Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Motion Transformer with Global Intention Localization and Local Movement Refinement

About

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.

Shaoshuai Shi, Li Jiang, Dengxin Dai, Bernt Schiele• 2022

Related benchmarks

TaskDatasetResultRank
Motion forecastingArgoverse 2 Motion Forecasting Dataset (test)
Miss Rate (K=6)15
90
Joint predictionWaymo Open Motion Dataset (WOMD) Interaction (test)
minADE0.9181
26
Trajectory PredictionWaymo Open Motion Dataset (WOMD) (test)
minADE0.605
24
Trajectory ForecastingNuScenes v1.0 (test)
minADEk1.36
14
Motion PredictionWaymo Open Dataset leaderboard (test)
mAP42.49
13
Marginal Motion PredictionWaymo Open Motion Dataset (WOMD) Motion Leaderboard v1.1 (test)
minADE0.3486
12
Marginal Motion PredictionWaymo Open Motion Dataset (WOMD) (val)
minADE0.3549
11
Marginal Motion PredictionWOMD (val)
minADE0.6046
11
Trajectory PredictionArgoverse 2 (val)
Miss Rate33.61
11
Motion PlanningInteractive (val)
Time (ms)37
9
Showing 10 of 30 rows

Other info

Code

Follow for update