Handling Noise in Search-Based Scenario Generation for Autonomous Driving Systems
This addresses noise reduction in scenario generation for autonomous driving systems, though it appears incremental as it builds on existing repetition approaches.
This paper tackles noise in multi-objective optimization for autonomous driving scenario generation by introducing kNN-Avg, a technique that approximates repetitions to avoid costly re-runs. The results show it outperforms a noisy baseline and is compared to repetition methods with situational guidance.
This paper presents the first evaluation of k-nearest neighbours-Averaging (kNN-Avg) on a real-world case study. kNN-Avg is a novel technique that tackles the challenges of noisy multi-objective optimisation (MOO). Existing studies suggest the use of repetition to overcome noise. In contrast, kNN-Avg approximates these repetitions and exploits previous executions, thereby avoiding the cost of re-running. We use kNN-Avg for the scenario generation of a real-world autonomous driving system (ADS) and show that it is better than the noisy baseline. Furthermore, we compare it to the repetition-method and outline indicators as to which approach to choose in which situations.