{"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/gpd-1-generative-pre-training-for-driving","title":"GPD-1: Generative Pre-training for Driving","arxiv_id":"2412.08643","date":"2024-12-11","proceeding":null,"authors":["Zixun Xie","Sicheng Zuo","Wenzhao Zheng","Yunpeng Zhang","Dalong Du","Jie zhou","Jiwen Lu","Shanghang Zhang"],"abstract":"Modeling the evolutions of driving scenarios is important for the evaluation and decision-making of autonomous driving systems. Most existing methods focus on one aspect of scene evolution such as map generation, motion prediction, and trajectory planning. In this paper, we propose a unified Generative Pre-training for Driving (GPD-1) model to accomplish all these tasks altogether without additional fine-tuning. We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem. We adopt the autoregressive transformer architecture and use a scene-level attention mask to enable intra-scene bi-directional interactions. For the ego and agent tokens, we propose a hierarchical positional tokenizer to effectively encode both 2D positions and headings. For the map tokens, we train a map vector-quantized autoencoder to efficiently compress ego-centric semantic maps into discrete tokens. We pre-train our GPD-1 on the large-scale nuPlan dataset and conduct extensive experiments to evaluate its effectiveness. With different prompts, our GPD-1 successfully generalizes to various tasks without finetuning, including scene generation, traffic simulation, closed-loop simulation, map prediction, and motion planning. Code: https://github.com/wzzheng/GPD.","url_abs":"https://arxiv.org/abs/2412.08643v1","url_pdf":"https://arxiv.org/pdf/2412.08643v1.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":"gpd-1-generative-pre-training-for-driving","repo_url":"https://github.com/wzzheng/gpd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"gpd-1-generative-pre-training-for-driving","repo_url":"https://github.com/wzzheng/doe","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":"decision-making","task_name":"Decision Making"},{"task_slug":"motion-planning","task_name":"Motion Planning"},{"task_slug":"scene-generation","task_name":"Scene Generation"},{"task_slug":"trajectory-planning","task_name":"Trajectory Planning"},{"task_slug":"motion-prediction","task_name":"motion prediction"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}