EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning
This addresses motion prediction for applications like particle dynamics and pedestrian trajectories by introducing a novel approach that ensures geometric and interaction properties, representing a significant advancement over existing methods.
The paper tackles the problem of predicting agent motions while maintaining equivariance under geometric transformations and invariance in interactions, proposing EqMotion, which achieves state-of-the-art performance with improvements of 24.0%, 30.1%, 8.6%, and 9.2% across four distinct scenarios.
Learning to predict agent motions with relationship reasoning is important for many applications. In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle. However, such equivariance and invariance properties are overlooked by most existing methods. To fill this gap, we propose EqMotion, an efficient equivariant motion prediction model with invariant interaction reasoning. To achieve motion equivariance, we propose an equivariant geometric feature learning module to learn a Euclidean transformable feature through dedicated designs of equivariant operations. To reason agent's interactions, we propose an invariant interaction reasoning module to achieve a more stable interaction modeling. To further promote more comprehensive motion features, we propose an invariant pattern feature learning module to learn an invariant pattern feature, which cooperates with the equivariant geometric feature to enhance network expressiveness. We conduct experiments for the proposed model on four distinct scenarios: particle dynamics, molecule dynamics, human skeleton motion prediction and pedestrian trajectory prediction. Experimental results show that our method is not only generally applicable, but also achieves state-of-the-art prediction performances on all the four tasks, improving by 24.0/30.1/8.6/9.2%. Code is available at https://github.com/MediaBrain-SJTU/EqMotion.