Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network
This work addresses the challenge of modeling interactions in trajectory prediction for autonomous vehicles, representing an incremental improvement with strong specific gains.
The paper tackles trajectory prediction for autonomous vehicles by proposing a Transformer-like module with masked goal conditioning, achieving state-of-the-art performance with a 2nd place win in the 2022 Waymo Open Dataset Motion Prediction Challenge and 1st place in minADE.
Transformers have enabled breakthroughs in NLP and computer vision, and have recently began to show promising performance in trajectory prediction for Autonomous Vehicle (AV). How to efficiently model the interactive relationships between the ego agent and other road and dynamic objects remains challenging for the standard attention module. In this work we propose a general Transformer-like architectural module MnM network equipped with novel masked goal conditioning training procedures for AV trajectory prediction. The resulted model, named golfer, achieves state-of-the-art performance, winning the 2nd place in the 2022 Waymo Open Dataset Motion Prediction Challenge and ranked 1st place according to minADE.