCA l'optimisation en temps réel et le modèle de perception doivent être garantis afin améliorer l'immersion du conducteur dans l'environnement virtuel. Nous avons donc comparé différentes techniques pour résoudre les problèmes d'optimisation sous contraintes et avons propose une technique d'optimisation a partir de circuits integres, qui propose une solution intuitive et rapide au problème d'optimisation. Enfin, nous avons établi des recommandations de paramétrage des MCA en fonction du comportement de conduite auto-declare qui permet une meilleure perception du mouvement dans un simulateur de conduite, en conduite interactive et en mode autonomeThe work presented in this manuscript takes part in the context of driving simulation and more specifically in the one of dynamic driving simulators used for the validation of advanced systems and the autonomous vehicle. In order to address the issues of performance and motion perception, we have presented different approaches to improve the Motion Cueing Algorithms (MCA). All our studies show that the model predictive control (MPC) strategy is the best choice to MCA on high-performance driving simulators. Indeed, compared to other strategies, it allows to better take advantage of the workspace without endangering the simulator and/or the driver. However, in this MCA, the real-time optimization and the perception model must be guaranteed in order to improve the driver's immersion in the virtual environment. Therefore, we compared different techniques to solve constrained optimization problems. We proposed a based optimization technique, which provides an intuitive and fast solution to the MPC constrained optimization problem. Finally, we established recommendations for MCA parameterization according to the self-declared driving behavior allowing a better perception of motion in a driving simulator, in interactive driving and in autonomous mode
30
Fioravanço, Lucas Monteiro. "Human-aware Collaborative Manipulation with Reaching Motion Prediction." Master's thesis, 2021. http://hdl.handle.net/10362/125779.
Full textAbstract:
This dissertations presents a possible approach to improve human-robot interaction in an
industrial collaborative situation, where the human operator and a collaborative industrial
robot work within a shared work-space. The approach presented in this dissertation
focuses on a situation where part of the assembly process needs to be carried out by a
human operator, whose assembly station is located on a work-bench, and a robot is used
to pick and place products in specific locations on the operator’s work station. Because
those locations can be accessed both by the robot or the human operator at any time,
collisions can occur and should be avoided in order to make the process more natural
for the human operator as well as to avoid the emergency stop of the collaborative robot
which has to be restarted and thus decreases productivity.
In order to prevent those collisions the proposed system defines key-areas in each of
the locations as well as other relevant positions for the collaborative task. The system uses
a Kinect Sensor and a neural network to track the user’s hand over time and Gaussian
Mixture Models to make predictions regarding the possible destination key-area given
the observed trajectory until that moment. If a collision is predicted the robot pauses the
task being executed at the moment in order to prevent it and, once the conflict has been
resolved, resumes operation.Esta dissertação apresenta uma possível aproximação para melhorar a interação humanorobot em situações industrias colaborativas, onde um operador humano e um robot industrial colaborativo trabalham num espaço partilhado. A aproximação apresentada nesta dissertação foca situações onde parte do processo de produção deve ser realizado por um operador humano cuja área de trabalho se localiza numa mesa. É utilizado um robot de forma a colocar e retirar produtos de locais especificos da mesa de trabalho do operador. Uma vez que estes locais podem ser acedidos pelo utilizador e pelo robot a qualquer momento é possivel que ocorram colisões que devem ser evitadas, de forma a tornar a interação mais natural para o humano e evitar paragens de emergencia, que requerem que o robot colaborativo seja reiniciado manualmente e, portanto, diminuem a produtividade. De forma a prevenir essas colisões, o sistema proposto define áreas-chave nos locais onde podem ocorrer colisões e em outras localisões relevantes para a tarefa colaborativa a ser executada. A solução proposta utiliza um sensor Kinect, juntamente com uma rede neuronal para seguir a mão do operador ao longo do tempo e usa Gaussian Mixture Models para fazer previsões relativas à área de destino dada a trajetoria observada até ao momento. Se for prevista uma colisão o robot interrompe a execução da tarefa programada de forma a evitar a colisão. Uma vez o conflito resolvido, o robot retoma a tarefa do ponto onde parou.
31
MURANAGA), XU YE (AKIRA, and 葉旭 (村永旭). "On Human Motion Prediction Using Bidirectional Encoder Representations from Transformers." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/du2jv4.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
107
Pose prediction found applications in a variety of areas. However, current methods adopting recurrent neural networks suffer from error accumulation in the training stage. Furthermore, encoder-decoder architecture in general fails to predict continuous poses between the end of the encoder input and the beginning of the decoder output. Benefiting from the recent successes of the attention mechanism, in the thesis, we propose a novel method which combined the transformer encoder architecture and universal transformer. The new architecture is free of error accumulation because this architecture processes data parallelly and the weight of updating for each position is equal. Moreover, the proposed attention map helps attention mechanism to refrain the predicted poses from discontinuity. We also apply adaptive computation time algorithm to optimize the iteration numbers of performing an attention mechanism. The mean absolute loss is considered to handle human motion prediction problem in the training process on the Human3.6M dataset. Simulations show that the proposed method outperforms the main state-of-the-art approaches.
32
CHO, YU, and 卓諭. "Deep Learning Based Real-Time Human Action Recognition and Motion Prediction System." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/fw9pre.
Full textAbstract:
碩士國立臺北科技大學
電機工程系
107
In the field of machine intelligence, it is a necessary task also a challenge for machines to understand human behavior. In order to improve the efficiency of human-machine interaction, the accuracy of scene understanding or the early warning of unexpected situations, human action recognition and motion prediction become important keys. First, in the human action recognition task, this thesis regards it as a classification problem, and uses the sequence of the human body pose to classify the action labels. A simple action recognition neural network architecture is employed to achieve the purpose of real-time application. The performance of action recognition is further improved by combining the results of motion prediction. In the processing of human motion prediction, we regard it as a regression task and utilizes the pose sequence from the past time period to predict the future pose sequence results. By considering the momentum of skeleton and the estimating confidence of each joint, the mean pose problem in motion prediction can be solved in this thesis, and the discriminating ability when joints obscured is also increased. In the experimental results, the analysis experiments have been carried out the real-time system, the action recognition performance with motion prediction, and the motion prediction evaluation. It can be verified from the experimental results that the motion prediction information can improve the performance of motion recognition, and adding the features of skeleton momentum and joint confidence can also make the motion prediction show better results.
33
Ruiz, Jaime. "Predicting Endpoint of Goal-Directed Motion in Modern Desktop Interfaces using Motion Kinematics." Thesis, 2012. http://hdl.handle.net/10012/6666.
Full textAbstract:
Researchers who study pointing facilitation have identified the ability to identify--during motion--the likely target of a user's pointing gesture, as a necessary precursor to pointing facilitation in modern computer interfaces. To address this need, we develop and analyze how an understanding of the underlying characteristics of motion can enhance our ability to predict the target or endpoint of a goal-directed movement in graphical user interfaces.
Using established laws of motion and an analysis of users' kinematic profiles, we demonstrate that the initial 90% of motion is primarly balistic and submovements are limited to the last 10% of gesture movement. Through experimentation, we demonstrate that target constraint and the intended use of a target has either a minimal effect on the motion profile or affects the last 10% of motion. Therefore, we demonstrate that any technique that models the intial 90% of gesture motion will not be affected by target constraint or intended use.
Given, these results, we develop a technique to model the initial ballistic motion to predict user endpoint by adopting principles from the minimum jerk principle. Based on this principle, we derive an equation to model the initial ballistic phase of movement in order to predict movement distance and direction. We demonstrate through experimentation that we can successfully model pointing motion to identify a region of likely targets on the computer display. Next, we characterize the effects of target size and target distance on prediction accuracy. We demonstrate that there exists a linear relationship between prediction accuracy and target distance and that this relationship can be leveraged to create a probabilistic model for each target on the computer display. We then demonstrate how these probabilities could be used to enable pointing facilitation in modern computer interfaces.
Finally, we demonstrate that the results from our evaluation of our technique are supported by the current motor control literature. In addition, we show that our technique provides optimal accuracy for any optimal accuracy when prediction of motion endpoint is performed using only the ballistic components of motion and before 90% of motion distance.
34
Gonçalves, Diogo Barata. "Towards real-time recognition and prediction of human and humanoid robot locomotion modes." Master's thesis, 2018. http://hdl.handle.net/1822/59364.
Full textAbstract:
Dissertação de mestrado em Industrial Electronics and Computer EngineeringSeveral afflictions can affect a person’s ability to walk from muscular impairments, weakness or neurologic injury. In many of these cases, rehabilitation is essential for a full recovery. With the advances in the field of robotics and its bigger integration in rehabilitation, namely in the form of active orthosis and prosthesis, novel solutions to old challenges are made available. One of these challenges is the ability to use these assistive devices seamlessly without expert intervention in a subject’s daily life. Faced with this hindrance it becomes important to develop strategies that can recognize and predict human locomotion modes to allow a timely and correct response to a user’s needs from assistive devices. As such, this thesis proposes a pipeline of which the output is either a machine learning model that can recognize in real-time the user’s current locomotion mode or one that can predict a user’s walking intention. The locomotion mode recognition model can identify walking direction (forward, backward, anti-clockwise and clockwise) as well as locomotion activities (level walking, stair ascent, stair descent, ramp ascent and ramp descent) in real-time. Similarly, the intention prediction model also predicts both direction and locomotion activity intention in a timeframe that allows an assistive device to preemptively act in a seamless manner to provide the user a fluid walking ability and avoid a fall due to improper terrain traversing manner. An assessment of the required biomechanical features is done to identify the ones that best help predict or recognize the locomotion mode using feature selection methods (Principal Component Analysis, Analysis of variance-based selection, forward and backwards sequential selection). Several classification algorithms (Support Vector Machines, K-nearest neighbors, random forests and discriminant analysis) were explored and implemented to find the best performing one. These models were tested with data from healthy human subjects and a humanoid robot with a human-like gait controller. Results revealed that during the model building procedure using the Support Vector Machines algorithm with a feature selection method that combined the mRMR (minimum redundancy Maximum Relevancy) ranking technique and the forward feature selection procedure yielded the most robust and best-performing model. Direction prediction and recognition models presented an MCC (Matthews Correlation Coefficient) value of 0.98, on average, after validation showing promising results. However, and despite steady-state step type models (models classifying non-transitional steps) having an MCC value of 0.98, models involved in the classification of transitional steps, both for recognition and prediction, revealed poor results. MCC values as low as 0.61 were reported, showing that the used features were inadequate for the prediction of a subject’s gait intention. Future work will be to integrate other kinds of sensors and use different features that can rectify the classification flaws present in the obtained models in order to increase their accuracy.
Vários fatores podem afetar a capacidade de locomoção de uma pessoa desde lesões ou fraqueza musculares a lesões neurológicas. Em muito destes casos, reabilitação é essencial para uma completa recuperação. Com os avanços no campo da robótica e a sua maior integração em reabilitação, nomeadamente na forma de próteses e ortóteses ativas, novas soluções para velhos problemas tornam-se disponíveis. Um destes desafios é a habilidade de usar estes dispositivos assistivos de forma fluida e não-obstrutiva durante o dia-a-dia sem necessidade da intervenção de um especialista. Face a este problema torna-se importante desenvolver estratégias que possibilitem o reconhecimento e previsão de modos de locomoção humanos para permitir uma resposta correta e pontual de dispositivos assistivos face ás necessidades do utilizador. Como tal, esta tese propõe uma pipeline que tem como resultado um modelo de machine learning que consegue reconhecer em tempo-real o modo de locomoção enquanto acontece ou um modelo que consegue identificar a intenção de locomoção do utilizador. A pipeline delineada nesta tese permite obter um modelo que reconhece a direção de locomoção (frente, trás, anti-horário, horário) assim como a atividade locomotora (andar em terreno plano, subir escadas, descer escadas, subir rampas e descer rampas) em tempo real. A previsão de intenção também prevê tanto a direção como a atividade locomotora numa janela de tempo que permite ao dispositivo assistivo atuar sobre essa intenção. Um estudo das características biomecânicas necessárias é feito para identificar aquelas que melhor ajudam na previsão ou reconhecimento do modo de locomoção usando métodos de feature selection (Principal Component Analysis, ANOVA-based selection, forward e backwards sequential selection). Vários algoritmos de classificação (Support Vector Machines, K-nearest neighbors, Random Forests e Discriminant Analysis) foram explorados e implementados de forma a descobrir qual o melhor. Estes modelos foram testados com dados de sujeitos saudáveis e de um robô humanoide com um controlador de marcha humano. Resultados revelaram que para, a construção do modelo, o uso do algoritmo SVM e a seleção de features através da combinação dos métodos mRMR e forward feature selection resultavam no melhor e mais robusto modelo. Os modelos de classificação de direção, tato de reconhecimento como de previsão, obtiveram um valor de MCC de 0.98 em média depois da validação mostrando-se promissores. No entanto, e apesar dos modelos de reconhecimento e previsão de passos steady-state, terem obtido valores de MCC de 0.98, os modelos envolvidos na classificação de passos transicionais, tanto de reconhecimento como de previsão, obtiveram resultados fracos com valores de MCC tão baixos como 0.61, revelando que as features usadas são inadequadas para a previsão da intenção de marcha. Como trabalho futuro deverão ser integrados outros tios de sensores e usadas outras features que possam retificar as falhas de classificação presentes os modelos obtidos de forma a aumentar a sua perfromace.
35
Purkayastha, Sagar. "Analysis of human movement for a complex dynamic task: What predicts success?" Thesis, 2013. http://hdl.handle.net/1911/72025.
Full textAbstract:
This thesis identifies and analyzes successful movement strategies for the completion of a complex dynamic task. In the past it has been shown that movement strategies correlate well to performance for simple tasks. Therefore, in this thesis I
was motivated to find out if motion based metrics correlated well to performance for more complicated motor tasks. First, the Nintendo Wiimote was verified as a suitable
gaming interface enabling gross human motion capture through experimental comparisons with other gaming interfaces and precision sensors. Then, a complex motor task
was rendered in an open-source gaming environment. This environment enabled the design of a rhythmic task that could be controlled with the Wiimote while data were simultaneously recorded for later analysis. For the task, success and failure could be
explained by high correlation between two motion based performance metrics, mean absolute jerk (MAJ) and average frequency (AVF) per trial. A logistic regression analysis revealed that each subject had a range of MAJ and AVF values for being successful, outside of which they were unsuccessful. Therefore, this thesis identifies motion based performance metrics for a novel motor control task that is significantly difficult to master and the techniques used to identify successful movement strategies
can be used for predicting success for other such complex dynamic tasks.
36
Jardim, David Walter Figueira. "Human activity recognition and prediction in RGB-D videos." Doctoral thesis, 2018. http://hdl.handle.net/10071/19571.
Full textAbstract:
Reconhecimento de atividade humana é uma área de investigação multidisciplinar que tem atraído o interesse de investigadores especializados em aprendizagem automática, visão por computador e medicina. Esta área tem diversas aplicações: sistemas de vigilância, interação homem-máquina, análise de desportos, robôs colaborativos, saúde e automóveis autónomos. Capturar atividade humana apresenta dificuldades técnicas como oclusão, iluminação insuficiente, seguimento erróneo e questões éticas. O movimento humano pode ser ambíguo e com múltiplas intenções. A forma como interagimos com outros seres humanos e objetos cria uma combinação quase infinita de variações de como fazemos as coisas. O objetivo desta dissertação é desenvolver um sistema capaz de reconhecer e prever a atividade humana usando técnicas de aprendizagem automática para extrair significado de características calculadas a partir de articulações do corpo humano capturado pela câmara Kinect. Propomos uma arquitetura hierárquica e modular que realiza segmentação temporal de sequências de ações, anotação semi-supervisionada de sub-atividades utilizando técnicas de clustering, reconhecimento de sub-atividade frame-a-frame em tempo real usando classificadores binários de random decision forests logo a partir dos primeiros instantes da ação e previsão de atividade em tempo real baseada em conditional random fields para modelar a estrutura das sequências de ações para obter as futuras possibilidades.
Gravámos um novo conjunto de dados contendo sequências de ações agressivas com um total de 72 sequências, 360 amostras de 8 ações distintas realizadas por 12 sujeitos. Efetuamos testes extensivos com dois conjuntos de dados, comparando o desempenho de reconhecimento de vários classificadores supervisionados treinados com dados anotados manualmente ou com dados anotados de forma semi-supervisionada. Aprendemos como a qualidade dos conjuntos de treino afeta os resultado que dependem também da complexidade das ações que estão a ser reconhecidas. Conseguímos obter melhores resultados que algumas das abordagens existentes na literatura em reconhecimento de atividade, efetuamos o reconhecimento de forma antecipada e obtivemos resultados encorajadores na previsão de atividades.Human Activity Recognition is an interdisciplinary research area that has been attracting interest from several research communities specialized in machine learning, computer vision, and medical research. The potential applications range from surveillance systems, human computer interfaces, sports analysis, digital assistants, collaborative robots, health-care and self-driving cars. Capturing human activity presents technical difficulties like occlusion, insufficient lighting, unreliable tracking and ethical concerns. Human motion can be ambiguous and have multiple intents. The complexity of our lives and how we interact with other humans and objects prompt to a nearly infinite combination of variations in how we do things. The focus of this dissertation is to develop a system capable of recognizing and predicting human activity using machine learning techniques to extract meaning from features computed from relevant joints of the human body captured by the skeleton tracker of the Kinect sensor. We propose a modular framework that performs off-line temporal segmentation of sequences of actions, off-line semi unsupervised labeling of sub-activities via clustering techniques, real-time frame by-frame sub-activity recognition using random decision forest binary classifiers right from the very first frames of the action and real-time activity prediction with conditional random fields to model the sequential structure of sequences of actions to reason about future possibilities. We recorded a new dataset containing long sequences of aggressive actions with a total of 72 sequences, 360 samples of 8 distinct actions performed by 12 subjects. We experimented extensively with two different datasets, compared the recognition performance of several supervised classifiers trained with manually labeled data versus semi-unsupervised labeled data. We learned how the quality of the training data affects the results which also depends on the complexity of the actions being recognized. We outperformed state-ofthe-art activity recognition approaches, performed early action recognition and obtained encouraging results in activity prediction.
37
Wei-Chih, Lin. "Predicting Novel Gene Regulatory Motifs based on Hypothetical Genes in Human Genome Using Phylogenetic Footprinting." 2006. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0016-1303200709471490.
Full text
38
Lin, Wei-Chih, and 林威志. "Predicting Novel Gene Regulatory Motifs based on Hypothetical Genes in Human Genome Using Phylogenetic Footprinting." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/65161283459571999355.
Full textAbstract:
碩士國立清華大學
資訊系統與應用研究所
94
Functional genomics focuses on assigning genes into functional categories and providing a comprehensive understanding of genetic networks. Genetic networks are complicated to perform complex biological tasks. Lots of works are still working on deciphering it and forcing to higher accuracy of algorithm. But there are still about one-fourth of genes in human genome functionally indistinct and are annotated to hypothetical genes. Genes involve in the same biological process are often regulated by similar transcriptional mechanism and are likely to contain similar transcription factor binding sites (TFBS) in their proximal promoters. Functional elements tend to evolve much slower than non-functional region, as they are subjected to selective pressure. Multi-species approach is come to make sense of TFBS prediction in silico, and was used with success to identify regulatory elements in various genes. The method is so-called “Phylogenetic Footprinting’’. The work flow goes through promoter extraction, prediction, and regulatory elements detection. Thus, both hypothetical genes and cancer-related genes are the inputs for testing. In this thesis, I analyzed the promoter region of hypothetical genes of Homo sapiens which are homologous to other organism, and provide a web service for biologists to analyze genetic networks between different organisms easily. Finally, the results are interesting because of discovering several conserved elements within some hypothetical genes and cancer-related genes, and supplying the highly conserved regulatory elements from different taxonomic nodes.