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。
Vision-Language Models (VLMs) and world models have demonstrated strong capabilities in semantic understanding and future scene evolution for autonomous driving. However, effectively integrating both capabilities for trajectory generation remains challenging.
The fidelity of teleoperated demonstrations used for imitation learning is determined by how faithfully a robot hand can replicate the operator's posture. The posture retargeting law that the robot will execute is typically selected only once the hardware has been finalized, and conventional hand designs often neglect human-like grasping postures.
Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-horizon whole-body mobile manipulation, where long horizons amplify compounding errors and coordinated arm, torso, and base motion makes exhaustive demonstration coverage impractical.
Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the dataset. Yet not all states are created equal: in a small number of critical states, even a slight deviation from the expert action can lead to a failure, while in many other states such errors are recoverable and inconsequential.
Robot manipulation policies trained through imitation learning commonly rely on costly demonstrations recorded in one task direction and at one temporal resolution. We propose Reversal and Stride-based Trajectory Augmentation (RESTA), which exploits time-scaling data augmentation to improve data efficiency through trajectory reversal and temporal resampling.
Long-horizon robotic manipulation is inherently composed of semantically meaningful sub-tasks. While Movement Primitives (MPs) can model these components, their composition typically relies on manual engineering or sample-inefficient reinforcement learning.
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。
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。