Search papers, labs, and topics across Lattice.
This work was partially supported by the Texas Robotics Industrial Affiliate Program.*Equal contribution. All authors are with The University of Texas at Austin, TX, USA. Correspondence: siqi.shang@utexas.edu
1
0
3
1
Forget hand-engineered force models: a vision-language model, conditioned on past grasp attempts, can predict the perfect pre-grasp force, boosting success rates by 24% on real robots.
