LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting

17 Jan 2021  ·  Wenyuan Zeng, Ming Liang, Renjie Liao, Raquel Urtasun ·

Forecasting the future behaviors of dynamic actors is an important task in many robotics applications such as self-driving. It is extremely challenging as actors have latent intentions and their trajectories are governed by complex interactions between the other actors, themselves, and the maps. In this paper, we propose LaneRCNN, a graph-centric motion forecasting model. Importantly, relying on a specially designed graph encoder, we learn a local lane graph representation per actor (LaneRoI) to encode its past motions and the local map topology. We further develop an interaction module which permits efficient message passing among local graph representations within a shared global lane graph. Moreover, we parameterize the output trajectories based on lane graphs, a more amenable prediction parameterization. Our LaneRCNN captures the actor-to-actor and the actor-to-map relations in a distributed and map-aware manner. We demonstrate the effectiveness of our approach on the large-scale Argoverse Motion Forecasting Benchmark. We achieve the 1st place on the leaderboard and significantly outperform previous best results.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Motion Forecasting Argoverse CVPR 2020 LaneRCNN (IROS 2021) MR (K=6) 0.1232 # 264
minADE (K=1) 1.6852 # 232
minFDE (K=1) 3.6916 # 235
MR (K=1) 0.5685 # 253
minADE (K=6) 0.9038 # 168
minFDE (K=6) 1.4526 # 155
DAC (K=6) 0.9903 # 11
brier-minFDE (K=6) 2.147 # 151

Methods


No methods listed for this paper. Add relevant methods here