Asymmetry-based Behavior Planning for Cooperation at Shared Traffic Spaces

Wenzel, Raphael; Probst, Malte; Puphal, Tim; Weisswange, Thomas H.; Eggert, Julian

doi:10.1109/iv48863.2021.9575187

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These systems have sophisticated planning algorithms to tackle complex situations. For example, cooperative planners [4] provide multiple predictions of the future behavior for sensed agents and plan for each predicted scenario an optimal behavior for the ego agent. That means, the system does not only predict a constant velocity trajectory but also anticipates braking and accelerating trajectories for the other agents.…”

Section: Introductionmentioning

confidence: 99%

Importance Filtering with Risk Models for Complex Driving Situations

Puphal

Wenzel

Flade

et al. 2022

2022 7th International Conference on Robotics and Automation Engineering (ICRAE)

Self Cite

View full text Add to dashboard Cite

Self-driving cars face complex driving situations with a large amount of agents when moving in crowded cities. However, some of the agents are actually not influencing the behavior of the self-driving car. Filtering out unimportant agents would inherently simplify the behavior or motion planning task for the system. The planning system can then focus on fewer agents to find optimal behavior solutions for the ego agent. This is helpful especially in terms of computational efficiency. In this paper, therefore, the research topic of importance filtering with driving risk models is introduced. We give an overview of state-of-the-art risk models and present newly adapted risk models for filtering. Their capability to filter out surrounding unimportant agents is compared in a large-scale experiment. As it turns out, the novel trajectory distance balances performance, robustness and efficiency well. Based on the results, we can further derive a novel filter architecture with multiple filter steps, for which risk models are recommended for each step, to further improve the robustness. We are confident that this will enable current behavior planning systems to better solve complex situations in everyday driving.

show abstract

Section: Introductionmentioning

confidence: 99%