ContactExplorer: 接触覆盖引导的通用灵巧操作探索
ContactExplorer: Contact Coverage-Guided Exploration for General-Purpose Dexterous Manipulation
AI总结：
提出ContactExplorer方法，通过接触覆盖奖励和能量引导奖励，在灵巧操作任务中高效探索接触模式，提升样本效率和成功率。
摘要：
强化学习在Atari游戏、导航和移动等任务中取得了显著成功，这些任务中的探索通常可以通过状态或动态的新颖性来引导。相比之下，灵巧操作需要丰富的物理手-物体交互，但现有方法常受限于不稳定的基于接触的新颖性信号、低效的距离新颖性信号或依赖任务先验知识。我们提出ContactExplorer，一种用于灵巧操作任务的通用探索方法。ContactExplorer将接触表示为物体表面点与手部关键点的交集，鼓励灵巧手发现多样且新颖的接触模式，即哪些手指接触物体的哪些区域。它维护一个基于离散化物体状态（通过学习的哈希码获得）的接触计数器，捕捉每个手指与不同物体区域交互的频率。该计数器以两种互补方式利用：（1）分配基于计数的接触覆盖奖励，促进对新接触模式的探索；（2）基于能量的到达奖励，引导智能体朝向未充分探索的接触区域。我们在多种灵巧操作任务上评估ContactExplorer。实验结果表明，ContactExplorer在样本效率和成功率上显著优于现有探索方法，并且通过ContactExplorer学习的接触模式能鲁棒地迁移到现实世界。项目页面：https://contact-explorer.github.io。
英文摘要：
Reinforcement learning explores effectively in domains such as Atari games, navigation, and locomotion, where novelty over states or dynamics is a sufficient signal. In contrast, dexterous manipulation requires rich physical hand--object interactions, but existing methods often suffer from unstable contact-based novelty signals, inefficient distance novelty signals, or reliance on task-specific priors. We propose ContactExplorer, a general exploration method for dexterous manipulation tasks. ContactExplorer represents contact as the intersection between object surface points and hand keypoints, encouraging dexterous hands to discover diverse and novel contact patterns, namely which fingers contact which object regions. It maintains a contact counter conditioned on discretized object states obtained via learned hash codes. This counter is leveraged in two complementary ways: (1) a count-based contact coverage reward that promotes exploration of novel contact patterns, and (2) an energy-based reaching reward that guides the agent toward under-explored contact regions. We evaluate ContactExplorer on seven contact-rich manipulation tasks and five dexterous hand embodiments. Experimental results show that ContactExplorer substantially improves sample efficiency and success rates over existing exploration methods, that it reduces the need for task-specific priors, and that it remains effective across hand embodiments and transfers to the real world. Project page is https://contact-explorer.github.io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
