Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation

Autor:	Li, Zhenxin, Li, Kailin, Wang, Shihao, Lan, Shiyi, Yu, Zhiding, Ji, Yishen, Li, Zhiqi, Zhu, Ziyue, Kautz, Jan, Wu, Zuxuan, Jiang, Yu-Gang, Alvarez, Jose M.
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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}. Comment: The 1st place solution of End-to-end Driving at Scale at the CVPR 2024 Autonomous Grand Challenge
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.06978 Zobrazit plný text záznamu View this record from Arxiv