SimToolReal：面向零样本靈巧工具操作的物件導向策略

SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation

February 18, 2026

作者: Kushal Kedia, Tyler Ga Wei Lum, Jeannette Bohg, C. Karen Liu

cs.AI

摘要

操作工具的能力显著拓展了机器人可执行的任务范围。然而工具操作代表着一类具有挑战性的精细操作技能，需要掌握细长物体的抓取、手内物体旋转以及强力交互等能力。由于针对这些行为收集远程操作数据颇具挑战性，仿真到现实的强化学习（RL）成为一种前景广阔的替代方案。但现有方法通常需要大量工程工作来建模物体并为每个任务调整奖励函数。本研究提出SimToolReal方法，朝着通用化工具操作的仿真到现实强化学习策略迈出重要一步。通过程序化生成大量仿真环境中的工具化物体基元，并训练具有通用目标的单一强化学习策略——将每个物体操控至随机目标位姿，该方法使SimToolReal在测试时无需任何物体或任务特定训练即可执行通用精细工具操作。实验表明，SimToolReal在特定目标物体和任务上的表现与专业强化学习策略相当，同时比先前的重定向方法和固定抓取方法的性能提升37%。最后我们证明，SimToolReal能够泛化至多种日常工具，在涵盖24项任务、12个物体实例和6种工具类别的120次现实世界测试中展现出强大的零样本性能。

English

The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging class of dexterity, requiring grasping thin objects, in-hand object rotations, and forceful interactions. Since collecting teleoperation data for these behaviors is challenging, sim-to-real reinforcement learning (RL) is a promising alternative. However, prior approaches typically require substantial engineering effort to model objects and tune reward functions for each task. In this work, we propose SimToolReal, taking a step towards generalizing sim-to-real RL policies for tool manipulation. Instead of focusing on a single object and task, we procedurally generate a large variety of tool-like object primitives in simulation and train a single RL policy with the universal goal of manipulating each object to random goal poses. This approach enables SimToolReal to perform general dexterous tool manipulation at test-time without any object or task-specific training. We demonstrate that SimToolReal outperforms prior retargeting and fixed-grasp methods by 37% while matching the performance of specialist RL policies trained on specific target objects and tasks. Finally, we show that SimToolReal generalizes across a diverse set of everyday tools, achieving strong zero-shot performance over 120 real-world rollouts spanning 24 tasks, 12 object instances, and 6 tool categories.