P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving
This addresses the safety issue of conflict identification in motion prediction for autonomous vehicles, but it is incremental as it builds on existing methods with a hybrid approach.
The paper tackled the problem of motion prediction for autonomous driving by evaluating existing predictors on conflict identification and finding they lead to high collision rates, then proposed P4P, which achieved superior performance in realistic scenarios from the Waymo Open Motion Dataset.
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.