Digital Maps for ADAS

Kleine-Besten, Thomas; Behrens, Ralph; Pöchmüller, Werner; Engelsberg, A.

doi:10.1007/978-3-319-12352-3_27

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In automotive industries, the most popular navigation map format is the socalled Navigation Data Standard (NDS), which is developed by NDS e.V. [35][36][37]. NDS e.V.…”

Section: Navigation Map and Point Of Interest Objectmentioning

confidence: 99%

“…In addition to the basic geometry and topology of road network, a navigation map usually also contains other geo-referenced data. For example, a typical NDS map includes the following data blocks in its database: Routing block for road geometry and topology, POI block for geo-referenced places that can be selected as the navigation destination, and Name block for human references to certain locations and roads [35,40].…”

Section: Navigation Map and Point Of Interest Objectmentioning

confidence: 99%

“…In fact, the parameter vector a contains many zero entities, and only the nonzero entities have an effect on the final decision according to Equation (35). The training samples corresponding to these nonzero entities are known as support vectors, and hence, this technique is named support vector machine.…”

Section: Support-vector-machine-based Inference Enginementioning

confidence: 99%

See 2 more Smart Citations

Driving Environment Inference from POI of Navigation Map: Fuzzy Logic and Machine Learning Approaches

Li,

Metzner,

Schwieger

2023

Sensors

View full text Add to dashboard Cite

To adapt vehicle control and plan strategies in a predictive manner, it is usually desired to know the context of a driving environment. This paper aims at efficiently inferring the following five driving environments around vehicle’s vicinity: shopping zone, tourist zone, public station, motor service area, and security zone, whose existences are not necessarily mutually exclusive. To achieve that, we utilize the Point of Interest (POI) data from a navigation map as the semantic clue, and solve the inference task as a multilabel classification problem. Specifically, we first extract all relevant POI objects from a map, then transform these discrete POI objects into numerical POI features. Based on these POI features, we finally predict the occurrence of each driving environment via an inference engine. To calculate representative POI features, a statistical approach is introduced. To composite an inference engine, three inference systems are investigated: fuzzy inference system (FIS), support vector machine (SVM), and multilayer perceptron (MLP). In total, we implement 11 variants of inference engine following two inference strategies: independent and unified inference strategies, and conduct comprehensive evaluation on a manually collected dataset. The result shows that the proposed inference framework generalizes well on different inference systems, where the best overall F1 score 0.8699 is achieved by the MLP-based inference engine following the unified inference strategy, along with the fastest inference time of 0.0002 millisecond per sample. Hence, the generalization ability and efficiency of the proposed inference framework are proved.

show abstract

“…In automotive industries, the most popular navigation map format is the socalled Navigation Data Standard (NDS), which is developed by NDS e.V. [35][36][37]. NDS e.V.…”

Section: Navigation Map and Point Of Interest Objectmentioning

confidence: 99%

Section: Navigation Map and Point Of Interest Objectmentioning

confidence: 99%

See 1 more Smart Citation

Driving Environment Inference from POI of Navigation Map: Fuzzy Logic and Machine Learning Approaches

Li,

Metzner,

Schwieger

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In contrast, the autonomous world has the computer to take over these tasks. Thanks to the high speed of data processing of the onboard computers, the data request has also been increased (Kleine-Besten et al, 2015). This reason has led to the development of the maps with respect to the resolution (Craig, 2012).…”

Section: Map Production Technologiesmentioning

confidence: 99%

The Role of Maps in Autonomous Driving Simulations

Barsi

Csepinszky²,

Lógó

et al. 2020

Period. Polytech. Transp. Eng.

View full text Add to dashboard Cite

The vehicles of the conditional, high, and full automation levels have a common unique sensor, the map. The term map has undergone a significant change because the spatial resolution has been increased considerably, the road infrastructure and its neighborhood are represented with higher accuracy in 3D. The development of these vehicles requires enormous efforts, where computer-based techniques, like the simulations, can offer a helping hand. The autonomous simulations will be supported by high-quality map information, which generates interest in the best field data-capturing techniques. The paper provides an overview of the available modern surveying methodologies, then introduces the most preferred data formats – both in physical information storage and in exchanging information content between mapping systems. Some examples are presented to demonstrate the usage of the relevant map-making outputs in automotive simulators.

show abstract

“…Vehicle assistants with navigation support -especially Advanced Driver Assistance Systems (ADAS) -use the map as a sensor [19]. For example, the Adaptive Front-lighting System uses map information to better illuminate curves and intersections, while Predictive Lighting controls the vehicle lighting based on topography.…”

Section: : Functional Component Blocks In a Vehiclementioning

confidence: 99%

Maps Towards Autonomous Driving Ecosystem

Barsi,

Lógó

Proceedings of the Seventeenth International Conference On Civil, Structural and Environmental Engineering Computing

View full text Add to dashboard Cite

The development of vehicle navigation maps used for vehicle transportation from the early days of paper maps to the modern use of satellite and mobile mapping technologies is not only ongoing but accelerating. Current maps have undergone significant changes in terms of format, content, and topology. They have evolved into 3D representations and now include dynamic content such as real-time road events and traffic updates. Different production technologies, such as aerial photogrammetry and mobile mapping, are used. The importance of standardizing the map content is also emphasized. Two main applications of map data, Standard-Definition maps (SD maps) for human interpretation and High-Definition maps (HD maps) for machine interpretation, are available today. The role of maps in the perception of the environment by vehicles is also discussed.

show abstract

Digital Maps for ADAS

Cited by 5 publications

References 0 publications

Driving Environment Inference from POI of Navigation Map: Fuzzy Logic and Machine Learning Approaches

Driving Environment Inference from POI of Navigation Map: Fuzzy Logic and Machine Learning Approaches

The Role of Maps in Autonomous Driving Simulations

Maps Towards Autonomous Driving Ecosystem

Contact Info

Product

Resources

About