The Impact of Class Uncertainty Propagation in Perception-Based Motion Planning

TL;DR

This paper analyzes how the propagation and calibration of perception uncertainty affect autonomous vehicle motion planning, demonstrating that proper uncertainty handling improves generalization in complex urban scenarios.

Contribution

It introduces a detailed analysis of uncertainty propagation in perception-based planning and compares two novel pipelines on a benchmark, highlighting the importance of calibration.

Findings

Uncertainty propagation improves planning robustness.

Proper calibration enhances scenario generalization.

The proposed method outperforms baselines in complex scenarios.

Abstract

Autonomous vehicles (AVs) are being increasingly deployed in urban environments. In order to operate safely and reliably, AVs need to account for the inherent uncertainty associated with perceiving the world through sensor data and incorporate that into their decision-making process. Uncertainty-aware planners have recently been developed to account for upstream perception and prediction uncertainty. However, such planners may be sensitive to prediction uncertainty miscalibration, the magnitude of which has not yet been characterized. Towards this end, we perform a detailed analysis on the impact that perceptual uncertainty propagation and calibration has on perception-based motion planning. We do so by comparing two novel prediction-planning pipelines with varying levels of uncertainty propagation on the recently-released nuPlan planning benchmark. We study the impact of upstream uncertainty calibration using closed-loop evaluation on the nuPlan challenge scenarios. We find that the method incorporating upstream uncertainty propagation demonstrates superior generalization to complex closed-loop scenarios.