The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes

TL;DR

This paper evaluates the neural planning metric (PKL) for autonomous driving object detection, analyzing its correlation with traditional metrics and environmental factors using nuScenes challenge data.

Contribution

It provides a comprehensive analysis of PKL's behavior in different driving scenarios and proposes extensions to improve its effectiveness.

Findings

PKL correlates with mAP but behaves differently under various traffic conditions.

PKL responds uniquely to traffic density, ego velocity, and road curvature.

Analysis suggests potential improvements for the neural planning metric.

Abstract

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.