LiMTR: Time Series Motion Prediction for Diverse Road Users through Multimodal Feature Integration

TL;DR

LiMTR introduces a multimodal time series motion prediction model for diverse road users, leveraging LiDAR data and PointNet architecture to improve accuracy in autonomous vehicle scenarios.

Contribution

The paper presents a novel multimodal approach using LiDAR features within a PointNet-based model for enhanced motion prediction of road users.

Findings

Achieved 6.20% improvement in minADE on Waymo dataset.

Achieved 1.58% improvement in mAP on Waymo dataset.

Open-sourced the LiMTR code for community use.

Abstract

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.