研究人员开发了一个扭矩自适应模块（TAM），以改善机器人跨不同硬件和负载的运动迁移。TAM学习调整扭矩指令，使在模拟中训练的策略能够在真实机器人上稳健执行，而无需进行广泛的再训练或领域随机化。该模块已在 Franka Panda 机器人上成功实现了零样本执行，用于推箱子和平衡等任务。 AI
影响 能够更可靠地将训练好的机器人策略部署到具有不同硬件的真实世界场景中。
排序理由 该集群包含一篇详细介绍机器人运动迁移新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.06218v1 Announce Type: cross Abstract: A policy tuned for one robot often behaves differently on another, whether due to the sim-to-real gap, unknown payloads, or the differing dynamics of two instances of the same robot. In contact-rich, dynamic manipulation, even sma…
A policy tuned for one robot often behaves differently on another, whether due to the sim-to-real gap, unknown payloads, or the differing dynamics of two instances of the same robot. In contact-rich, dynamic manipulation, even small motion discrepancies can result in failure to t…