机器人与具身智能领域的最新论文，以及每篇对产业的意义。
Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy.
这篇预印本提出 AdaTempo，一种自监督方法，通过提取多个演示中共享的相对节奏模式，对演示轨迹进行离线重采样，训练出更快执行的视觉运动策略。在5个仿真和6个真机任务上，AdaTempo 最高实现3.57倍加速，仿真平均成功率达75.5%、平均加速2.83倍，真机汇总成功率从58.3%提升到77.8%且平均快2.02倍。该方法无需运行时速度选择或在线重定时，简化部署。
这是一篇arXiv预印本。作者提出VISTA，一种工作空间级等变视觉触觉扩散策略，将腕部RGB和触觉图像投影到球面并融合，利用末端执行器姿态对齐后进行等变扩散解码。在50个演示/任务下，VISTA在8个仿真任务中平均成功率达80.9%，比最强等变基线EquiDiff+Tac高15.9个百分点；在3个真机任务上平均成功7.33/10次，远高于基线的1.33/10次。
这是一篇arXiv预印本。作者提出Sub-ID方法，用时空核相关性作为子运动分解的可辨识性判据，在合成数据上恢复地面真值参数分布，并扩展到真实三维长时程运动。该方法首次提供可计算的失效诊断，有望用于运动控制研究和机器人模仿学习。
机器人AI模型每次预测一段未来动作，执行多少步之后再重新观察环境，过去大多由工程师手动设为固定值。清华大学、北京智源人工智能研究院（BAAI）等机构发布的这篇预印本提出一个即插即用模块，在运行中自动决定这一步数，无需重新训练，就提升了Physical Intelligence和英伟达现有模型在仿真和真实双臂机器人上的成功率。
Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose Blended DAgger (BlenDAgger), an approach for collecting data to train imitation learning policies by using shared control to blend the policy's and demonstrator's actions during interventions.
While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target positions or poses. Even methods that incorporate force sensing either use it solely as an observation or, when predicting forces as part of the output, rely on a hybrid force controller.
Co-training a VLA on heterogeneous data (multi-robot, web, high-level subtask labels) lets a mobile manipulator clean unseen homes end-to-end.
论文来自 arXiv 机器人领域。尚未生成摘要的论文，显示摘要开头部分。