Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals

28 Jun 2021  ·  Nachiket Deo, Eric M. Wolff, Oscar Beijbom ·

Accurately predicting the future motion of surrounding vehicles requires reasoning about the inherent uncertainty in driving behavior. This uncertainty can be loosely decoupled into lateral (e.g., keeping lane, turning) and longitudinal (e.g., accelerating, braking). We present a novel method that combines learned discrete policy rollouts with a focused decoder on subsets of the lane graph. The policy rollouts explore different goals given current observations, ensuring that the model captures lateral variability. Longitudinal variability is captured by our latent variable model decoder that is conditioned on various subsets of the lane graph. Our model achieves state-of-the-art performance on the nuScenes motion prediction dataset, and qualitatively demonstrates excellent scene compliance. Detailed ablations highlight the importance of the policy rollouts and the decoder architecture.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Trajectory Prediction nuScenes PGP MinADE_5 1.27 # 4
MinADE_10 0.94 # 3
MissRateTopK_2_5 0.52 # 3
MissRateTopK_2_10 0.34 # 3
MinFDE_1 7.17 # 6
OffRoadRate 0.03 # 5

Methods


No methods listed for this paper. Add relevant methods here