论文/arXiv 2610.07681·22 天前

EigenDEXplore：利用人类先验进行灵巧操作的结构化探索

提出EigenDEXplore，用人手先验特征向量结构化关节空间探索，并在多种灵巧手与操作任务中验证。

AI 整理

• 本体 SDK 与控制
• 仿真与训练
• 数据与采集

原文链接：EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors（arXiv 2610.07681 · 发布日期：2026-10-06）

EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors

提出EigenDEXplore，用人手先验特征向量结构化关节空间探索，并在多种灵巧手与操作任务中验证。

核心要点

• 灵巧操作需多关节协调，独立关节扰动难以发现有效协调行为。
• 方法在保持动作空间不变的同时，沿人类数据得到的特征向量加入相关扰动。
• 实验表明其在抓取、手内重定向和接触丰富操作中优于关节空间与学习动作空间基线。
• 收益覆盖无结构与参考引导RL、轨迹优化和sim-to-real部署，弱奖励塑形与课程设计时更明显。

验证范围与局限：验证范围包括多种灵巧手的抓取、手内重定向和接触丰富操作，并涵盖sim-to-real部署。

英文摘要 (Abstract)

Dexterous manipulation poses a challenging high-dimensional optimization problem, as useful behaviors require coordinated motion across many hand joints. In reinforcement learning (RL) and sampling-based trajectory optimization, exploration commonly relies on independent robot joint perturbations, making coordinated behaviors difficult to discover. Prior work reduces this search space for grasp learning using low-dimensional spaces of coordinated joint motions learned from human hand data, but this restricts the expressivity required for general manipulation. Some combine learned and joint-space actions to restore expressivity, but this increases dimensionality and introduces redundancy. We study these effects across diverse manipulation settings, varying action dimensionality, exploration strategy, and the source of human data. Our experiments suggest that human-motion priors are most effective when used to structure exploration rather than change the action representation. Motivated by this finding, we propose EigenDEXplore, which induces correlated exploration by adding perturbations along human-derived eigenvectors to independent joint-space noise, leaving the action space unchanged. Across multiple dexterous hands, EigenDEXplore consistently outperforms joint-space and learned action-space baselines in grasping, in-hand reorientation, and contact-rich manipulation. These gains span unstructured and reference-guided RL, trajectory optimization, and sim-to-real deployment, and are largest in settings with less reward shaping and curriculum design.

作者：Harsh Gupta, Tyler Ga Wei Lum, Changhao Wang, Chuer Pan, C. Karen Liu, Jeannette Bohg, Shuran Song

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.07681：EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors访问 2026-10-21