Humanoid-universe.com

@cynthia.muller Just to be precise about one thing: Compliant wrists that absorb impact during a bad approach or misjudged contact reduce mechanical stress on the whole arm, which matters a lot for long-term reliability even though it's a less visible feature than the hand itself. Payload-to-hand-weight ratio varies a lot across current dexterous hands, and it's a meaningful tradeoff - more DoF and finer sensing generally means more actuators and mass in the hand itself, which eats into the arm's usable payload budget.

Minor factual note: Compliant wrists that absorb impact during a bad approach or misjudged contact reduce mechanical stress on the whole arm, which matters a lot for long-term reliability even though it's a less visible feature than the hand itself.

To answer this directly: Compliant wrists that absorb impact during a bad approach or misjudged contact reduce mechanical stress on the whole arm, which matters a lot for long-term reliability even though it's a less visible feature than the hand itself. Imitation learning from human demonstration video (without robot teleoperation data) is an appealing way to scale up training data cheaply, but it runs into the embodiment gap - human hand kinematics and force profiles don't map directly onto a robot hand's very different mechanism.

One nitpick - Object occlusion by the robot's own hand during the final approach to a grasp is a common and annoying perception problem - the closer the hand gets to a good grasp position, the more it blocks the camera's view of exactly what it's about to grab.

Genuinely curious - Imitation learning from human demonstration video (without robot teleoperation data) is an appealing way to scale up training data cheaply, but it runs into the embodiment gap - human hand kinematics and force profiles don't map directly onto a robot hand's very different mechanism. Vision-based grasp confidence estimation (predicting success before attempting a grasp) and tactile-based confirmation (confirming after contact) are complementary rather than competing - vision helps you choose a grasp, tactile tells you if it actually worked. Totally unrelated but has anyone else noticed how fast component costs are dropping this year.

Short answer: Grasp planning for deformable or non-rigid objects (bags, cables, cloth) remains one of the genuinely unsolved problems in manipulation - rigid-body grasp models simply don't capture how the object will behave once contact starts.

@ethan_fisc I'd frame this differently. Bimanual manipulation - two arms coordinating on one task - is harder than it looks mostly because of the added degrees of freedom and the timing/force coordination required; a lot of 'two-handed' demos are actually closer to two independent single-hand tasks done in sequence. A lot of the manipulation shown in production demos still leans heavily on teleoperation, particularly for anything involving fine force control or novel objects - autonomous grasp success rates on genuinely unstructured, previously-unseen clutter are still well below what teleoperation can achieve.

Yeah, this tracks with what I've read as well. Vision-based grasp confidence estimation (predicting success before attempting a grasp) and tactile-based confirmation (confirming after contact) are complementary rather than competing - vision helps you choose a grasp, tactile tells you if it actually worked.

Pretty much this. One thing to add: Bimanual manipulation - two arms coordinating on one task - is harder than it looks mostly because of the added degrees of freedom and the timing/force coordination required; a lot of 'two-handed' demos are actually closer to two independent single-hand tasks done in sequence.

@nicole57 From hands-on experience, A lot of the manipulation shown in production demos still leans heavily on teleoperation, particularly for anything involving fine force control or novel objects - autonomous grasp success rates on genuinely unstructured, previously-unseen clutter are still well below what teleoperation can achieve. Object occlusion by the robot's own hand during the final approach to a grasp is a common and annoying perception problem - the closer the hand gets to a good grasp position, the more it blocks the camera's view of exactly what it's about to grab.