用双系统架构让机器人更高效执行复杂任务
A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM
- 分两层处理：大模型慢决策，小模型快执行
- 在RoboCasa上推理更快，成功率更高
- 适合需要实时响应的智能机器人场景
视觉-语言-动作（VLA）模型因其能融合视觉信息与语言指令，使机器人完成复杂任务而受到关注。但现有模型计算量大，难以实现实时性能。为此，我们提出双过程VLA（DP-VLA），受双过程理论启发，采用层级框架：大型系统2模型（L-Sys2）负责复杂推理与决策，小型系统1模型（S-Sys1）处理实时运动控制与感知。借助视觉-语言模型（VLMs），L-Sys2以低频运行，降低计算开销；S-Sys1则确保快速精准的任务执行。在RoboCasa数据集上的实验表明，DP-VLA实现更快推理速度和更高任务成功率，为高级机器人应用提供可扩展解决方案。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models are receiving increasing attention for their ability to enable robots to perform complex tasks by integrating visual context with linguistic commands. However, achieving efficient real-time performance remains challenging due to the high computational demands of existing models. To overcome this, we propose Dual Process VLA (DP-VLA), a hierarchical framework inspired by dual-process theory. DP-VLA utilizes a Large System 2 Model (L-Sys2) for complex reasoning and decision-making, while a Small System 1 Model (S-Sys1) handles real-time motor control and sensory processing. By leveraging Vision-Language Models (VLMs), the L-Sys2 operates at low frequencies, reducing computational overhead, while the S-Sys1 ensures fast and accurate task execution. Experimental results on the RoboCasa dataset demonstrate that DP-VLA achieves faster inference and higher task success rates, providing a scalable solution for advanced robotic applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。