A Diffusion-Model of Joint Interactive Navigation
Keywords: Diffusion Models, Trajecotry Forecasting, Autonomous Vehicles, Motion Forecasting, Simulation
TL;DR: We present a diffusion model which generates joint traffic scenes, and investigate its performance and test time conditioning methods.
Abstract: 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.
Submission Number: 15178