P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving

TL;DR

This paper evaluates existing motion predictors for autonomous driving, finds they often fail to identify conflicts effectively, and introduces P4P, a new conflict-aware predictor that improves safety in interactive scenarios.

Contribution

The paper introduces P4P, a novel conflict-aware motion prediction method combining physics-based and learning-based components, improving conflict detection in autonomous driving.

Findings

Existing predictors have low conflict identification success rates.

P4P outperforms existing predictors in realistic scenarios.

P4P reduces collision rates in interactive driving simulations.

Abstract

Motion prediction is crucial in enabling safe motion planning for autonomous vehicles in interactive scenarios. It allows the planner to identify potential conflicts with other traffic agents and generate safe plans. Existing motion predictors often focus on reducing prediction errors, yet it remains an open question on how well they help identify the conflicts for the planner. In this paper, we evaluate state-of-the-art predictors through novel conflict-related metrics, such as the success rate of identifying conflicts. Surprisingly, the predictors suffer from a low success rate and thus lead to a large percentage of collisions when we test the prediction-planning system in an interactive simulator. To fill the gap, we propose a simple but effective alternative that combines a physics-based trajectory generator and a learning-based relation predictor to identify conflicts and infer conflict relations. We demonstrate that our predictor, P4P, achieves superior performance over existing learning-based predictors in realistic interactive driving scenarios from Waymo Open Motion Dataset.