{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bitrap-bi-directional-pedestrian-trajectory","title":"BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation","arxiv_id":"2007.14558","date":"2020-07-29","proceeding":null,"authors":["Yu Yao","Ella Atkins","Matthew Johnson-Roberson","Ram Vasudevan","Xiaoxiao Du"],"abstract":"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 paper presents BiTraP, a goal-conditioned bi-directional multi-modal trajectory prediction method based on the CVAE. BiTraP estimates the goal (end-point) of trajectories and introduces a novel bi-directional 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 ~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.","url_abs":"https://arxiv.org/abs/2007.14558v2","url_pdf":"https://arxiv.org/pdf/2007.14558v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bitrap-bi-directional-pedestrian-trajectory","repo_url":"https://github.com/umautobots/bidireaction-trajectory-prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"collision-avoidance","task_name":"Collision Avoidance"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"multi-future-trajectory-prediction","task_name":"Multi-future Trajectory Prediction"},{"task_slug":"pedestrian-trajectory-prediction","task_name":"Pedestrian Trajectory Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"robot-navigation","task_name":"Robot Navigation"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[{"method_slug":"cvae","method_name":"cVAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/trajectory-prediction-on-jaad","task":"Trajectory Prediction","dataset":"JAAD","model":"BiTrap-D","rank_in_archive_order":2,"of":5,"metrics":{"CF_MSE(1.5)":"4565","C_MSE(1.5)":"1105","MSE(0.5)":"93","MSE(1.0)":"378","MSE(1.5)":"1206"},"uses_additional_data":false},{"leaderboard":"/sota/trajectory-prediction-on-pie","task":"Trajectory Prediction","dataset":"PIE","model":"Bitrap-D","rank_in_archive_order":2,"of":5,"metrics":{"CF_MSE(1.5)":"1949","C_MSE(1.5)":"481","MSE(0.5)":"41","MSE(1.0)":"161","MSE(1.5)":"511"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.14558","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}