Motion Transformer with Global Intention Localization and Local Movement Refinement

TL;DR

This paper introduces Motion Transformer (MTR), a novel framework for multimodal traffic behavior prediction that uses learnable motion queries for stable, efficient, and accurate trajectory forecasting, achieving state-of-the-art results.

Contribution

MTR models motion prediction as joint global intention localization and local movement refinement using learnable motion queries, improving stability and multimodal prediction quality.

Findings

Achieves state-of-the-art performance on Waymo Open Motion Dataset

Outperforms existing methods in both marginal and joint motion prediction tasks

Demonstrates stable training and efficient multimodal trajectory prediction

Abstract

Predicting multimodal future behavior of traffic participants is essential for robotic vehicles to make safe decisions. Existing works explore to directly predict future trajectories based on latent features or utilize dense goal candidates to identify agent's destinations, where the former strategy converges slowly since all motion modes are derived from the same feature while the latter strategy has efficiency issue since its performance highly relies on the density of goal candidates. In this paper, we propose Motion TRansformer (MTR) framework that models motion prediction as the joint optimization of global intention localization and local movement refinement. Instead of using goal candidates, MTR incorporates spatial intention priors by adopting a small set of learnable motion query pairs. Each motion query pair takes charge of trajectory prediction and refinement for a specific motion mode, which stabilizes the training process and facilitates better multimodal predictions. Experiments show that MTR achieves state-of-the-art performance on both the marginal and joint motion prediction challenges, ranking 1st on the leaderboards of Waymo Open Motion Dataset. The source code is available at https://github.com/sshaoshuai/MTR.