TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction

2022/06/30 by Wang, Yuting, Zhou, Hangning, Zhang, Zhigang +10
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2207.00170

Abstract

This technical report presents an effective method for motion prediction in autonomous driving. We develop a Transformer-based method for input encoding and trajectory prediction. Besides, we propose the Temporal Flow Header to enhance the trajectory encoding. In the end, an efficient K-means ensemble method is used. Using our Transformer network and ensemble method, we win the first place of Argoverse 2 Motion Forecasting Challenge with the state-of-the-art brier-minFDE score of 1.90.

Related

• Transformer based trajectory prediction
• Multimodal Motion Prediction with Stacked Transformers
• LMFormer: Lane based Motion Prediction Transformer
• S2TNet: Spatio-Temporal Transformer Networks for Trajectory Prediction in Autonomous Driving
• DyTTP: Trajectory Prediction with Normalization-Free Transformers