自动生成复杂抓取任务的仿真环境，提升灵巧手训练效率。
GenDexHand: Generative Simulation for Dexterous Hands
- 通过视觉语言模型反馈闭环优化物体布局与尺度，提升环境质量。
- 将任务分解为子任务，实现分步强化学习，训练速度更快、成功率更高。
- 适合研究灵巧操作与机器人仿真数据生成的学者和工程师。
数据稀缺仍是具身智能的核心瓶颈。现有方法利用大语言模型自动化生成基于夹爪的仿真任务，但难以迁移至对环境设计要求更高的灵巧操作。由于自由度更高，灵巧操作本身更具挑战性，大规模生成可行且可训练的灵巧手任务仍是开放难题。为此，我们提出 GenDexHand，一个自动生成灵巧操作机器人任务与环境的生成式仿真流程。该方法引入闭环精炼机制，根据视觉-语言模型反馈动态调整物体位置与尺度，显著提升生成环境的平均质量。每个任务进一步分解为子任务，支持顺序强化学习，有效降低训练时间并提高成功率。本工作为具身智能中多样化灵巧手行为的可扩展训练提供了基于仿真的合成数据生成方案。
原文摘要 · Abstract (English)
Data scarcity remains a fundamental bottleneck for embodied intelligence. Existing approaches use large language models (LLMs) to automate gripper-based simulation generation, but they transfer poorly to dexterous manipulation, which demands more specialized environment design. Meanwhile, dexterous manipulation tasks are inherently more difficult due to their higher degrees of freedom. Massively generating feasible and trainable dexterous hand tasks remains an open challenge. To this end, we present GenDexHand, a generative simulation pipeline that autonomously produces diverse robotic tasks and environments for dexterous manipulation. GenDexHand introduces a closed-loop refinement process that adjusts object placements and scales based on vision-language model (VLM) feedback, substantially improving the average quality of generated environments. Each task is further decomposed into sub-tasks to enable sequential reinforcement learning, reducing training time and increasing success rates. Our work provides a viable path toward scalable training of diverse dexterous hand behaviors in embodied intelligence by offering a simulation-based solution to synthetic data generation. Our website: https://winniechen2002.github.io/GenDexHand/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。