M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction
This addresses the problem of scene-compliant multi-agent trajectory prediction for autonomous driving, representing an incremental improvement over existing marginal prediction methods.
The paper tackles the challenge of jointly predicting future trajectories for multiple interacting road agents by proposing M2I, which classifies agents as influencers and reactors and uses separate models for marginal and conditional prediction, achieving state-of-the-art performance on the Waymo Open Motion Dataset.
Predicting future motions of road participants is an important task for driving autonomously in urban scenes. Existing models excel at predicting marginal trajectories for single agents, yet it remains an open question to jointly predict scene compliant trajectories over multiple agents. The challenge is due to exponentially increasing prediction space as a function of the number of agents. In this work, we exploit the underlying relations between interacting agents and decouple the joint prediction problem into marginal prediction problems. Our proposed approach M2I first classifies interacting agents as pairs of influencers and reactors, and then leverages a marginal prediction model and a conditional prediction model to predict trajectories for the influencers and reactors, respectively. The predictions from interacting agents are combined and selected according to their joint likelihoods. Experiments show that our simple but effective approach achieves state-of-the-art performance on the Waymo Open Motion Dataset interactive prediction benchmark.