FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs
About
Predicting the future motion of road agents is a critical task in an autonomous driving pipeline. In this work, we address the problem of generating a set of scene-level, or joint, future trajectory predictions in multi-agent driving scenarios. To this end, we propose FJMP, a Factorized Joint Motion Prediction framework for multi-agent interactive driving scenarios. FJMP models the future scene interaction dynamics as a sparse directed interaction graph, where edges denote explicit interactions between agents. We then prune the graph into a directed acyclic graph (DAG) and decompose the joint prediction task into a sequence of marginal and conditional predictions according to the partial ordering of the DAG, where joint future trajectories are decoded using a directed acyclic graph neural network (DAGNN). We conduct experiments on the INTERACTION and Argoverse 2 datasets and demonstrate that FJMP produces more accurate and scene-consistent joint trajectory predictions than non-factorized approaches, especially on the most interactive and kinematically interesting agents. FJMP ranks 1st on the multi-agent test leaderboard of the INTERACTION dataset.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Joint prediction | INTERACTION multi-agent v1.2 (test) | minADE0.275 | 7 | |
| Joint Trajectory Prediction | INTERACTION (test) | minJointFDE0.9218 | 6 | |
| Trajectory Prediction | INTERACTION | minJointFDE (m)0.922 | 6 | |
| Multi-agent motion forecasting | Argoverse multi-agent 2 (test) | Average minFDE (K=1)4 | 5 |