SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving

Abstract-- This paper presents a Simple and effIcient Motion Prediction baseLine (SIMPL) for autonomous vehicles. Unlike conventional agent-centric methods with high accuracy but repetitive computations and scene-centric methods with compromised accuracy and generalizability, SIMPL delivers realtime, accurate motion predictions for all relevant traffic participants. To achieve improvements in both accuracy and inference speed, we propose a compact and efficient global feature fusion module that performs directed message passing in a symmetric manner, enabling the network to forecast future motion for all road users in a single feed-forward pass and mitigating accuracy loss caused by viewpoint shifting. Please refer to the attached video for more examples. To achieve better accuracy and robustness, a common solution is normalizing the scene context w.r.t. Motion forecasting for the surrounding traffic participants It means the normalization process and feature is essential in autonomous vehicles, especially for the encoding have to be executed repeatedly for each target downstream decision-making and planning modules, since agent, leading to better performance but at the cost of accurate and timely intention and trajectory prediction will redundant computation.