{"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/hydra-mdp-end-to-end-multimodal-planning-with","title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","arxiv_id":"2406.06978","date":"2024-06-11","proceeding":null,"authors":["Zhenxin Li","Kailin Li","Shihao Wang","Shiyi Lan","Zhiding Yu","Yishen Ji","Zhiqi Li","Ziyue Zhu","Jan Kautz","Zuxuan Wu","Yu-Gang Jiang","Jose M. Alvarez"],"abstract":"We propose Hydra-MDP, a novel paradigm employing multiple teachers in a teacher-student model. This approach uses knowledge distillation from both human and rule-based teachers to train the student model, which features a multi-head decoder to learn diverse trajectory candidates tailored to various evaluation metrics. With the knowledge of rule-based teachers, Hydra-MDP learns how the environment influences the planning in an end-to-end manner instead of resorting to non-differentiable post-processing. This method achieves the $1^{st}$ place in the Navsim challenge, demonstrating significant improvements in generalization across diverse driving environments and conditions. More details by visiting \\url{https://github.com/NVlabs/Hydra-MDP}.","url_abs":"https://arxiv.org/abs/2406.06978v4","url_pdf":"https://arxiv.org/pdf/2406.06978v4.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":"hydra-mdp-end-to-end-multimodal-planning-with","repo_url":"https://github.com/nvlabs/hydra-mdp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"hydra-mdp-end-to-end-multimodal-planning-with","repo_url":"https://github.com/woxihuanjiangguo/hydra-mdp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"hydra-mdp-end-to-end-multimodal-planning-with","repo_url":"https://github.com/yvanyin/goalflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"navsim","task_name":"NavSim"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/navsim-on-openscene","task":"NavSim","dataset":"OpenScene","model":"Hydra-MDP-C","rank_in_archive_order":6,"of":29,"metrics":{"PDMS":"91.0"},"uses_additional_data":false},{"leaderboard":"/sota/navsim-on-openscene","task":"NavSim","dataset":"OpenScene","model":"Hydra-MDP++","rank_in_archive_order":7,"of":29,"metrics":{"PDMS":"91.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.06978","atlas_url":"https://app.syntology.ai/?focus=2406.06978","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}