Academic literature on the topic 'HD maps'

In a world where autonomous driving cars are becoming increasingly more common, creating an adequate infrastructure for this new technology is essential. This includes building and labeling high-definition (HD) maps accurately and efficiently. Today, the process of creating HD maps requires a lot of human input, which takes time and is prone to errors. In this paper, we propose a novel method capable of generating labelled HD maps from raw sensor data. We implemented and tested our methods on several urban scenarios using data collected from our test vehicle. The results show that the proposed deep learning based method can produce highly accurate HD maps. This approach speeds up the process of building and labeling HD maps, which can make meaningful contribution to the deployment of autonomous vehicles.

With growing attention being devoted to autonomous vehicle (AV) safety, people have recently attached importance to high-definition (HD) maps. HD maps are not limited by environmental factors and can limit AVs driving in certain lanes. HD maps provide accurate auxiliary information on factors such as road geometry, traffic sign placement, and traffic topology. Nowadays, most HD maps are made from point clouds data, and this data contains accurate 3D position information. However, the production costs associated with HD maps are substantial. This article proposes an algorithm that reduces a great amount of time and human resource. The algorithm is divided into three phases, lane lines’ extraction from point clouds, modelling lane lines with attributes, and building OpenDRIVE file. The algorithm extracts lane lines resting on intensity value within the range of roads. Next, it models lane lines by cubic spline interpolation with the result of first phase, and build the OpenDRIVE file following the announcement of OpenDRIVE. The final result is compared with the verified HD map from the mapping company to analyze the accuracy. The root mean square (RMSE) obtained were 0.069 and 0.079 m for 2D and 3D maps, respectively.

Microarray patches (MAPs) have the potential to be a safer, more acceptable, easier to use and more cost-effective method for administration of vaccines when compared to the needle and syringe. Since MAPs deliver vaccine to the dermis and epidermis, a degree of local immune response at the site of application is expected. In a phase 1 clinical trial (ACTRN 12618000112268), the Vaxxas high-density MAP (HD-MAP) was used to deliver a monovalent, split inactivated influenza virus vaccine into the skin. HD-MAP immunisation led to significantly enhanced humoral responses on day 8, 22 and 61 compared with IM injection of a quadrivalent commercial seasonal influenza vaccine (Afluria Quadrivalent®). Here, the aim was to analyse cellular responses to HD-MAPs in the skin of trial subjects, using flow cytometry and immunohistochemistry. HD-MAPs were coated with a split inactivated influenza virus vaccine (A/Singapore/GP1908/2015 [H1N1]), to deliver 5 μg haemagglutinin (HA) per HD-MAP. Three HD-MAPs were applied to the volar forearm (FA) of five healthy volunteers (to achieve the required 15 μg HA dose), whilst five control subjects received three uncoated HD-MAPs (placebo). Local skin response was recorded for over 61 days and haemagglutination inhibition antibody titres (HAI) were assessed on days 1, 4, 8, 22, and 61. Skin biopsies were taken before (day 1), and three days after HD-MAP application (day 4) and analysed by flow-cytometry and immunohistochemistry to compare local immune subset infiltration. HD-MAP vaccination with 15 μg HA resulted in significant HAI antibody titres compared to the placebo group. Application of uncoated placebo HD-MAPs resulted in mild erythema and oedema in most subjects, that resolved by day 4 in 80% of subjects. Active, HA-coated HD-MAP application resulted in stronger erythema responses on day 4, which resolved between days 22–61. Overall, these erythema responses were accompanied by an influx of immune cells in all subjects. Increased cell infiltration of CD3+, CD4+, CD8+ T cells as well as myeloid CD11b+ CD11c+ and non-myeloid CD11b- dendritic cells were observed in all subjects, but more pronounced in active HD-MAP groups. In contrast, CD19+/CD20+ B cell counts remained unchanged. Key limitations include the use of an influenza vaccine, to which the subjects may have had previous exposure. Different results might have been obtained with HD-MAPs inducing a primary immune response. In conclusion, influenza vaccine administered to the forearm (FA) using the HD-MAP was well-tolerated and induced a mild to moderate skin response with lymphocytic infiltrate at the site of application.

Abstract. High-definition maps (HD Maps) becomes a trend supporting autonomous vehicles (AVs) which provides accurate auxiliary information about geometries of road, such as center lines of lanes, geometries of roads, traffic signs, etc. It is not restricted by the severe environment, lack of Global Navigation Satellite System (GNSS) signal, or torrential rain, for Avs; furthermore, the standard of HD Maps is defined as tens of centimeters positioning level. However, the production cost of HD Maps is enormous involving human resources and time. The general way of producing HD Maps is to vectorize the roads from point clouds to shapefiles and import them into Geographic Information System (GIS) software to generate HD Maps. In order to simplify this complicated process, this article purposes an algorithm to automated generate high-definition maps from road marks’ data which is extracted from point clouds. The methodology in this article is mainly dived into three steps, extraction of road marks, classify lane lines, and modelling OpenDRIVE files. The achieved 2D and 3D accuracies of proposed algorithm in first fields are about 0.069 m in 2D and 0.107 m, respectively.

The upraise of autonomous driving technologies asks for maps characterized bya broad range of features and quality parameters, in contrast to traditional navigation maps which in most cases are enriched graph-based models. This paper tackles several uncertainties within the domain of HD Maps. The authors give an overview about the current state in extracting road features from aerial imagery for creating HD maps, before shifting the focus of the paper towards remote sensing technology. Possible data sources and their relevant parameters are listed. A random forest classifier is used, showing how these data can deliver HD Maps on a country-scale, meeting specific quality parameters.

As one of the key enabling technologies for automated driving, High Definition (HD) Maps have become a major research focus in recent years. While increasing research effort has been directed toward HD Map development, a comprehensive review of the overall conceptual framework and development status is still lacking. In this study, we start with a brief review of the highlights of navigation map history, and then present an extensive literature review of HD Map development for automated driving, focusing on HD Map structure, functionalities, and accuracy requirements as well as standardisation aspects. In addition, this study conducts an analysis of HD Map-based vehicle localisation. The numerical results demonstrate the potential capabilities of HD Maps. Some recommendations for further investigation are made.

Abstract. High Definition Map (HD Map) is one of the essential components for autonomous driving systems. The HD Map helps localization, detection, prediction and planning of autonomous driving cars in combination with GNSS and IMU sensors. A lot of map providers and major car manufactures have been trying the development of efficient ways to create and update HD Maps with centimeter-level precision. However, there are no open standard ways well-established to produce HD Map at the present time. Since 2013, we have been being engaged in the research projects and actual production projects on the creation of HD Maps. This paper introduces practical knowledge on five key steps of our large-scale production lines for HD Map creation, which are 1) Mobile Mapping System (MMS) survey, 2) 3D plotting, 3) Feature attributes editing and road network topology building, 4) Format conversion and 5) Quality assurance.

Abstract. Over the decades, autonomous driving technology has attracted a lot of attention and is under rapid development. However, it still suffers from inadequate accuracy in a certain area, such as the urban area, Global Navigation Satellite System (GNSS) hostile area, due to the multipath interference or Non-Line-of-Sight (NLOS) reception. In order to realize fully autonomous applications, High Definition Maps (HD Maps) become extra assisted information for autonomous vehicles to improve road safety in recent years. Compared with the conventional navigation maps, the accuracy requirement in HD Maps, which is 20 cm in the horizontal direction and 30 cm in 3D space, is considerably higher than the conventional one. Additionally, HD Maps consist of rich and high accurate road traffic information and road elements. For the requirement of high accuracy, conducting a Mobile Laser Scanning (MLS) system is an appropriate method to collect the geospatial data accurately and efficiently. Nowadays, digital vector maps are constructed by digitalizing manually on the collected data. However, the manual process spends a lot of manpower and is not efficient and practical for a large field. Therefore, this paper proposes to automatically construct the crucial road elements, such as road edge, lane line, and centerline, to generate the HD Maps based on point clouds collected by the MMS from the surveying company. The RMSEs in the horizontal direction of the road edge, lane line, and centerline are all lower than 30 cm in 3D space.

Several groups at this meeting are presenting maps of the spatial distribution of either brightness or effective temperature in the photospheres of rapidly-rotating, late-type stars. It is generally believed that structure seen in these maps traces the magnetic topology, in analogy with the Sun. We expect the structure of the outer atmospheres (i.e., chromosphere and corona) of these stars to be even more directly tied to the magnetic topology; the magnetic structure is three-dimensional. In order to probe the radial dimension of stellar atmospheres, we need to combine maps of the spatial distribution of emission from chromospheres and coronae with these detailed photospheric maps.Along with collaborators at Armagh, Catania, Boulder, Paris, Helsinki, and Stony Brook, I have been obtaining high-dispersion ultraviolet spectra of several rapidly-rotating, late-type stars using the IUE spacecraft. I discuss results for two stars, El Eridani and HD 199178, for which photospheric maps are presented elsewhere at this conference.