TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction
About
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.
Yuting Wang, Hangning Zhou, Zhigang Zhang, Chen Feng, Huadong Lin, Chaofei Gao, Yizhi Tang, Zhenting Zhao, Shiyu Zhang, Jie Guo, Xuefeng Wang, Ziyao Xu, Chi Zhang• 2022
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Motion forecasting | Argoverse 2 Motion Forecasting Dataset (test) | Miss Rate (K=6)19 | 90 | |
| Motion Prediction | AV2 2.0 (test) | Brier Score (minFDE@6s)1.9 | 8 |
Showing 2 of 2 rows