OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
OneDrive: 统一的多范式驾驶与视觉-语言-动作模型
机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA School of Artificial Intelligence, University of Chinese Academy of Sciences AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University Voyager Research, Didi Chuxing School of Information Science(多模态人工智能系统国家重点实验室,中国科学院自动化所人工智能学院,中国科学院大学,AutoLab,上海交通大学人工智能学院,Voyager Research,滴滴出行,信息科学与技术学院)
AI总结 本文提出基于预训练视觉语言模型的统一自动驾驶框架,通过单一Transformer解码器整合异构解码行为,实现多任务联合优化,实验表明在nuScenes和NAVSIM上取得最优性能,且推理效率高。