Edge Case Detection in Automated Driving: Methods, Challenges and Future Directions
The episode discusses a paper titled "Edge Case Detection in Automated Driving: Methods, Challenges and Future Directions." Hosts Jane and Tom explore how to find rare, unpredictable situations that autonomous vehicles might encounter. They cover detection methods like perception-related and trajectory-related cases, knowledge-driven detection using expert data, assessment frameworks, and future improvements such as using foundation models for scenario generation.