{"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/orion-a-holistic-end-to-end-autonomous","title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","arxiv_id":"2503.19755","date":"2025-03-25","proceeding":null,"authors":["Haoyu Fu","Diankun Zhang","Zongchuang Zhao","Jianfeng Cui","Dingkang Liang","Chong Zhang","Dingyuan Zhang","Hongwei Xie","Bing Wang","Xiang Bai"],"abstract":"End-to-end (E2E) autonomous driving methods still struggle to make correct decisions in interactive closed-loop evaluation due to limited causal reasoning capability. Current methods attempt to leverage the powerful understanding and reasoning abilities of Vision-Language Models (VLMs) to resolve this dilemma. However, the problem is still open that few VLMs for E2E methods perform well in the closed-loop evaluation due to the gap between the semantic reasoning space and the purely numerical trajectory output in the action space. To tackle this issue, we propose ORION, a holistic E2E autonomous driving framework by vision-language instructed action generation. ORION uniquely combines a QT-Former to aggregate long-term history context, a Large Language Model (LLM) for driving scenario reasoning, and a generative planner for precision trajectory prediction. ORION further aligns the reasoning space and the action space to implement a unified E2E optimization for both visual question-answering (VQA) and planning tasks. Our method achieves an impressive closed-loop performance of 77.74 Driving Score (DS) and 54.62% Success Rate (SR) on the challenge Bench2Drive datasets, which outperforms state-of-the-art (SOTA) methods by a large margin of 14.28 DS and 19.61% SR.","url_abs":"https://arxiv.org/abs/2503.19755v1","url_pdf":"https://arxiv.org/pdf/2503.19755v1.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":[],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"bench2drive","task_name":"Bench2Drive"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/bench2drive-on-bench2drive","task":"Bench2Drive","dataset":"Bench2Drive","model":"ORION","rank_in_archive_order":6,"of":35,"metrics":{"Driving Score":"77.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.19755","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}