SkillMimicGen：面向高效技能学习与部署的自动化演示生成
SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment
AI总结：
本文提出 SkillMimicGen 自动演示生成系统与 HSP 框架，从少量人类演示生成大规模技能数据，提升机器人长时序操作的学习、部署及零样本 sim-to-real 性能。
摘要：
从人类演示中进行模仿学习是机器人操作的一种有效范式，但获取大规模数据集成本高昂且资源密集，对于长时序任务尤其如此。为解决这一问题，我们提出 SkillMimicGen（SkillGen），这是一个可从少量人类演示生成演示数据集的自动化系统。SkillGen 将人类演示分割为多个操作技能，使这些技能适应新的情境，并通过自由空间过渡运动和转移运动将其拼接起来。我们还提出 Hybrid Skill Policy（HSP）框架，用于从 SkillGen 数据集中学习技能的启动、控制和终止组件，使技能能够在测试时借助运动规划进行排序。我们证明，相较于一个最先进的数据生成框架，SkillGen 显著提升了数据生成和策略学习性能，从而能够为包括杂乱场景在内的大规模场景变化生成数据，并使智能体的成功率平均提高 24%。我们仅用 60 个人类演示，就在仿真中跨 18 个任务变体生成了超过 24K 个演示，并训练出熟练且通常近乎完美的 HSP 智能体，以此证明 SkillGen 的有效性。最后，我们将 SkillGen 应用于 3 个真实世界操作任务，并在一个长时序装配任务上展示了零样本仿真到现实迁移。视频及更多内容见 https://skillgen.github.io。
英文摘要：
Imitation learning from human demonstrations is an effective paradigm for robot manipulation, but acquiring large datasets is costly and resource-intensive, especially for long-horizon tasks. To address this issue, we propose SkillMimicGen (SkillGen), an automated system for generating demonstration datasets from a few human demos. SkillGen segments human demos into manipulation skills, adapts these skills to new contexts, and stitches them together through free-space transit and transfer motion. We also propose a Hybrid Skill Policy (HSP) framework for learning skill initiation, control, and termination components from SkillGen datasets, enabling skills to be sequenced using motion planning at test-time. We demonstrate that SkillGen greatly improves data generation and policy learning performance over a state-of-the-art data generation framework, resulting in the capability to produce data for large scene variations, including clutter, and agents that are on average 24% more successful. We demonstrate the efficacy of SkillGen by generating over 24K demonstrations across 18 task variants in simulation from just 60 human demonstrations, and training proficient, often near-perfect, HSP agents. Finally, we apply SkillGen to 3 real-world manipulation tasks and also demonstrate zero-shot sim-to-real transfer on a long-horizon assembly task. Videos, and more at https://skillgen.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。
