A Diffusion-Model of Joint Interactive Navigation
About
Simulation of autonomous vehicle systems requires that simulated traffic participants exhibit diverse and realistic behaviors. The use of prerecorded real-world traffic scenarios in simulation ensures realism but the rarity of safety critical events makes large scale collection of driving scenarios expensive. In this paper, we present DJINN - a diffusion based method of generating traffic scenarios. Our approach jointly diffuses the trajectories of all agents, conditioned on a flexible set of state observations from the past, present, or future. On popular trajectory forecasting datasets, we report state of the art performance on joint trajectory metrics. In addition, we demonstrate how DJINN flexibly enables direct test-time sampling from a variety of valuable conditional distributions including goal-based sampling, behavior-class sampling, and scenario editing.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Vehicle Trajectory Prediction | INTERACTION (val) | Min FDE (6)0.39 | 22 | |
| Ego-only motion forecasting | Argoverse (test) | minADE (6h)1.02 | 7 | |
| Trajectory Prediction | INTERACTION DR_DEU_Roundabout_OF | Collision Rate1.48 | 4 | |
| Trajectory Prediction | INTERACTION DR_USA_Roundabout_FT | Collision Rate1.1 | 4 | |
| Trajectory Prediction | INTERACTION DR_DEU_Merging_MT 2019 (val) | Collision Rate0.39 | 4 | |
| Trajectory Prediction | INTERACTION DR_USA_Intersection_MA 2019 | Collision Rate (%)1.24 | 4 |