Learning Group Interactions and Semantic Intentions for Multi-Object Trajectory Prediction
This work addresses trajectory forecasting in complex scenarios like sports, where agents' movements are influenced by team strategies and opponent actions, offering improvements for applications in sports analytics and autonomous systems.
The paper tackles multi-object trajectory prediction by modeling group interactions and dynamic semantic intentions, proposing a diffusion-based framework that integrates group-level interactions and frames group interaction prediction as a cooperative game using Banzhaf interaction. The model outperforms state-of-the-art methods on three datasets, with results demonstrated through extensive experiments.
Effective modeling of group interactions and dynamic semantic intentions is crucial for forecasting behaviors like trajectories or movements. In complex scenarios like sports, agents' trajectories are influenced by group interactions and intentions, including team strategies and opponent actions. To this end, we propose a novel diffusion-based trajectory prediction framework that integrates group-level interactions into a conditional diffusion model, enabling the generation of diverse trajectories aligned with specific group activity. To capture dynamic semantic intentions, we frame group interaction prediction as a cooperative game, using Banzhaf interaction to model cooperation trends. We then fuse semantic intentions with enhanced agent embeddings, which are refined through both global and local aggregation. Furthermore, we expand the NBA SportVU dataset by adding human annotations of team-level tactics for trajectory and tactic prediction tasks. Extensive experiments on three widely-adopted datasets demonstrate that our model outperforms state-of-the-art methods. Our source code and data are available at https://github.com/aurora-xin/Group2Int-trajectory.