ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planning
This addresses the challenge of improving safety and planning in autonomous driving by ensuring predictions are consistent across all agents in a scene, though it appears incremental as it builds on existing prediction methods.
The paper tackles the problem of generating scene-consistent trajectory predictions for autonomous systems, such as self-driving vehicles, by introducing ScePT, which matches state-of-the-art prediction accuracy while significantly reducing self-collisions between agents.
Trajectory prediction is a critical functionality of autonomous systems that share environments with uncontrolled agents, one prominent example being self-driving vehicles. Currently, most prediction methods do not enforce scene consistency, i.e., there are a substantial amount of self-collisions between predicted trajectories of different agents in the scene. Moreover, many approaches generate individual trajectory predictions per agent instead of joint trajectory predictions of the whole scene, which makes downstream planning difficult. In this work, we present ScePT, a policy planning-based trajectory prediction model that generates accurate, scene-consistent trajectory predictions suitable for autonomous system motion planning. It explicitly enforces scene consistency and learns an agent interaction policy that can be used for conditional prediction. Experiments on multiple real-world pedestrians and autonomous vehicle datasets show that ScePT} matches current state-of-the-art prediction accuracy with significantly improved scene consistency. We also demonstrate ScePT's ability to work with a downstream contingency planner.