外观
论文arXiv 2604.251266 个月前
HANDFUL框架实现资源感知灵巧手序列操作与LEAP手实机验证
本文由 AI 根据公开内容整理，可能有误，请以原文为准：HANDFUL: Sequential Grasp-Conditioned Dexterous Manipulation with Resource Awareness（arXiv 2604.25126）
核心内容
针对灵巧机器人需在执行初始抓取后保持控制并完成第二子任务的序列操作需求，研究团队提出HANDFUL学习框架。该方法突破单物体单技能局限，将手指占用建模为有限资源，通过课程学习策略优化抓取规划。配套发布的HANDFUL-Bench仿真基准涵盖推、拉、压等多种共享抓取条件下的子任务目标，实验证实资源感知抓取相比贪婪优化基线显著提升了第二子任务的成功率与鲁棒性，且已在真实LEAP灵巧手上完成验证。
技术层面，HANDFUL核心在于引入手指级接触奖励机制，鼓励策略探索“资源感知型”抓取姿态，即在稳固持物的同时预留空闲手指用于后续操作，而非仅优化当前抓握稳定性。系统采用基于课程学习的策略选择机制，根据下游任务需求动态匹配最优抓取方案。该框架解决了传统方法因过度消耗手指自由度导致序列任务中断的问题，为多功能灵巧操作提供了从仿真训练到真机部署的完整技术路径，相关补充材料与代码已在项目主页开源。
关键看点
- 资源感知建模：将手指定义为有限资源，通过手指级接触奖励引导策略保留操作冗余度
- 序列任务基准：发布HANDFUL-Bench仿真环境，支持推拉压等多目标共享抓取条件评测
- 性能对比验证：仿真结果显示资源感知策略在第二子任务成功率与鲁棒性上优于贪婪基线
- 真机部署验证：在LEAP灵巧手上成功验证框架有效性，实现抓取保持下的连续多功能操作
工程与产业观察
该工作确立了“资源感知抓取”作为灵巧手序列操作的关键工程原则，解决了多步任务中自由度分配冲突痛点。其手指级奖励设计与课程学习范式可直接迁移至其他高自由度末端执行器训练，为具身智能复杂操作技能库构建提供了可复用的算法组件与标准化评测基准。
英文摘要 (Abstract)
Dexterous robot hands offer rich opportunities for multifunctional manipulation, where a robot must execute multiple skills in sequence while maintaining control over previously grasped objects. Most prior work in dexterous manipulation focuses on single-object, single-skill tasks. In contrast, our insight is that many sequential tasks require resource-aware grasps that conserve fingers for future actions. In this paper, we study sequential grasp-conditioned dexterous manipulation, where a robot first grasps an object and then performs a second, distinct manipulation subtask while preserving the initial grasp. We introduce HANDFUL, a learning framework that models finger usage as a limited resource and encourages exploration of resource-aware grasps through finger-level contact rewards. These grasps are subsequently selected for downstream tasks via curriculum-based policy learning. We further propose HANDFUL-Bench, a simulation benchmark that introduces sequential dexterous manipulation tasks across multiple secondsubtask objectives, including pushing, pulling, and pressing, under a shared grasp-conditioned setup. Extensive simulation results demonstrate that prioritizing resource-aware grasps improves second-subtask success and robustness compared to a baseline that greedily optimizes the initial grasp before attempting the second subtask. We additionally validate our approach on a real dexterous LEAP hand. Together, this work establishes resource-aware grasp planning as a key principle for multifunctional dexterous manipulation. Supplementary material is available on our website: https://handful-dex.github.io.
作者：Ethan Foong, Yunshuang Li, Hao Jiang, Gaurav S. Sukhatme, Daniel Seita
来源
本页事实对应的公开页面，以原文为准。