arXiv:2608. 15917v1 Announce Type: cross Abstract: Large-scale pre-training has made robot policy fine-tuning increasingly data-efficient, but this progress has largely been driven by datasets and embodiments built around simple parallel-jaw grippers.
arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.
arXiv:2606. 14561v1 Announce Type: cross Abstract: Robotics manipulation research increasingly focuses on two-finger parallel grippers for their effectiveness, affordability, and ease of teleoperation.
arXiv:2602. 13197v2 Announce Type: replace-cross Abstract: The ability to learn manipulation skills by watching videos of humans has the potential to unlock a new source of highly scalable data for robot learning.
arXiv:2609.34182v2 Announce Type: replace-cross Abstract: Dexterous manipulation requires tactile feedback. However, robot tactile demonstrations are difficult to scale,because dexterous-hand teleope...
arXiv:2607. 11874v1 Announce Type: cross Abstract: Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them.
arXiv:2607. 00033v1 Announce Type: cross Abstract: Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging.
arXiv:2608. 14028v1 Announce Type: cross Abstract: Dexterous manipulation is a fundamental capability for embodied intelligence, but scaling it remains difficult because robot demonstrations are expensive to collect and action spaces vary across embodiments.
ADEPT is a reinforcement‑learning framework that first pre‑trains a dexterous policy on a generic object reposing task and then post‑trains downstream policies using this pretrained behavior as a prior. The approach avoids relearning basic skills for each new task, and employs a stable post‑training recipe—behavior‑cloning distillation, critic warm‑up, and conservative on‑policy updates—to preserve the pretrained capabilities. ADEPT’s joint‑space Geometric Fabric mediates between the policy and the robot, enabling zero‑shot sim‑to‑real transfer on a 23‑DoF Kuka‑Allegro and a 29‑DoF Flexiv‑Sharpa, where the robots solve long‑horizon tasks from challenging initial states at human‑level speed.
Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation?
arXiv:2608.22449v1 Announce Type: cross Abstract: Forecasting dexterous hand motions from egocentric observations is fundamental to intelligent interactive systems. Existing VLM-based methods typical...
DexTouch-WM is an action‑conditioned world model that learns from scalable human touch to predict future RGB observations and bilateral tactile dynamics for dexterous robot manipulation. By using compatible piezoresistive arrays on both human and robot hands and retargeting human motion into the robot action space, the model can be supervised with human interaction data while keeping a fixed amount of real‑robot supervision. Experiments show that adding up to 100 hours of human interaction improves robot‑domain visual, geometric, and contact prediction, and the model can serve as a surrogate environment for policy evaluation and synthetic trajectory generation.
Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories frequently violate kinematic limits, incur collisions, or exceed controller bandwidth, teaching VLA policies physically infeasible actions.