四足机器人在仿真中学会多阶段抓取放置，真实世界成功率近80%。
Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator
- 全仿真训练视觉运动策略，实现搜索-靠近-抓取-运输-放置全流程
- 真实环境成功率接近80%，支持重抓、任务链等复杂行为
- 适用于室内外多种场景，适合移动操作机器人研究者参考
基于四足的移动操作面临技能多样性、任务周期长和部分可观测性的挑战。本文以一个多阶段抓取放置任务为简明但丰富的设置，捕捉四足移动操作的关键需求。提出一种完全在仿真中训练视觉运动策略的方法，在真实世界中实现了近80%的成功率。该策略能高效执行搜索、靠近、抓取、运输和放置动作，涌现出重抓和任务链等行为。通过大量真实实验与消融研究，验证了高效训练与有效仿真到现实迁移的关键技术。额外实验展示了在多种室内外环境中的部署能力。演示视频及更多资源见项目页：https://horizonrobotics.github.io/gail/SLIM。
原文摘要 · Abstract (English)
Quadruped-based mobile manipulation presents significant challenges in robotics due to the diversity of required skills, the extended task horizon, and partial observability. After presenting a multi-stage pick-and-place task as a succinct yet sufficiently rich setup that captures key desiderata for quadruped-based mobile manipulation, we propose an approach that can train a visuo-motor policy entirely in simulation, and achieve nearly 80\% success in the real world. The policy efficiently performs search, approach, grasp, transport, and drop into actions, with emerged behaviors such as re-grasping and task chaining. We conduct an extensive set of real-world experiments with ablation studies highlighting key techniques for efficient training and effective sim-to-real transfer. Additional experiments demonstrate deployment across a variety of indoor and outdoor environments. Demo videos and additional resources are available on the project page: https://horizonrobotics.github.io/gail/SLIM.
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。