LiMTR: Time Series Motion Prediction for Diverse Road Users through Multimodal Feature Integration
This work addresses motion prediction for autonomous vehicles in urban areas, representing an incremental advancement by incorporating LiDAR features into an existing foundation model.
The paper tackles the problem of predicting road user motion for autonomous vehicles by proposing a novel multimodal approach that integrates local LiDAR features, achieving a 6.20% improvement in minADE and 1.58% in mAP on the Waymo Open Dataset compared to the previous state-of-the-art.
Predicting the behavior of road users accurately is crucial to enable the safe operation of autonomous vehicles in urban or densely populated areas. Therefore, there has been a growing interest in time series motion prediction research, leading to significant advancements in state-of-the-art techniques in recent years. However, the potential of using LiDAR data to capture more detailed local features, such as a person's gaze or posture, remains largely unexplored. To address this, we develop a novel multimodal approach for motion prediction based on the PointNet foundation model architecture, incorporating local LiDAR features. Evaluation on the Waymo Open Dataset shows a performance improvement of 6.20% and 1.58% in minADE and mAP respectively, when integrated and compared with the previous state-of-the-art MTR. We open-source the code of our LiMTR model.