Accurate vehicle self-localization in high definition map dataset

Zang, Andi; Li, Zichen; Doria, David; Trajcevski, Goce

doi:10.1145/3149092.3149094

Cited by 30 publications

(10 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data sent from the vehicles include the vehicle ID, vehicle position, speed, direction of travel, time stamp, etc. The vehicle position is obtained by using vehicle position information obtained by GPS or scan matching [21][22][23]. In this paper, each vehicle and edge server are referred to as a node, and each node has a unique ID, like the ITS systems that are being standardized in Europe [24].…”

Section: Proposed Methodsmentioning

confidence: 99%

Efficient Access Method for Multi-access Edge Servers in Dynamic Map Systems

Hosono

Maki

Watanabe

et al. 2021

Preprint

View full text Add to dashboard Cite

Research and development on connected cars equipped with communication functions is being conducted, and dynamic maps are being researched and developed as an information and communication platform for cooperative automatic driving. There is a concern about scalability when dynamic maps are constructed on a cloud server to aggregate a wide range of vehicle information. The problem can be alleviated by deploying edge servers that divide the geographic area where vehicles travel and manage each of them. The IP addresses of the edge servers need to be resolved on the basis of the location information of the moving vehicles. Using TCP improves reliability but reduces efficiency because the vehicles move. In this study, we developed a novel method for accessing edge servers that achieves higher reliability and efficiency by adopting UDP using anycast for transmission from vehicle to edge server and implementing a retransmission function. The effectiveness of this access method was verified by using a vehicle driving simulation.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Efficient Access Method for Multi-access Edge Servers in Dynamic Map Systems

Hosono

Maki

Watanabe

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…For instance, GNSS-based sensors that integrate Global Positioning System (GPS) are still susceptible to the latter's localisation inaccuracies [114]. GNSS-based lane-level self-localisation methods are also susceptible to "multi-path interference" that occurs when the GPS signal is obstructed by external objects [113], satellite clock errors and inevitable inconsistencies between GNSS coordinates and High Definition (HD) Map coordinates [115]. Alternatively, visual sensors are less costly but are still inaccurate in adverse weather conditions and busy backgrounds, as they have been designed to operate on more clear images and videos [116][117][118].…”

Section: Perceptionmentioning

confidence: 99%

Algorithmic Decision-Making in AVs: Understanding Ethical and Technical Concerns for Smart Cities

Lim

Taeihagh

2019

Sustainability

View full text Add to dashboard Cite

Autonomous Vehicles (AVs) are increasingly embraced around the world to advance smart mobility and more broadly, smart, and sustainable cities. Algorithms form the basis of decision-making in AVs, allowing them to perform driving tasks autonomously, efficiently, and more safely than human drivers and offering various economic, social, and environmental benefits. However, algorithmic decision-making in AVs can also introduce new issues that create new safety risks and perpetuate discrimination. We identify bias, ethics, and perverse incentives as key ethical issues in the AV algorithms' decision-making that can create new safety risks and discriminatory outcomes. Technical issues in the AVs' perception, decision-making and control algorithms, limitations of existing AV testing and verification methods, and cybersecurity vulnerabilities can also undermine the performance of the AV system. This article investigates the ethical and technical concerns surrounding algorithmic decision-making in AVs by exploring how driving decisions can perpetuate discrimination and create new safety risks for the public. We discuss steps taken to address these issues, highlight the existing research gaps and the need to mitigate these issues through the design of AV's algorithms and of policies and regulations to fully realise AVs' benefits for smart and sustainable cities.Sustainability 2019, 11, 5791 2 of 28 surroundings and algorithms that process the data, make, and execute driving decisions through the vehicle's actuators. The quality of data retrieved by the AV's sensors is critical for decision-making [21], and the efficiency, precision and reliability of decision-making algorithms allows AVs to surpass the typical human driver in performing driving tasks [22]. A major component in AVs is machine-learning (ML) [23] algorithms that continuously learn and adapt to new information, which is essential for responding to unexpected situations and providing on-demand transportation services [24]. Algorithms' independence from human input and ML's data-driven nature allows AVs to significantly reduce or eliminate human errors that have been responsible for 90% of road fatalities, such as speeding, alcohol impairment, distractions and induced fear [25,26].However, an overemphasis on technological solutions alone for economic development could risk neglecting social and environmental considerations and thus hinder true "smartness" [27]. Scholars have cautioned against rushing to develop smart mobility solutions such as AVs without being prepared to manage their potential "negative externalities" [1,28]. In particular, issues in algorithmic decision-making in AVs can have undesirable effects on safety and equity. Firstly, data mining processes in AVs are susceptible to biases that lead algorithms to prioritise the safety of certain groups of road users over others and thus, perpetuate discrimination [29,30]. Secondly, many scholars stress the need to design algorithms with ethical considerations to ensure that AVs make ethical driving dec...

show abstract

“…Modern vehicles contain a range of sensors from which they create local geospatial knowledge, and can share this information with map providers, Original Equipment Manufacturers (OEMs), and other road users. However, the local knowledge is neither sufficient for route planning nor for local navigation under challenging conditions, such as fog or snow-covered roads, and must be combined with geospatial information from pre-processed databases covering larger areas [2,3]. The users of ITS applications for route planning and navigation rely on accurate and updated geospatial information for the complete knowledge needed for legal and safe navigation.…”

Section: Geospatial Information In Intelligent Transport Systems (Its)mentioning

confidence: 99%

“…Several research projects have worked with specific models and solutions for geospatial ITS databases. Possible models for HD maps are described at an overview level in [1,2]. Conceptual models for transportation networks on different topology levels similar to GDF are described in [52,53], while [54] describes a conceptual UML model for multimodal transport.…”

Section: Other Research and Solutionsmentioning

confidence: 99%

Information Exchange between GIS and Geospatial ITS Databases Based on a Generic Model

Jetlund

Onstein

Huang

2019

IJGI

View full text Add to dashboard Cite

This study aims to improve interoperability between Geographic Information Systems (GIS) and geospatial databases for Intelligent Transport Systems (ITS). Road authorities maintain authoritative information for legal and safe navigation in GIS databases. This information needs to be shared with ITS databases for route planning and navigation, and for use in combination with local knowledge from vehicle sensors. Current solutions for modelling and exchanging geospatial information in the domains of GIS and ITS have been studied and evaluated. Limitations have been pointed out related to usability in the GIS domain and flexibility for representing an evolving real world. A prototype for an improved information exchange model has been developed, based on ISO/TC 211 standards, Model Driven Architecture (MDA), and concepts from the studied solutions. The prototype contains generic models for feature catalogues and features, with implementation schemas in the Geography Markup Language (GML). Results from a case study indicated that the models could be implemented with feature catalogues from the ITS standard ISO 14825 Geographic Data Files (GDF) and the INSPIRE Transport Networks specification. The prototype can be a candidate solution for improved information exchange from GIS databases to ITS databases that are based on the Navigation Data Standard. maintain geospatial information representing the road network, regulations, events, conditions, and road equipment, often in applications and databases from the domain of Geographic Information Systems (GIS). Furthermore, road authorities may have geospatial information for rural areas where fewer vehicles have travelled, as well as Building Information Models (BIM) with geospatial information representing new roads before the roads are opened. Meanwhile, mapping authorities, of course, maintain base maps of roads and the surrounding environment in GIS databases.The research question in this study is how to improve existing methods for exchange of geospatial information from road and mapping authorities' GIS databases to geospatial ITS databases, illustrated by the three right-headed horizontal arrows in Figure 1. Materials and Methods Research DesignThe research described in this paper was based on five steps, illustrated in Figure 3. The state of the art of solutions for information modelling and exchange, in and between the domains of GIS and ITS, was studied and evaluated in step one and two. A prototype for an improved information exchange model was developed in step three. Schema files for implementing the prototype in the GML format were derived from the UML models in step four, following the conversion rules from ISO 19136 [16] and by using the conversion software ShapeChange [26]. Finally, the model was tested and demonstrated in a case study with different feature catalogues in step five.

show abstract

Accurate vehicle self-localization in high definition map dataset

Cited by 30 publications

References 55 publications

Efficient Access Method for Multi-access Edge Servers in Dynamic Map Systems

Efficient Access Method for Multi-access Edge Servers in Dynamic Map Systems

Algorithmic Decision-Making in AVs: Understanding Ethical and Technical Concerns for Smart Cities

Information Exchange between GIS and Geospatial ITS Databases Based on a Generic Model

Contact Info

Product

Resources

About