{"ID":2885248,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05402","arxiv_id":"2508.05402","title":"DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model","abstract":"End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives and lacks of planning-oriented understanding, which limits the robustness of the overall decision-making prcocess. In this work, we introduce DistillDrive, an end-to-end knowledge distillation-based autonomous driving model that leverages diversified instance imitation to enhance multi-mode motion feature learning. Specifically, we employ a planning model based on structured scene representations as the teacher model, leveraging its diversified planning instances as multi-objective learning targets for the end-to-end model. Moreover, we incorporate reinforcement learning to enhance the optimization of state-to-decision mappings, while utilizing generative modeling to construct planning-oriented instances, fostering intricate interactions within the latent space. We validate our model on the nuScenes and NAVSIM datasets, achieving a 50\\% reduction in collision rate and a 3-point improvement in closed-loop performance compared to the baseline model. Code and model are publicly available at https://github.com/YuruiAI/DistillDrive","short_abstract":"End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives and lacks of planning-oriented understanding, which limits the robustness of the...","url_abs":"https://arxiv.org/abs/2508.05402","url_pdf":"https://arxiv.org/pdf/2508.05402v1","authors":"[\"Rui Yu\",\"Xianghang Zhang\",\"Runkai Zhao\",\"Huaicheng Yan\",\"Meng Wang\"]","published":"2025-08-07T13:54:35Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\"]","methods":"[\"Reinforcement Learning\"]","has_code":false,"code_links":[{"ID":611167,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2885248,"paper_url":"https://arxiv.org/abs/2508.05402","paper_title":"DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model","repo_url":"https://github.com/YuruiAI/DistillDrive","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}