RobotUse：分配计算、上下文与决策
RobotUse: Allocating Computation, Context, and Decisions
浏览论文内容
中文总结 AI 辅助
RobotUse通过分配计算、上下文和决策，使机器人智能体在多次尝试中修正行动，在RoboLab上实现45%成功率，优于CaP-X 6.7个百分点，并能从真实执行中学习。
中文摘要 AI 辅助
机器人智能体必须将其预期行动与观察到的结果联系起来，同时保留在多次尝试中修正选择所需的上下文。现有接口往往将这些选择留在预定义的工具中，或要求智能体管理详细的执行代码及其不断增长的历史记录。我们引入了RobotUse，一个机器人智能体框架，它围绕指定和修正物理行动来组织计算、上下文和决策。智能体以视觉方式选择目标和姿态，而后端处理几何、运动规划和控制。子智能体在每个子目标内保留详细的交互，并返回后续决策所需的信息。持续框架化使智能体能够通过更新持久化的操作手册从执行中学习。在RoboLab上，RobotUse实现了45%的任务成功率，比CaP-X高出6.7个百分点，同时保持紧凑的决策上下文并减少对预定义行动抽象的依赖。此外，我们展示了RobotUse尽管反馈不完美，仍能从真实世界执行中学习，并将其所学迁移到后续任务。项目页面可在以下URL获取。
英文摘要
Robot agents must connect their intended actions to observed outcomes while retaining the context needed to revise their choices over repeated attempts. Existing interfaces often leave these choices inside predefined tools or require agents to manage detailed execution code and its growing history. We introduce RobotUse, a robot agent harness that organizes computation, context, and decisions around specifying and revising physical actions. Agents visually select targets and poses, while the backend handles geometry, motion planning, and control. Subagents retain detailed interactions within each subgoal and return the information needed for subsequent decisions. Continual harnessing lets agents learn from execution by updating a persistent playbook. On RoboLab, RobotUse achieves 45% task success, outperforming CaP-X by 6.7 percentage points while maintaining compact decision contexts and reducing reliance on predefined action abstractions. Furthermore, we show that RobotUse learns from real-world execution despite imperfect feedback and transfers what it learns to subsequent tasks. Project page is available at https://robotuse-team.github.io/.
发表机构
- KAIST（韩国科学技术院）
- Seoul National University（首尔大学）
机构由 AI 辅助整理，请以论文原文为准。
