The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
This work provides insights for improving safety evaluation in autonomous driving, though it is incremental as it applies an existing metric to new data.
The paper analyzed autonomous driving detection systems using the neural planning metric PKL on nuScenes challenge submissions, finding that PKL behaves differently from mAP under varying traffic conditions like density and road curvature.
A high-performing object detection system plays a crucial role in autonomous driving (AD). The performance, typically evaluated in terms of mean Average Precision, does not take into account orientation and distance of the actors in the scene, which are important for the safe AD. It also ignores environmental context. Recently, Philion et al. proposed a neural planning metric (PKL), based on the KL divergence of a planner's trajectory and the groundtruth route, to accommodate these requirements. In this paper, we use this neural planning metric to score all submissions of the nuScenes detection challenge and analyze the results. We find that while somewhat correlated with mAP, the PKL metric shows different behavior to increased traffic density, ego velocity, road curvature and intersections. Finally, we propose ideas to extend the neural planning metric.