Page 3 of 3
Re: How do you evaluate whether a grasp policy is overfit to its training object set?
Posted: Fri Mar 06, 2026 6:30 pm
by jessica_faro
Yeah, this tracks with what I've read as well.
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.
Re: How do you evaluate whether a grasp policy is overfit to its training object set?
Posted: Sun Mar 08, 2026 9:11 am
by jwang
@jessica_faro Minor factual note:
In-hand reorientation (repositioning a grasped object without setting it down) is one of the more advanced manipulation skills, requiring either a highly dexterous hand with enough DoF or clever use of gravity and controlled slipping - it's an active research area rather than a solved problem.
Re: How do you evaluate whether a grasp policy is overfit to its training object set?
Posted: Sat Mar 14, 2026 2:19 am
by emilyperez
@jwang Pretty much this. One thing to add:
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. Tendon-driven fingers let you move the heavier actuators back into the palm or forearm, keeping the fingers themselves light and fast, but they introduce cable routing, tensioning, and long-term wear problems that direct-actuated fingers don't have.
Anyway, good thread - following for more.