Scenario Factory: Creating Safety-Critical Traffic Scenarios for Automated Vehicles

Klischat, Moritz; Liu, Edmond Irani; Holtke, Fabian; Althoff, Matthias

doi:10.1109/itsc45102.2020.9294629

Cited by 45 publications

(20 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To explore more different kinds of scenarios, [81] generate the motion of other traffic participants with a backtracking search. To make the scenarios diverse, [82] build a pipeline that introduces the road topology from OpenStreetMap [132]. Using the safetycritical scenarios from [82], [83] designs a comprehensive open-source toolbox to train and evaluate RL motion planners for autonomous vehicles with customized configuration from users.…”

Section: Constraint Optimizationmentioning

confidence: 99%

“…To make the scenarios diverse, [82] build a pipeline that introduces the road topology from OpenStreetMap [132]. Using the safetycritical scenarios from [82], [83] designs a comprehensive open-source toolbox to train and evaluate RL motion planners for autonomous vehicles with customized configuration from users. To obtain a robust trajectory prediction model, [78] generate adversarial trajectory by perturbing existing trajectory with feasible constraints.…”

Section: Constraint Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

Ding¹,

Xu²,

Arief³

et al. 2022

Preprint

View full text Add to dashboard Cite

Autonomous driving systems have witnessed a significant development during the past years thanks to the advance in machine learning-enabled sensing and decision-making algorithms. One critical challenge for their massive deployment in the real world is their safety evaluation. Most existing driving systems are still trained and evaluated on naturalistic scenarios collected from daily life or heuristically-generated adversarial ones. However, the large population of cars, in general, leads to an extremely low collision rate, indicating that the safety-critical scenarios are rare in the collected real-world data. Thus, methods to artificially generate scenarios become crucial to measure the risk and reduce the cost. In this survey, we focus on the algorithms of safety-critical scenario generation in autonomous driving. We first provide a comprehensive taxonomy of existing algorithms by dividing them into three categories: data-driven generation, adversarial generation, and knowledge-based generation. Then, we discuss useful tools for scenario generation, including simulation platforms and packages. Finally, we extend our discussion to five main challenges of current works -fidelity, efficiency, diversity, transferability, controllability -and research opportunities lighted up by these challenges.

show abstract

Section: Constraint Optimizationmentioning

confidence: 99%

Section: Constraint Optimizationmentioning

confidence: 99%

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

Ding¹,

Xu²,

Arief³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…From a safety and verification perspective, it has been studied how to select scenarios, e.g. [10], and how simulative scenario-based verification methods can help to approve the safety of automated driving. An overview on scenario-based verification can be found in [1].…”

Section: B Related Workmentioning

confidence: 99%

DeepSIL: A Software-in-the-Loop Framework for Evaluating Motion Planning Schemes Using Multiple Trajectory Prediction Networks

Strohbeck

Müller

Holzbock

et al. 2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Testing and verification is still an open issue on the way to fully automated driving. Simulations can help to reduce the required testing efforts, however, classical simulators based on physical models and heuristics, such as the intelligent driver model (IDM), show limited model accuracy on a microscopic scenario level. In turn, learning-based driver models are often capable to predict human driver's behavior accurately, but are difficult to tailor such that they follow an intended scenario description. In this work, we propose a software-in-the-loop framework to combine a learned model with a rule-based logic layer and a kinematic vehicle model of a classical traffic simulator. Thus, the merits of both, classical simulators and learning-based models are exploited. We demonstrate with a case study of evaluating a motion planning scheme that the simulator fits well with the needs of testing such methods. Furthermore, we show by experiments with real-world traffic data from a traffic surveillance system that the proposed simulator yields realistic behavior of the simulated road users.

show abstract

“…Feng et al (2020) designed a critical scenario searching method based on multi-start optimization and seed-fill method. Klischat et al (2020) used particle swarm optimization (PSO) to increase the criticality of the simulation scenarios. Zhu et al (2021) proposed an optimization searching method to explore the critical-scenarios in a huge search space faster.…”

Section: Introductionmentioning

confidence: 99%

Multimodal critical-scenarios search method for test of autonomous vehicles

Liu

Xing

Chen

2022

JICV

View full text Add to dashboard Cite

Purpose The purpose of this paper is to search for the critical-scenarios of autonomous vehicles (AVs) quickly and comprehensively, which is essential for verification and validation (V&V). Design/methodology/approach The author adopted the index F1 to quantitative critical-scenarios' coverage of the search space and proposed the improved particle swarm optimization (IPSO) to enhance exploration ability for higher coverage. Compared with the particle swarm optimization (PSO), there were three improvements. In the initial phase, the Latin hypercube sampling method was introduced for a uniform distribution of particles. In the iteration phase, the neighborhood operator was adapted to explore more modals with the particles divided into groups. In the convergence phase, the convergence judgment and restart strategy were used to explore the search space by avoiding local convergence. Compared with the Monte Carlo method (MC) and PSO, experiments on the artificial function and critical-scenarios search were carried out to verify the efficiency and the application effect of the method. Findings Results show that IPSO can search for multimodal critical-scenarios comprehensively, with a stricter threshold and fewer samples in the experiment on critical-scenario search, the coverage of IPSO is 14% higher than PSO and 40% higher than MC. Originality/value The critical-scenarios' coverage of the search space is firstly quantified by the index F1, and the proposed method has higher search efficiency and coverage for the critical-scenarios search of AVs, which shows application potential for V&V.

show abstract

Scenario Factory: Creating Safety-Critical Traffic Scenarios for Automated Vehicles

Cited by 45 publications

References 33 publications

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

DeepSIL: A Software-in-the-Loop Framework for Evaluating Motion Planning Schemes Using Multiple Trajectory Prediction Networks

Multimodal critical-scenarios search method for test of autonomous vehicles

Contact Info

Product

Resources

About