Dissertations / Theses on the topic 'Robots – Apprentissage automatique'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Robots – Apprentissage automatique.'
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.
Ahle, Elmar. "Autonomous systems : a cognitive oriented approach applied to mobile robotics /." Aachen : Shaker, 2007. http://catalogue.bnf.fr/ark:/12148/cb41447189p.
Full textZennir, Youcef. "Apprentissage par renforcement et systèmes distribués : application à l'apprentissage de la marche d'un robot hexapode." Lyon, INSA, 2004. http://theses.insa-lyon.fr/publication/2004ISAL0034/these.pdf.
Full textThe goal of this thesis is to study and to develop reinforcement learning techniques in order a hexapod robot to learn to walk. The main assumption on which this work is based is that effective gaits can be obtained as the control of the movements is distributed on each leg rather than centralised in a single decision centre. A distributed approach of the Q-learning technique is adopted in which the agents contributing to the same global objective perform their own learning process taking into account or not the other agents. The centralised and distributed approaches are compared. Different simulations and tests are carried out so as to generate stable periodic gaits. The influence of the learning parameters on the quality of the gaits are studied. The walk appears as an emerging phenomenon from the individual movements of the legs. Problems of fault tolerance and lack of state information are investigated. Finally it is verified that with the developed algorithm the simulated robot learns how to reach a desired trajectory while controlling its posture
Paléologue, Victor. "Teaching Robots Behaviors Using Spoken Language in Rich and Open Scenarios." Thesis, Sorbonne université, 2019. http://www.theses.fr/2019SORUS458.
Full textSocial robots like Pepper are already found "in the wild". Their behaviors must be adapted for each use case by experts. Enabling the general public to teach new behaviors to robots may lead to better adaptation at lesser cost. In this thesis, we study a cognitive system and a set of robotic behaviors allowing home users of Pepper robots to teach new behaviors as a composition of existing behaviors, using solely the spoken language. Homes are open worlds and are unpredictable. In open scenarios, a home social robot should learn about its environment. The purpose of such a robot is not restricted to learning new behaviors or about the environment: it should provide entertainment or utility, and therefore support rich scenarios. We demonstrate the teaching of behaviors in these unique conditions: the teaching is achieved by the spoken language on Pepper robots deployed in homes, with no extra device and using its standard system, in a rich and open scenario. Using automatic speech transcription and natural language processing, our system recognizes unpredicted teachings of new behaviors, and a explicit requests to perform them. The new behaviors may invoke existing behaviors parametrized with objects learned in other contexts, and may be defined as parametric. Through experiments of growing complexity, we show conflicts between behaviors in rich scenarios, and propose a solution based on symbolic task planning and priorization rules to resolve them. The results rely on qualitative and quantitative analysis and highlight the limitations of our solution, but also the new applications it enables
Lucidarme, Philippe. "Apprentissage et adaptation pour des ensembles de robots réactifs coopérants." Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 2003. http://tel.archives-ouvertes.fr/tel-00641563.
Full textRafflin, catherine. "Conception d'un système de programmation et de commande de robots mobiles par apprentissage." Montpellier 2, 1995. http://www.theses.fr/1995MON20093.
Full textXia, Chen. "Apprentissage Intelligent des Robots Mobiles dans la Navigation Autonome." Thesis, Ecole centrale de Lille, 2015. http://www.theses.fr/2015ECLI0026/document.
Full textModern robots are designed for assisting or replacing human beings to perform complicated planning and control operations, and the capability of autonomous navigation in a dynamic environment is an essential requirement for mobile robots. In order to alleviate the tedious task of manually programming a robot, this dissertation contributes to the design of intelligent robot control to endow mobile robots with a learning ability in autonomous navigation tasks. First, we consider the robot learning from expert demonstrations. A neural network framework is proposed as the inference mechanism to learn a policy offline from the dataset extracted from experts. Then we are interested in the robot self-learning ability without expert demonstrations. We apply reinforcement learning techniques to acquire and optimize a control strategy during the interaction process between the learning robot and the unknown environment. A neural network is also incorporated to allow a fast generalization, and it helps the learning to converge in a number of episodes that is greatly smaller than the traditional methods. Finally, we study the robot learning of the potential rewards underneath the states from optimal or suboptimal expert demonstrations. We propose an algorithm based on inverse reinforcement learning. A nonlinear policy representation is designed and the max-margin method is applied to refine the rewards and generate an optimal control policy. The three proposed methods have been successfully implemented on the autonomous navigation tasks for mobile robots in unknown and dynamic environments
Soula, Hédi Favrel Joel Beslon Guillaume. "Dynamique et plasticité dans les réseaux de neurones à impulsions étude du couplage temporel réseau / agent / environnement /." Villeurbanne : Doc'INSA, 2005. http://docinsa.insa-lyon.fr/these/pont.php?id=soula.
Full textSoula, Hédi. "Dynamique et plasticité dans les réseaux de neurones à impulsions : étude du couplage temporel réseau / agent / environnement." Lyon, INSA, 2005. http://theses.insa-lyon.fr/publication/2005ISAL0056/these.pdf.
Full textAn «artificial life » approach is conducted in order to assess the neural basis of behaviours. Behaviour is the consequence of a good concordance between the controller, the agent’s sensori-motors capabilities and the environment. Within a dynamical system paradigm, behaviours are viewed as attractors in the perception/action space – derived from the composition of the internal and external dynamics. Since internal dynamics is originated by the neural dynamics, learning behaviours therefore consists on coupling external and internal dynamics by modifying network’s free parameters. We begin by introducing a detailed study of the dynamics of large networks of spiking neurons. In spontaneous mode (i. E. Without any input), these networks have a non trivial functioning. According to the parameters of the weight distribution and provided independence hypotheses, we are able to describe completely the spiking activity. Among other results, a bifurcation is predicted according to a coupling factor (the variance of the distribution). We also show the influence of this parameter on the chaotic dynamics of the network. To learn behaviours, we use a biologically plausible learning paradigm – the Spike-Timing Dependent Plasticity (STDP) that allows us to couple neural and external dynamics. Applying shrewdly this learning law enables the network to remain “at the edge of chaos” which corresponds to an interesting state of activity for learning. In order to validate our approach, we use these networks to control an agent whose task is to avoid obstacles using only the visual flow coming from its linear camera. We detail the results of the learning process for both simulated and real robotics platform
Salaün, Camille. "Learning models to control redundancy in robotics." Paris 6, 2010. http://www.theses.fr/2010PA066238.
Full textBenureau, Fabien. "Self Exploration of Sensorimotor Spaces in Robots." Thesis, Bordeaux, 2015. http://www.theses.fr/2015BORD0072/document.
Full textDevelopmental robotics has begun in the last fifteen years to study robots that havea childhood—crawling before trying to run, playing before being useful—and that are basing their decisions upon a lifelong and embodied experience of the real-world. In this context, this thesis studies sensorimotor exploration—the discovery of a robot’s own body and proximal environment—during the early developmental stages, when no prior experience of the world is available. Specifically, we investigate how to generate a diversity of effects in an unknown environment. This approach distinguishes itself by its lack of user-defined reward or fitness function, making it especially suited for integration in self-sufficient platforms. In a first part, we motivate our approach, formalize the exploration problem, define quantitative measures to assess performance, and propose an architectural framework to devise algorithms. through the extensive examination of a multi-joint arm example, we explore some of the fundamental challenges that sensorimotor exploration faces, such as high-dimensionality and sensorimotor redundancy, in particular through a comparison between motor and goal babbling exploration strategies. We propose several algorithms and empirically study their behaviour, investigating the interactions with developmental constraints, external demonstrations and biologicallyinspired motor synergies. Furthermore, because even efficient algorithms can provide disastrous performance when their learning abilities do not align with the environment’s characteristics, we propose an architecture that can dynamically discriminate among a set of exploration strategies. Even with good algorithms, sensorimotor exploration is still an expensive proposition— a problem since robots inherently face constraints on the amount of data they are able to gather; each observation takes a non-negligible time to collect. [...] Throughout this thesis, our core contributions are algorithms description and empirical results. In order to allow unrestricted examination and reproduction of all our results, the entire code is made available. Sensorimotor exploration is a fundamental developmental mechanism of biological systems. By decoupling it from learning and studying it in its own right in this thesis, we engage in an approach that casts light on important problems facing robots developing on their own
Bideaux, Eric. "Stan : systeme de transport a apprentissage neuronal. application de la vision omnidirectionnelle a la localisation d'un robot mobile autonome." Besançon, 1995. http://www.theses.fr/1995BESA2008.
Full textArora, Ankuj. "Apprentissage du modèle d'action pour une interaction socio-communicative des hommes-robots." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAM081/document.
Full textDriven with the objective of rendering robots as socio-communicative, there has been a heightened interest towards researching techniques to endow robots with social skills and ``commonsense'' to render them acceptable. This social intelligence or ``commonsense'' of the robot is what eventually determines its social acceptability in the long run.Commonsense, however, is not that common. Robots can, thus, only learn to be acceptable with experience. However, teaching a humanoid the subtleties of a social interaction is not evident. Even a standard dialogue exchange integrates the widest possible panel of signs which intervene in the communication and are difficult to codify (synchronization between the expression of the body, the face, the tone of the voice, etc.). In such a scenario, learning the behavioral model of the robot is a promising approach. This learning can be performed with the help of AI techniques. This study tries to solve the problem of learning robot behavioral models in the Automated Planning and Scheduling (APS) paradigm of AI. In the domain of Automated Planning and Scheduling (APS), intelligent agents by virtue require an action model (blueprints of actions whose interleaved executions effectuates transitions of the system state) in order to plan and solve real world problems. During the course of this thesis, we introduce two new learning systems which facilitate the learning of action models, and extend the scope of these new systems to learn robot behavioral models. These techniques can be classified into the categories of non-optimal and optimal. Non-optimal techniques are more classical in the domain, have been worked upon for years, and are symbolic in nature. However, they have their share of quirks, resulting in a less-than-desired learning rate. The optimal techniques are pivoted on the recent advances in deep learning, in particular the Long Short Term Memory (LSTM) family of recurrent neural networks. These techniques are more cutting edge by virtue, and produce higher learning rates as well. This study brings into the limelight these two aforementioned techniques which are tested on AI benchmarks to evaluate their prowess. They are then applied to HRI traces to estimate the quality of the learnt robot behavioral model. This is in the interest of a long term objective to introduce behavioral autonomy in robots, such that they can communicate autonomously with humans without the need of ``wizard'' intervention
MOGA, SORIN DANIEL. "Apprendre par imitation : une nouvelle voie d'apprentissage pour les robots autonomes." Cergy-Pontoise, 2000. http://www.theses.fr/2000CERG0111.
Full textMartinez, Margarit Aleix. "Apprentissage visuel dans un système de vision active : application dans un contexte de robotique et reconnaissance du visage." Paris 8, 1998. http://www.theses.fr/1998PA081521.
Full textLatulippe, Maxime. "Calage robuste et accéléré de nuages de points en environnements naturels via l'apprentissage automatique." Thesis, Université Laval, 2013. http://www.theses.ulaval.ca/2013/30226/30226.pdf.
Full textLocalization of a mobile robot is crucial for autonomous navigation. Using laser scanners, this can be facilitated by the pairwise alignment of consecutive scans. For this purpose, landmarks called descriptors are generally effective as they facilitate point matching. However, we show that in some natural environments, many of them are likely to be unreliable. The presence of these unreliable descriptors adversely affects the performances of the alignment process. Therefore, we propose to filter unreliable descriptors as a prior step to alignment. Our approach uses a fast machine learning algorithm, trained on-the-fly under the positive and unlabeled learning paradigm without the need for human intervention. Our results show that the number of descriptors can be significantly reduced, while increasing the proportion of reliable ones, thus speeding up and improving the robustness of the scan alignment process.
Langlois, Julien. "Vision industrielle et réseaux de neurones profonds : application au dévracage de pièces plastiques industrielles." Thesis, Nantes, 2019. http://www.theses.fr/2019NANT4010/document.
Full textThis work presents a pose estimation method from a RGB image of industrial parts placed in a bin. In a first time, neural networks are used to segment a certain number of parts in the scene. After applying an object mask to the original image, a second network is inferring the local depth of the part. Both the local pixel coordinates of the part and the local depth are used in two networks estimating the orientation of the object as a quaternion and its translation on the Z axis. Finally, a registration module working on the back-projected local depth and the 3D model of the part is refining the pose inferred from the previous networks. To deal with the lack of annotated real images in an industrial context, an data generation process is proposed. By using various light parameters, the dataset versatility allows to anticipate multiple challenging exploitation scenarios within an industrial environment
Chatzilygeroudis, Konstantinos. "Micro-Data Reinforcement Learning for Adaptive Robots." Thesis, Université de Lorraine, 2018. http://www.theses.fr/2018LORR0276/document.
Full textRobots have to face the real world, in which trying something might take seconds, hours, or even days. Unfortunately, the current state-of-the-art reinforcement learning algorithms (e.g., deep reinforcement learning) require big interaction times to find effective policies. In this thesis, we explored approaches that tackle the challenge of learning by trial-and-error in a few minutes on physical robots. We call this challenge “micro-data reinforcement learning”. In our first contribution, we introduced a novel learning algorithm called “Reset-free Trial-and-Error” that allows complex robots to quickly recover from unknown circumstances (e.g., damages or different terrain) while completing their tasks and taking the environment into account; in particular, a physical damaged hexapod robot recovered most of its locomotion abilities in an environment with obstacles, and without any human intervention. In our second contribution, we introduced a novel model-based reinforcement learning algorithm, called Black-DROPS that: (1) does not impose any constraint on the reward function or the policy (they are treated as black-boxes), (2) is as data-efficient as the state-of-the-art algorithm for data-efficient RL in robotics, and (3) is as fast (or faster) than analytical approaches when several cores are available. We additionally proposed Multi-DEX, a model-based policy search approach, that takes inspiration from novelty-based ideas and effectively solved several sparse reward scenarios. In our third contribution, we introduced a new model learning procedure in Black-DROPS (we call it GP-MI) that leverages parameterized black-box priors to scale up to high-dimensional systems; for instance, it found high-performing walking policies for a physical damaged hexapod robot (48D state and 18D action space) in less than 1 minute of interaction time. Finally, in the last part of the thesis, we explored a few ideas on how to incorporate safety constraints, robustness and leverage multiple priors in Bayesian optimization in order to tackle the micro-data reinforcement learning challenge. Throughout this thesis, our goal was to design algorithms that work on physical robots, and not only in simulation. Consequently, all the proposed approaches have been evaluated on at least one physical robot. Overall, this thesis aimed at providing methods and algorithms that will allow physical robots to be more autonomous and be able to learn in a handful of trials
Marin, Didier. "Méthodes d'apprentissage pour l'interaction physique homme-robot : application à l'assistance robotisée pour le transfert assis-debout." Paris 6, 2013. http://www.theses.fr/2013PA066293.
Full textSit-to-stand is a task that becomes increasingly difficult with aging. It is however necessary for an autonomous life, since it precedes walking. Physical assistance robotics offers solutions that provide an active assistance in the realization of motor tasks. It gives the possibility to adapt the assistance to the specific needs of each user. Our work proposes and implements a mechanism for automatic adaptation of an assistance robot behaviour to its user. The provided assistance is evaluated using a confort criterion which is specific to the task. The adaptation consists in an optimisation of control parameters using Reinforcement Learning methods. This approach is tested on smart walker prototypes, with healthy subjects and patients
Geisert, Mathieu. "Optimal control and machine learning for humanoid and aerial robots." Thesis, Toulouse, INSA, 2018. http://www.theses.fr/2018ISAT0011/document.
Full textWhat are the common characteristics of humanoid robots and quadrotors? Well, not many… Therefore, this thesis focuses on the development of algorithms allowing to dynamically control a robot while staying generic with respect to the model of the robot and the task that needs to be solved. Numerical optimal control is good candidate to achieve such objective. However, it suffers from several difficulties such as a high number of parameters to tune and a relatively important computation time. This document presents several ameliorations allowing to reduce these problems. On one hand, the tasks can be ordered according to a hierarchy and solved with an appropriate algorithm to lower the number of parameters to tune. On the other hand, machine learning can be used to initialize the optimization solver or to generate a simplified model of the robot, and therefore can be used to decrease the computation time
Kaushik, Rituraj. "Data-Efficient Robot Learning using Priors from Simulators." Electronic Thesis or Diss., Université de Lorraine, 2020. http://www.theses.fr/2020LORR0105.
Full textAs soon as the robots step out in the real and uncertain world, they have to adapt to various unanticipated situations by acquiring new skills as quickly as possible. Unfortunately, on robots, current state-of-the-art reinforcement learning (e.g., deep-reinforcement learning) algorithms require large interaction time to train a new skill. In this thesis, we have explored methods to allow a robot to acquire new skills through trial-and-error within a few minutes of physical interaction. Our primary focus is to incorporate prior knowledge from a simulator with real-world experiences of a robot to achieve rapid learning and adaptation. In our first contribution, we propose a novel model-based policy search algorithm called Multi-DEX that (1) is capable of finding policies in sparse reward scenarios (2) does not impose any constraints on the type of policy or the type of reward function and (3) is as data-efficient as state-of-the-art model-based policy search algorithm in non-sparse reward scenarios. In our second contribution, we propose a repertoire-based online learning algorithm called APROL which allows a robot to adapt to physical damages (e.g., a damaged leg) or environmental perturbations (e.g., terrain conditions) quickly and solve the given task. In this work, we use several repertoires of policies generated in simulation for a subset of possible situations that the robot might face in real-world. During the online learning, the robot automatically figures out the most suitable repertoire to adapt and control the robot. We show that APROL outperforms several baselines including the current state-of-the-art repertoire-based learning algorithm RTE by solving the tasks in much less interaction times than the baselines. In our third contribution, we introduce a gradient-based meta-learning algorithm called FAMLE. FAMLE meta-trains the dynamical model of the robot from simulated data so that the model can be adapted to various unseen situations quickly with the real-world observations. By using FAMLE with a model-predictive control framework, we show that our approach outperforms several model-based and model-free learning algorithms, and solves the given tasks in less interaction time than the baselines
Pastor, Philippe. "Étude et application des méthodes d'apprentissage pour la navigation d'un robot en environnement inconnu." Toulouse, ENSAE, 1995. http://www.theses.fr/1995ESAE0013.
Full textBlanchet, Katleen. "Au coeur de l’interaction humain-robot collaboratif : comment concevoir une assistance personnalisée au profil utilisateur ?" Electronic Thesis or Diss., Institut polytechnique de Paris, 2021. http://www.theses.fr/2021IPPAS001.
Full textThe transformation of production plants is accelerating, driven by advances in collaborative robotics and data science. As a result, the organisation of work is changing, directly affecting the working conditions of operators. Loss of autonomy, information overload, increased pace, operators have to change their habits and learn to collaborate with the robot. In this context, the aim of this research work is to improve the operators quality of life at work, while performing a physical collaborative task, by means of user profile-based assistance. In the literature, the assistance mainly relies on external observation devices, causes of stress, and proposes exclusively a priori-based adjustments of the robot's behaviour. Thus, these assistance do not dynamically adapt to human behaviour variations. In order to overcome these challenges, this study presents two contributions. Firstly, we propose a methodology for extracting high-level information on the user profile from the robot raw signals, which is applied to expertise. We then introduce a hybrid approach to profile-based assistance which combines human-centered reinforcement learning and symbolic logic (ontology and reasoning) to guide operators towards skill improvement. This synergy guarantees online adaptation to user needs while reducing the learning process. Then, we extend the robotic assistance with informative assistance. We have demonstrated, through simulation and experiments in real conditions on three robotic usecases, the consistency of our profile as well as the positive effect of the assistance on the skills acquisition. We thereby create a more favourable environment for professional satisfaction by reducing the mental workload
Paquier, Williams. "Apprentissage ouvert de représentations et de fonctionalités en robotique : analyse, modèles et implémentation." Toulouse 3, 2004. http://www.theses.fr/2004TOU30233.
Full textAutonomous acquisition of representations and functionalities by a machine address several theoretical questions. Today’s autonomous robots are developed around a set of functionalities. Their representations of the world are deduced from the analysis and modeling of a given problem, and are initially given by the developers. This limits the learning capabilities of robots. In this thesis, we propose an approach and a system able to build open-ended representation and functionalities. This system learns through its experimentations of the environment and aims to augment a value function. Its objective consists in acting to reactivate the representations it has already learnt to connote positively. An analysis of the generalization capabilities to produce appropriate actions enable define a minimal set of properties needed by such a system. The open-ended representation system is composed of a network of homogeneous processing units and is based on position coding. The meaning of a processing unit depends on its position in the global network. This representation system presents similarities with the principle of numeration by position. A representation is given by a set of active units. This system is implemented in a suite of software called NeuSter, which is able to simulate million unit networks with billions of connections on heterogeneous clusters of POSIX machines. .
Munzer, Thibaut. "Représentations relationnelles et apprentissage interactif pour l'apprentissage efficace du comportement coopératif." Thesis, Bordeaux, 2017. http://www.theses.fr/2017BORD0574/document.
Full textThis thesis presents new approaches toward efficient and intuitive high-level plan learning for cooperative robots. More specifically this work study Learning from Demonstration algorithm for relational domains. Using relational representation to model the world, simplify representing concurrentand cooperative behavior.We have first developed and studied the first algorithm for Inverse ReinforcementLearning in relational domains. We have then presented how one can use the RAP formalism to represent Cooperative Tasks involving a robot and a human operator. RAP is an extension of the Relational MDP framework that allows modeling concurrent activities. Using RAP allow us to represent both the human and the robot in the same process but also to model concurrent robot activities. Under this formalism, we have demonstrated that it is possible to learn behavior, as policy and as reward, of a cooperative team. Prior knowledge about the task can also be used to only learn preferences of the operator.We have shown that, using relational representation, it is possible to learn cooperative behaviors from a small number of demonstration. That these behaviors are robust to noise, can generalize to new states and can transfer to different domain (for example adding objects). We have also introduced an interactive training architecture that allows the system to make fewer mistakes while requiring less effort from the human operator. By estimating its confidence the robot is able to ask for instructions when the correct activity to dois unsure. Lastly, we have implemented these approaches on a real robot and showed their potential impact on an ecological scenario
Dermy, Oriane. "Prédiction du mouvement humain pour la robotique collaborative : du geste accompagné au mouvement corps entier." Thesis, Université de Lorraine, 2018. http://www.theses.fr/2018LORR0227/document.
Full textThis thesis lies at the intersection between machine learning and humanoid robotics, under the theme of human-robot interaction and within the cobotics (collaborative robotics) field. It focuses on prediction for non-verbal human-robot interactions, with an emphasis on gestural interaction. The prediction of the intention, understanding, and reproduction of gestures are therefore central topics of this thesis. First, the robots learn gestures by demonstration: a user grabs its arm and makes it perform the gestures to be learned several times. The robot must then be able to reproduce these different movements while generalizing them to adapt them to the situation. To do so, using its proprioceptive sensors, it interprets the perceived signals to understand the user's movement in order to generate similar ones later on. Second, the robot learns to recognize the intention of the human partner based on the gestures that the human initiates. The robot can then perform gestures adapted to the situation and corresponding to the user’s expectations. This requires the robot to understand the user’s gestures. To this end, different perceptual modalities have been explored. Using proprioceptive sensors, the robot feels the user’s gestures through its own body: it is then a question of physical human-robot interaction. Using visual sensors, the robot interprets the movement of the user’s head. Finally, using external sensors, the robot recognizes and predicts the user’s whole body movement. In that case, the user wears sensors (in our case, a wearable motion tracking suit by XSens) that transmit his posture to the robot. In addition, the coupling of these modalities was studied. From a methodological point of view, the learning and the recognition of time series (gestures) have been central to this thesis. In that aspect, two approaches have been developed. The first is based on the statistical modeling of movement primitives (corresponding to gestures) : ProMPs. The second adds Deep Learning to the first one, by using auto-encoders in order to model whole-body gestures containing a lot of information while allowing a prediction in soft real time. Various issues were taken into account during this thesis regarding the creation and development of our methods. These issues revolve around: the prediction of trajectory durations, the reduction of the cognitive and motor load imposed on the user, the need for speed (soft real-time) and accuracy in predictions
Cruz, maya Arturo. "The Role of Personality, Memory, and Regulatory Focus for Human-Robot Interaction." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLY002/document.
Full textIn the domain of Human-Robot Interaction, and more specifically in the social robotics field, companion robots are more and more part of our daily lives and they have a great potential for helping people in their daily activities, especially in tasks that need one-on-one interaction. This scenario where robots are sharing the same environment with the humans and interact with them can be beneficial but it can also present some negative effects like generating stress on the human users, this is also the case of the social facilitation effect, aborded at the beggining of this work.Having robots helping us with our daily activities leads to the need of endowing them with social capabilities in order to adapt their behavior to their users, environment, and tasks. Nevertheless, how to achieve this adaptation remains a challenge.In order to address these research questions, "How to achieve lifelong learning and adaptation for personalized Human-Robot Interaction?" and "What is the role of personality, memory, and regulatory focus in HRI?",we propose the use of the Big 5 personality traits model in order to adapt the robot's behavior to the profile of the users. Moreover, our system contains an implementation of the OCC Model, and an Episodic-like Memory, in order to generate a natural behavior, being capable of remembering past events and behaving accordingly. We present several experimental studies, where we test our system, and where we analyze the link between the human user's personality traits and robot's behavior. The generated stress on the users was measured by using external sensors such as a thermal camera and a GSR sensor. Our proposed system showed to be effective in generating a robot behavior adapted to users personality. We found some relations between personality, user preferences and task performance, which are detailed in this work. Our studies showed that people with high conscientiousness have greater task performance than people with low conscientiousness. Also, that introverted people were more influenced to perform a task than extroverted people. Also, we observed an increase on user stress, caused by a robot with a machine-like voice.Besides of adapting to the users preferences, we wanted our system to be able to generate robot behaviors capable ofpersuading effectively their users in achieving the tasks they need to do (i.e. taking medication, calling family members, etc). For this reason, we propose the use of the Regulatory Focus theory, which concentrate on the inclinations that people have when taking decisions, and how to increase the motivation on people to achieve an objective. We conducted several experiments in order to validate this theory in the context of human-robot interaction. Our results show that robot behaviors based on the Regulatory Focus Theory, including body gestures and speech speed, are effective in persuading users to accomplish a task. We also found an increase on user stress when the robot did not match the user Chronic Regulatory State.We conclude that the topics aborded on this thesis, that is to say: Personality, Memory and Regulatory Focus, have to be included in the design of robot behaviors, ir order to have more efficient robots on persuasive tasks, and less stressing to their users
Carpentier, Justin. "Computational foundations of anthropomorphic locomotion." Thesis, Toulouse 3, 2017. http://www.theses.fr/2017TOU30376/document.
Full textAnthropomorphic locomotion is a complex process that involves a very large number of degrees of freedom, the human body having more than three hundred joints against thirty in humanoid robots. Taken as a whole, these degrees of freedom show a certain coherence making it possible to set the anthropomorphic system in motion and maintain its equilibrium, in order to avoid falling. This thesis highlights the computational foundations behind this orchestration. It introduces a unified mathematical framework allowing both the study of human locomotion and the generation of locomotive trajectories for humanoid robots. This framework consists of a reduction of the body-complete dynamics of the system to consider only its projection around the center of gravity, also called centroid dynamics. Although reduced, we show that this centroidal dynamics plays a central role in the understanding and formation of locomotive movements. To do this, we first establish the observability conditions of this dynamic, that is to say that we show to what extent this data can be apprehended from sensors commonly used in biomechanics and robotics. Based on these observability conditions, we propose an estimator able to reconstruct the unbiased position of the center of gravity. From this estimator and the acquisition of walking motions on various subjects, we highlight the presence of a cycloidal pattern of the center of gravity in the sagittal plane when the human is walking nominally, that is, to say without thinking. The presence of this motif suggests the existence of a motor synergy hitherto unknown, supporting the theory of a general coordination of movements during locomotion. The last contribution of this thesis is on multi-contact locomotion. Humans have remarkable agility to perform locomotive movements that require joint use of the arms and legs, such as when climbing a rock wall. How to equip humanoid robots with such capabilities? The difficulty is certainly not technological, since current robots are able to develop sufficient mechanical powers. Their performances, evaluated both in terms of quality of movement and computing time, remain very limited. In this thesis, we address the problem of generating multi-contact trajectories in the form of an optimal control problem. The interest of this formulation is to start from the reduced model of centroid dynamics while responding to equilibrium constraints. The original idea is to maximize the likelihood of this reduced dynamic with respect to body-complete dynamics. It is based on learning a measurement of occupation that reflects the kinematic and dynamic capabilities of the robot. It is effective: the resulting algorithmic is compatible with real-time applications. The approach has been successfully evaluated on the humanoid robot HRP-2, on several modes of locomotion, thus demonstrating its versatility
Melnyk, Artem. "Perfectionnement des algorithmes de contrôle-commande des robots manipulateur électriques en interaction physique avec leur environnement par une approche bio-inspirée." Thesis, Cergy-Pontoise, 2014. http://www.theses.fr/2014CERG0745/document.
Full textAutomated production lines integrate robots which are isolated from workers, so there is no physical interaction between a human and robot. In the near future, a humanoid robot will become a part of the human environment as a companion to help or work with humans. The aspects of coexistence always presuppose physical and social interaction between a robot and a human. In humanoid robotics, further progress depends on knowledge of cognitive mechanisms of interpersonal interaction as robots physically and socially interact with humans. An illustrative example of interpersonal interaction is an act of a handshake that plays a substantial social role. The particularity of this form of interpersonal interaction is that it is based on physical and social couplings which lead to synchronization of motion and efforts. Studying a handshake for robots is interesting as it can expand their behavioral properties for interaction with a human being in more natural way. The first chapter of this thesis presents the state of the art in the fields of social sciences, medicine and humanoid robotics that study the phenomenon of a handshake. The second chapter is dedicated to the physical nature of the phenomenon between humans via quantitative measurements. A new wearable system to measure a handshake was built in Donetsk National Technical University (Ukraine). It consists of a set of several sensors attached to the glove for recording angular velocities and gravitational acceleration of the hand and forces in certain points of hand contact during interaction. The measurement campaigns have shown that there is a phenomenon of mutual synchrony that is preceded by the phase of physical contact which initiates this synchrony. Considering the rhythmic nature of this phenomenon, the controller based on the models of rhythmic neuron of Rowat-Selverston, with learning the frequency during interaction was proposed and studied in the third chapter. Chapter four deals with the experiences of physical human-robot interaction. The experimentations with robot arm Katana show that it is possible for a robot to learn to synchronize its rhythm with rhythms imposed by a human during handshake with the proposed model of a bio-inspired controller. A general conclusion and perspectives summarize and finish this work
Malik, Muhammad Usman. "Learning multimodal interaction models in mixed societies A novel focus encoding scheme for addressee detection in multiparty interaction using machine learning algorithms." Thesis, Normandie, 2020. http://www.theses.fr/2020NORMIR18.
Full textHuman -Agent Interaction and Machine learning are two different research domains. Human-agent interaction refers to techniques and concepts involved in developing smart agents, such as robots or virtual agents, capable of seamless interaction with humans, to achieve a common goal. Machine learning, on the other hand, exploits statistical algorithms to learn data patterns. The proposed research work lies at the crossroad of these two research areas. Human interactions involve multiple modalities, which can be verbal such as speech and text, as well as non-verbal i.e. facial expressions, gaze, head and hand gestures, etc. To mimic real-time human-human interaction within human-agent interaction,multiple interaction modalities can be exploited. With the availability of multimodal human-human and human-agent interaction corpora, machine learning techniques can be used to develop various interrelated human-agent interaction models. In this regard, our research work proposes original models for addressee detection, turn change and next speaker prediction, and finally visual focus of attention behaviour generation, in multiparty interaction. Our addressee detection model predicts the addressee of an utterance during interaction involving more than two participants. The addressee detection problem has been tackled as a supervised multiclass machine learning problem. Various machine learning algorithms have been trained to develop addressee detection models. The results achieved show that the proposed addressee detection algorithms outperform a baseline. The second model we propose concerns the turn change and next speaker prediction in multiparty interaction. Turn change prediction is modeled as a binary classification problem whereas the next speaker prediction model is considered as a multiclass classification problem. Machine learning algorithms are trained to solve these two interrelated problems. The results depict that the proposed models outperform baselines. Finally, the third proposed model concerns the visual focus of attention (VFOA) behaviour generation problem for both speakers and listeners in multiparty interaction. This model is divided into various sub-models that are trained via machine learning as well as heuristic techniques. The results testify that our proposed systems yield better performance than the baseline models developed via random and rule-based approaches. The proposed VFOA behavior generation model is currently implemented as a series of four modules to create different interaction scenarios between multiple virtual agents. For the purpose of evaluation, recorded videos for VFOA generation models for speakers and listeners, are presented to users who evaluate the baseline, real VFOA behaviour and proposed VFOA models on the various naturalness criteria. The results show that the VFOA behaviour generated via the proposed VFOA model is perceived more natural than the baselines and as equally natural as real VFOA behaviour
Lallée, Stéphane. "Towards a distributed, embodied and computational theory of cooperative interaction." Thesis, Lyon 1, 2012. http://www.theses.fr/2012LYO10052/document.
Full textRobots will gradually integrate our homes wielding the role of companions, humanoids ornot. In order to cope with this status they will have to adapt to the user, especially bylearning knowledge or skills from him that they may lack. In this context, their interactionshould be natural and evoke the same cooperative mechanisms that humans use. At thecore of those mechanisms is the concept of action: what is an action, how do humansrecognize them, how they produce or describe them? The modeling of aspects of thesefunctionalities will be the basis of this thesis and will allow the implementation of higherlevel cooperative mechanisms. One of these is the ability to handle “shared plans” whichallow two (or more) individuals to cooperate in order to reach a goal shared by all.Throughout the thesis I will attempt to make links between the human development ofthese capabilities, their neurophysiology, and their robotic implementation. As a result ofthis work, I will present a fundamental difference between the representation of knowledgein humans and machines, still in the framework of cooperative interaction: the possibledissociation of a robot body and its cognition, which is not easily imaginable for humans.This dissociation will lead me to explore the “shared experience framework, a situationwhere a central artificial cognition manages the shared knowledge of multiple beings, eachof them owning some kind of individuality. In the end this phenomenon will interrogate thevarious philosophies of mind by asking the question of the attribution of a mind to amachine and the consequences of such a possibility regarding the human mind
Coupeté, Eva. "Reconnaissance de gestes et actions pour la collaboration homme-robot sur chaîne de montage." Thesis, Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLEM062/document.
Full textCollaborative robots are becoming more and more present in our everyday life. In particular, within the industrial environment, they emerge as one of the preferred solution to make assembly line in factories more flexible, cost-effective and to reduce the hardship of the operators’ work. However, to enable a smooth and efficient collaboration, robots should be able to understand their environment and in particular the actions of the humans around them.With this aim in mind, we decided to study technical gestures recognition. Specifically, we want the robot to be able to synchronize, adapt its speed and understand if something unexpected arises.We considered two use-cases, one dealing with copresence, the other with collaboration. They are both inspired by existing task on automotive assembly lines.First, for the co-presence use case, we evaluated the feasibility of technical gestures recognition using inertial sensors. We obtained a very good result (96% of correct recognition with one operator) which encouraged us to follow this idea.On the collaborative use-case, we decided to focus on non-intrusive sensors to minimize the disturbance for the operators and we chose to use a depth-camera. We filmed the operators with a top view to prevent most of the potential occultations.We introduce an algorithm that tracks the operator’s hands by calculating the geodesic distances between the points of the upper body and the top of the head.We also design and evaluate an approach based on discrete Hidden Markov Models (HMM) taking the hand positions as an input to recognize technical gestures. We propose a method to adapt our system to new operators and we embedded inertial sensors on tools to refine our results. We obtain the very good result of 90% of correct recognition in real time for 13 operators.Finally, we formalize and detail a complete methodology to realize technical gestures recognition on assembly lines
Sigaud, Olivier. "Automatisme et subjectivité : l'anticipation au coeur de l'expérience." Paris 1, 2002. http://www.theses.fr/2002PA010658.
Full textDesrochers, Benoît. "Simultaneous localization and mapping in unstructured environments : a set-membership approach." Thesis, Brest, École nationale supérieure de techniques avancées Bretagne, 2018. http://www.theses.fr/2018ENTA0006/document.
Full textThis thesis deals with the simultaneous localization and mapping (SLAM) problem in unstructured environments, i.e. which cannot be described by geometrical features. This type of environment frequently occurs in an underwater context.Unlike classical approaches, the environment is not described by a collection of punctual features or landmarks, but directly by sets. These sets, called shapes, are associated with physical features such as the relief, some textures or, in a more symbolic way, the space free of obstacles that can be sensed around a robot. In a theoretical point of view, the SLAM problem is formalized as an hybrid constraint network where the variables are vectors and subsets of Rn. Whereas an uncertain real number is enclosed in an interval, an uncertain shape is enclosed in an interval of sets. The main contribution of this thesis is the introduction of a new formalism, based on interval analysis, able to deal with these domains. As an application, we illustrate our method on a SLAM problem based on bathymetric data acquired by an autonomous underwater vehicle (AUV)
Ramezanpanah, Zahra. "Bi-lateral interaction between a humanoid robot and a human in mixed reality." Electronic Thesis or Diss., université Paris-Saclay, 2020. http://www.theses.fr/2020UPASG039.
Full textThis thesis can be divided into two parts: action recognition and emotion recognition. Each part is done in two method, classic method of Machine Learning and deep network. In the Action Recognition section, we first defined a local descriptor based on the LMA, to describe the movements. LMA is an algorithm to describe a motion by using its four components: Body, Space, Shape and Effort. Since the only goal in this part is gesture recognition, only the first three factors have been used. The DTW, algorithm is implemented to find the similarities of the curves obtained from the descriptor vectors obtained by the LMA method. Finally SVM, algorithm is used to train and classify the data. In the second part of this section, we constructed a new descriptor based on the geometric coordinates of different parts of the body to present a movement. To do this, in addition to the distances between hip centre and other joints of the body and the changes of the quaternion angles in time, we define the triangles formed by the different parts of the body and calculated their area. We also calculate the area of the single conforming 3-D boundary around all the joints of the body. At the end we add the velocity of different joint in the proposed descriptor. We used LSTM to evaluate this descriptor. In second section of this thesis, we first presented a higher-level module to identify the inner feelings of human beings by observing their body movements. In order to define a robust descriptor, two methods are carried out: The first method is the LMA, which by adding the "Effort" factor has become a robust descriptor, which describes a movement and the state in which it was performed. In addition, the second on is based on a set of spatio-temporal features. In the continuation of this section, a pipeline of recognition of expressive motions is proposed in order to recognize the emotions of people through their gestures by the use of machine learning methods. A comparative study is made between these 2 methods in order to choose the best one. The second part of this part consists of a statistical study based on human perception in order to evaluate the recognition system as well as the proposed motion descriptor
Raiola, Gennaro. "Co-manipulation with a library of virtual guides." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLY001/document.
Full textRobots have a fundamental role in industrial manufacturing. They not only increase the efficiency and the quality of production lines, but also drastically decrease the work load carried out by humans.However, due to the limitations of industrial robots in terms of flexibility, perception and safety, their use is limited to well-known structured environment. Moreover, it is not always cost-effective to use industrial autonomous robots in small factories with low production volumes.This means that human workers are still needed in many assembly lines to carry out specific tasks.Therefore, in recent years, a big impulse has been given to human-robot co-manipulation.By allowing humans and robots to work together, it is possible to combine the advantages of both; abstract task understanding and robust perception typical of human beings with the accuracy and the strength of industrial robots.One successful method to facilitate human-robot co-manipulation, is the Virtual Guides approach which constrains the motion of the robot along only certain task-relevant trajectories. The so realized virtual guide acts as a passive tool that improves the performances of the user in terms of task time, mental workload and errors.The innovative aspect of our work is to present a library of virtual guides that allows the user to easily select, generate and modify the guides through an intuitive haptic interaction with the robot.We demonstrated in two industrial tasks that these innovations provide a novel and intuitive interface for joint human-robot completion of tasks
Génevé, Lionel. "Système de déploiement d'un robot mobile autonome basé sur des balises." Thesis, Strasbourg, 2017. http://www.theses.fr/2017STRAD024/document.
Full textThis thesis is part of a project which aims at developing an autonomous mobile robot able to perform specific tasks in a preset area. To ease the setup of the system, radio-frequency beacons providing range measurements with respect to the robot are set up beforehand on the borders of the robot’s workspace. The system deployment consists in two steps, one for learning the environment, then a second, where the robot executes its tasks autonomously. These two steps require to solve the localization and simultaneous localization and mapping problems for which several solutions are proposed and tested in simulation and on real datasets. Moreover, to ease the setup and improve the system performances, a beacon placement algorithm is presented and tested in simulation in order to validate in particular the improvement of the localization performances
Le, Goff Léni. "Bootstrapping Robotic Ecological Perception with Exploration and Interactions." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS219.
Full textRobotics has reached a high accuracy on many tasks, like for instance manipulation or navigation. But most of the studies are based on a deep analysis of the problem to solve by the robot designer. These approaches are thus limited to the environment considered by the robot designer, i.e. to a closed environment. Robotics research community is now addressing the issue to allow robots to autonomously achieve tasks in realistic open environments. Such environments are complex and dynamic, like for instance human everyday environment which seems simple but vary a lot from one place to another. In this kind of contexts, the robots must be able to adapt to new situations which were not forecasted by the engineers who designed the robot. Our research work is focused on the development of an adaptive ecological perception for a robotic system. An agent ecological perception defines how it perceives the real world environment through its sensing and acting capabilities. According to J.J. Gibson who has initiated ecological psychology, humans and animals perceive the world through the actions that they can use. Thus, providing a robotic system with the skill to bootstrap autonomously its perception when facing a new unknown situation, would allow the system to be highly adaptive. Our goal is to provide the robot with the capacity to learn a first representation of its surrounding which would work on any environment. This would allow the robot to learn new representations from unknown situations. It is proposed to generate this ability through an interactive perception method. Interactive perception methods take advantage from action to build or enhance representations of the world and then exploit these representations to have more accurate actions. This relation between action and perception can be easily formalized thanks to affordances. Affordance is a concept introduced by J.J. Gibson which is a relationship between visual features, agent skills, and possible effects. The system collects data from an environment by interacting with it thanks to a specific action associated to an expected effect. With these data a probabilistic classifier is trained online to build a perceptual map. This map represents the areas that generate the expected effect when the action is applied. Therefore, the map is called a relevance map. Several relevance maps could be built according to different actions and effects, the sum of these maps represents a rich perception of what the robot can do on its surrounding. We name this final map an affordances map as it allows the robot to perceive the environment through the actions it can use. Our methods was tested on the PR2 robots
Grizou, Jonathan. "Apprentissage simultané d'une tâche nouvelle et de l'interprétation de signaux sociaux d'un humain en robotique." Thesis, Bordeaux, 2014. http://www.theses.fr/2014BORD0146/document.
Full textThis thesis investigates how a machine can be taught a new task from unlabeled humaninstructions, which is without knowing beforehand how to associate the human communicative signals withtheir meanings. The theoretical and empirical work presented in this thesis provides means to createcalibration free interactive systems, which allow humans to interact with machines, from scratch, using theirown preferred teaching signals. It therefore removes the need for an expert to tune the system for eachspecific user, which constitutes an important step towards flexible personalized teaching interfaces, a key forthe future of personal robotics.Our approach assumes the robot has access to a limited set of task hypotheses, which include the task theuser wants to solve. Our method consists of generating interpretation hypotheses of the teaching signalswith respect to each hypothetic task. By building a set of hypothetic interpretation, i.e. a set of signallabelpairs for each task, the task the user wants to solve is the one that explains better the history of interaction.We consider different scenarios, including a pick and place robotics experiment with speech as the modalityof interaction, and a navigation task in a brain computer interaction scenario. In these scenarios, a teacherinstructs a robot to perform a new task using initially unclassified signals, whose associated meaning can bea feedback (correct/incorrect) or a guidance (go left, right, up, ...). Our results show that a) it is possible tolearn the meaning of unlabeled and noisy teaching signals, as well as a new task at the same time, and b) itis possible to reuse the acquired knowledge about the teaching signals for learning new tasks faster. Wefurther introduce a planning strategy that exploits uncertainty from the task and the signals' meanings toallow more efficient learning sessions. We present a study where several real human subjects controlsuccessfully a virtual device using their brain and without relying on a calibration phase. Our system identifies, from scratch, the target intended by the user as well as the decoder of brain signals.Based on this work, but from another perspective, we introduce a new experimental setup to study howhumans behave in asymmetric collaborative tasks. In this setup, two humans have to collaborate to solve atask but the channels of communication they can use are constrained and force them to invent and agree ona shared interaction protocol in order to solve the task. These constraints allow analyzing how acommunication protocol is progressively established through the interplay and history of individual actions
Lesort, Timothée. "Continual Learning : Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes." Thesis, Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAE003.
Full textHumans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn similarly. They often rely on data rigorously preprocessed to learn solutions to specific problems such as classification or regression.In particular, they forget their past learning experiences if trained on new ones.Therefore, artificial neural networks are often inept to deal with real-lifesuch as an autonomous-robot that have to learn on-line to adapt to new situations and overcome new problems without forgetting its past learning-experiences.Continual learning (CL) is a branch of machine learning addressing this type of problems.Continual algorithms are designed to accumulate and improve knowledge in a curriculum of learning-experiences without forgetting.In this thesis, we propose to explore continual algorithms with replay processes.Replay processes gather together rehearsal methods and generative replay methods.Generative Replay consists of regenerating past learning experiences with a generative model to remember them. Rehearsal consists of saving a core-set of samples from past learning experiences to rehearse them later. The replay processes make possible a compromise between optimizing the current learning objective and the past ones enabling learning without forgetting in sequences of tasks settings.We show that they are very promising methods for continual learning. Notably, they enable the re-evaluation of past data with new knowledge and the confrontation of data from different learning-experiences. We demonstrate their ability to learn continually through unsupervised learning, supervised learning and reinforcement learning tasks
Bredèche, Nicolas. "Ancrage de lexique et perceptions : changements de représentation et apprentissage dans le contexte d'un agent situé et mobile." Paris 11, 2002. http://www.theses.fr/2002PA112225.
Full textIn Artificial Intelligence, the symbol grounding problem is considered as an important issue regarding the meaning of symbols used by an artificial agent. Our work is concerned with the grounding of symbols for a situated mobile robot that navigates through a real world environment. In this setting, the main problem the robot encounters is to ground symbols given by a human teacher that refers to physical entities (e. G. A door, a human, etc. ). Grounding such a lexicon is a difficult task because of the intrinsic nature of the environment: it is dynamic, complex and noisy. Moreover, one specific symbol (e. G. "door") may refer to different physical objects in size, shape or colour while the robot may acquire only a small number of examples for each symbol. Also, it is not possible to rely on ad-hoc physical models of symbols due to the great number of symbols that may be grounded. Thus, the problem is to define how to build a grounded representation in such a context. In order to address this problem, we have reformulated the symbol grounding problem as a supervised learning problem. We present an approach that relies on the use of abstraction operators. Thanks to these operators, information on granularity and structural configuration is extracted from the perceptions in order to case the building of an anchor. For each symbol, the appropriate definition for these operators is found out thanks to successive changes of representation that provide an efficient and adapted anchor. In order to implement our approach, we have developed PLIC and WMplic which are successfully used for long term symbol grounding by a PIONEER2 DX mobile robot in the corridors of the Computer Sciences Lab of the University of Paris 6
Duminy, Nicolas. "Découverte et exploitation de la hiérarchie des tâches pour apprendre des séquences de politiques motrices par un robot stratégique et interactif." Thesis, Lorient, 2018. http://www.theses.fr/2018LORIS513/document.
Full textEfforts are made to make robots operate more and more in complex unbounded ever-changing environments, alongside or even in cooperation with humans. Their tasks can be of various kinds, can be hierarchically organized, and can also change dramatically or be created, after the robot deployment. Therefore, those robots must be able to continuously learn new skills, in an unbounded, stochastic and high-dimensional space. Such environment is impossible to be completely explored during the robot's lifetime, therefore it must be able to organize its exploration and decide what is more important to learn and how to learn it, using metrics such as intrinsic motivation guiding it towards the most interesting tasks and strategies. This becomes an even bigger challenge, when the robot is faced with tasks of various complexity, some requiring a simple action to be achieved, other needing a sequence of actions to be performed. We developed a strategic intrinsically motivated learning architecture, called Socially Guided Intrinsic Motivation for Sequences of Actions through Hierarchical Tasks (SGIM-SAHT), able to learn the mapping between its actions and their outcomes on the environment. This architecture, is capable to organize its learning process, by deciding which outcome to focus on, and which strategy to use among autonomous and interactive ones. For learning hierarchical set of tasks, the architecture was provided with a framework, called procedure framework, to discover and exploit the task hierarchy and combine skills together in a task-oriented way. The use of sequences of actions enabled such a learner to adapt the complexity of its actions to that of the task at hand
Ghorpade, Vijaya Kumar. "3D Semantic SLAM of Indoor Environment with Single Depth Sensor." Thesis, Université Clermont Auvergne (2017-2020), 2017. http://www.theses.fr/2017CLFAC085/document.
Full textIntelligent autonomous actions in an ordinary environment by a mobile robot require maps. A map holds the spatial information about the environment and gives the 3D geometry of the surrounding of the robot to not only avoid collision with complex obstacles, but also selflocalization and for task planning. However, in the future, service and personal robots will prevail and need arises for the robot to interact with the environment in addition to localize and navigate. This interaction demands the next generation robots to understand, interpret its environment and perform tasks in human-centric form. A simple map of the environment is far from being sufficient for the robots to co-exist and assist humans in the future. Human beings effortlessly make map and interact with environment, and it is trivial task for them. However, for robots these frivolous tasks are complex conundrums. Layering the semantic information on regular geometric maps is the leap that helps an ordinary mobile robot to be a more intelligent autonomous system. A semantic map augments a general map with the information about entities, i.e., objects, functionalities, or events, that are located in the space. The inclusion of semantics in the map enhances the robot’s spatial knowledge representation and improves its performance in managing complex tasks and human interaction. Many approaches have been proposed to address the semantic SLAM problem with laser scanners and RGB-D time-of-flight sensors, but it is still in its nascent phase. In this thesis, an endeavour to solve semantic SLAM using one of the time-of-flight sensors which gives only depth information is proposed. Time-of-flight cameras have dramatically changed the field of range imaging, and surpassed the traditional scanners in terms of rapid acquisition of data, simplicity and price. And it is believed that these depth sensors will be ubiquitous in future robotic applications. In this thesis, an endeavour to solve semantic SLAM using one of the time-of-flight sensors which gives only depth information is proposed. Starting with a brief motivation in the first chapter for semantic stance in normal maps, the state-of-the-art methods are discussed in the second chapter. Before using the camera for data acquisition, the noise characteristics of it has been studied meticulously, and properly calibrated. The novel noise filtering algorithm developed in the process, helps to get clean data for better scan matching and SLAM. The quality of the SLAM process is evaluated using a context-based similarity score metric, which has been specifically designed for the type of acquisition parameters and the data which have been used. Abstracting semantic layer on the reconstructed point cloud from SLAM has been done in two stages. In large-scale higher-level semantic interpretation, the prominent surfaces in the indoor environment are extracted and recognized, they include surfaces like walls, door, ceiling, clutter. However, in indoor single scene object-level semantic interpretation, a single 2.5D scene from the camera is parsed and the objects, surfaces are recognized. The object recognition is achieved using a novel shape signature based on probability distribution of 3D keypoints that are most stable and repeatable. The classification of prominent surfaces and single scene semantic interpretation is done using supervised machine learning and deep learning systems. To this end, the object dataset and SLAM data are also made publicly available for academic research
Massé, Benoît. "Etude de la direction du regard dans le cadre d'interactions sociales incluant un robot." Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAM055/document.
Full textRobots are more and more used in a social context. They are required notonly to share physical space with humans but also to interact with them. Inthis context, the robot is expected to understand some verbal and non-verbalambiguous cues, constantly used in a natural human interaction. In particular,knowing who or what people are looking at is a very valuable information tounderstand each individual mental state as well as the interaction dynamics. Itis called Visual Focus of Attention or VFOA. In this thesis, we are interestedin using the inputs from an active humanoid robot – participating in a socialinteraction – to estimate who is looking at whom or what.On the one hand, we want the robot to look at people, so it can extractmeaningful visual information from its video camera. We propose a novelreinforcement learning method for robotic gaze control. The model is basedon a recurrent neural network architecture. The robot autonomously learns astrategy for moving its head (and camera) using audio-visual inputs. It is ableto focus on groups of people in a changing environment.On the other hand, information from the video camera images are used toinfer the VFOAs of people along time. We estimate the 3D head poses (lo-cation and orientation) for each face, as it is highly correlated with the gazedirection. We use it in two tasks. First, we note that objects may be lookedat while not being visible from the robot point of view. Under the assump-tion that objects of interest are being looked at, we propose to estimate theirlocations relying solely on the gaze direction of visible people. We formulatean ad hoc spatial representation based on probability heat-maps. We designseveral convolutional neural network models and train them to perform a re-gression from the space of head poses to the space of object locations. Thisprovide a set of object locations from a sequence of head poses. Second, wesuppose that the location of objects of interest are known. In this context, weintroduce a Bayesian probabilistic model, inspired from psychophysics, thatdescribes the dependency between head poses, object locations, eye-gaze di-rections, and VFOAs, along time. The formulation is based on a switchingstate-space Markov model. A specific filtering procedure is detailed to inferthe VFOAs, as well as an adapted training algorithm.The proposed contributions use data-driven approaches, and are addressedwithin the context of machine learning. All methods have been tested on pub-licly available datasets. Some training procedures additionally require to sim-ulate synthetic scenarios; the generation process is then explicitly detailed
Hasson, Cyril. "Modélisation des mécanismes émotionnels pour un robot autonome : perspective développementale et sociale." Phd thesis, Université de Cergy Pontoise, 2011. http://tel.archives-ouvertes.fr/tel-00904481.
Full textDubois, Mathieu. "Méthodes probabilistes basées sur les mots visuels pour la reconnaissance de lieux sémantiques par un robot mobile." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00679650.
Full textPetit, Maxime. "Raisonnement et planification développementale d'un robot via une interaction enactive avec un humain." Phd thesis, Université Claude Bernard - Lyon I, 2014. http://tel.archives-ouvertes.fr/tel-01015288.
Full textArsicault, Marc. "Suivi de trajectoires planes par auto-apprentissage en vue d'une application de soudage robotise de toles ondees sur longerons de renfort." Poitiers, 1989. http://www.theses.fr/1989POIT2264.
Full textPicardat, Jean-François. "Controle d'execution, comprehension et apprentissage de plans d'actions : developpement de la methode de la table triangulaire." Toulouse 3, 1987. http://www.theses.fr/1987TOU30122.
Full textLathuiliere, Stéphane. "Modèles profonds de régression et applications à la vision par ordinateur pour l'interaction homme-robot." Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAM026/document.
Full textIn order to interact with humans, robots need to perform basic perception taskssuch as face detection, human pose estimation or speech recognition. However, in order have a natural interaction with humans, the robot needs to modelhigh level concepts such as speech turns, focus of attention or interactions between participants in a conversation. In this manuscript, we follow a top-downapproach. On the one hand, we present two high-level methods that model collective human behaviors. We propose a model able to recognize activities thatare performed by different groups of people jointly, such as queueing, talking.Our approach handles the general case where several group activities can occur simultaneously and in sequence. On the other hand, we introduce a novelneural network-based reinforcement learning approach for robot gaze control.Our approach enables a robot to learn and adapt its gaze control strategy inthe context of human-robot interaction. The robot is able to learn to focus itsattention on groups of people from its own audio-visual experiences.Second, we study in detail deep learning approaches for regression prob-lems. Regression problems are crucial in the context of human-robot interaction in order to obtain reliable information about head and body poses or theage of the persons facing the robot. Consequently, these contributions are really general and can be applied in many different contexts. First, we proposeto couple a Gaussian mixture of linear inverse regressions with a convolutionalneural network. Second, we introduce a Gaussian-uniform mixture model inorder to make the training algorithm more robust to noisy annotations. Finally,we perform a large-scale study to measure the impact of several architecturechoices and extract practical recommendations when using deep learning approaches in regression tasks. For each of these contributions, a strong experimental validation has been performed with real-time experiments on the NAOrobot or on large and diverse data-sets
Tanguy, Roger. "Un reseau mobiles autonomes pour l'apprentissage de la communication." Paris 6, 1987. http://www.theses.fr/1987PA066640.
Full text