4.6 Article

BiTraP: Bi-Directional Pedestrian Trajectory Prediction With Multi-Modal Goal Estimation

期刊

IEEE ROBOTICS AND AUTOMATION LETTERS
卷 6, 期 2, 页码 1463-1470

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2021.3056339

关键词

Computer vision for automation; human and humanoid motion analysis and synthesis; deep learning methods; multi-modal trajectory prediction; goal-conditioned prediction

类别

资金

  1. Ford Motor Company via the Ford-UM Alliance [N028603]
  2. Federal Highway Administration [693JJ319000009]

向作者/读者索取更多资源

This letter introduces BiTraP, a goal-conditioned bidirectional multi-modal trajectory prediction method based on CVAE, which accurately predicts pedestrian trajectory goals and improves long-term prediction accuracy. Extensive experiments show BiTraP's superior performance across different scenarios, outperforming state-of-the-art methods by 10-50% in accuracy.
Pedestrian trajectory prediction is an essential task in robotic applications such as autonomous driving and robot navigation. State-of-the-art trajectory predictors use a conditional variational autoencoder (CVAE) with recurrent neural networks (RNNs) to encode observed trajectories and decode multi-modal future trajectories. This process can suffer from accumulated errors over long prediction horizons (>= 2 seconds). This letter presents BiTraP, a goal-conditioned hi-directional multi-modal trajectory prediction method based on the CVAE. BiTraP estimates the goal (end-point) of trajectories and introduces a novel bidirectional decoder to improve longer-term trajectory prediction accuracy. Extensive experiments show that BiTraP generalizes to both first-person view (FPV) and bird's-eye view (BEV) scenarios and outperforms state-of-the-art results by similar to 10-50%. We also show that different choices of non-parametric versus parametric target models in the CVAE directly influence the predicted multi-modal trajectory distributions. These results provide guidance on trajectory predictor design for robotic applications such as collision avoidance and navigation systems. Our code is available at: bups://github.com/untautobots/bidireaction-trajectory-prediction.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据