go back

Importance Filtering with Risk Models for Complex Driving Situations

Tim Puphal, Raphael Wenzel, Benedict Flade, Malte Probst , Julian Eggert, "Importance Filtering with Risk Models for Complex Driving Situations", IEEE ICRAE 2022, 2022.


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, the research topic of importance filtering with driving risk models is therefore introduced. Concretely, we present different risk models and compare their capability to filter out surrounding unimportant agents. Based on the results, we can develop a novel light-weight risk model that balances performance, robustness and efficiency. Furthermore, we 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 enables current behavior planning systems to better solve complex situations in everyday driving.

Download Bibtex file Download PDF