Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network

TL;DR

Golfer is a Transformer-based trajectory prediction model for autonomous vehicles that uses masked goal conditioning to improve interaction modeling, achieving state-of-the-art results in a major challenge.

Contribution

The paper introduces the MnM network with masked goal conditioning training, enhancing Transformer models for AV trajectory prediction.

Findings

Achieved 2nd place in Waymo Challenge

Ranked 1st by minADE in the dataset

Outperformed existing models in accuracy

Abstract

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.