Motion Prediction Performance Analysis for Autonomous Driving Systems and the Effects of Tracking Noise
This work highlights a practical issue for autonomous driving developers regarding the sensitivity of motion prediction to tracking errors, suggesting caution or alternatives.
The paper analyzes how tracking module imperfections affect motion prediction performance in autonomous driving systems, finding that tracking information improves performance in noise-free conditions but can degrade it when tracking noise is present.
Autonomous driving consists of a multitude of interacting modules, where each module must contend with errors from the others. Typically, the motion prediction module depends upon a robust tracking system to capture each agent's past movement. In this work, we systematically explore the importance of the tracking module for the motion prediction task and ultimately conclude that the overall motion prediction performance is highly sensitive to the tracking module's imperfections. We explicitly compare models that use tracking information to models that do not across multiple scenarios and conditions. We find that the tracking information plays an essential role and improves motion prediction performance in noise-free conditions. However, in the presence of tracking noise, it can potentially affect the overall performance if not studied thoroughly. We thus argue practitioners should be mindful of noise when developing and testing motion/tracking modules, or that they should consider tracking free alternatives.