Large language models (LLMs) can provide rich physical descriptions of most worldly objects, allowing robots to achieve more informed and capable grasping. We leverage LLMs’ common sense physical ...
To study fine touch, selecting samples based on how many mechanical instabilities they can form is more predictive than using the friction coefficient, which has been the default choice.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results