GPD-1: Generative Pre-training for Driving
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929625445171200 |
|---|---|
| author | Xie, Zixun Zuo, Sicheng Zheng, Wenzhao Zhang, Yunpeng Du, Dalong Zhou, Jie Lu, Jiwen Zhang, Shanghang |
| author_facet | Xie, Zixun Zuo, Sicheng Zheng, Wenzhao Zhang, Yunpeng Du, Dalong Zhou, Jie Lu, Jiwen Zhang, Shanghang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08643 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GPD-1: Generative Pre-training for Driving Xie, Zixun Zuo, Sicheng Zheng, Wenzhao Zhang, Yunpeng Du, Dalong Zhou, Jie Lu, Jiwen Zhang, Shanghang Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics 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. |
| title | GPD-1: Generative Pre-training for Driving |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2412.08643 |