Evaluating Robustness over High Level Driving Instruction for Autonomous Driving
This addresses a critical safety gap for autonomous vehicles in urban environments, though it is incremental as it focuses on evaluation rather than new methods.
The paper tackles the problem of evaluating autonomous driving agents' robustness to incorrect high-level navigation commands, proposing a benchmark to assess their ability to maintain safe behavior in such unexpected situations.
In recent years, we have witnessed increasingly high performance in the field of autonomous end-to-end driving. In particular, more and more research is being done on driving in urban environments, where the car has to follow high level commands to navigate. However, few evaluations are made on the ability of these agents to react in an unexpected situation. Specifically, no evaluations are conducted on the robustness of driving agents in the event of a bad high-level command. We propose here an evaluation method, namely a benchmark that allows to assess the robustness of an agent, and to appreciate its understanding of the environment through its ability to keep a safe behavior, regardless of the instruction.