Search papers, labs, and topics across Lattice.
3
0
3
0
A maritime navigation policy trained purely in simulation can now successfully pilot a 17-ton vessel in real-world congested waters, zero-shot.
Quadrupedal robots can now swim more efficiently and stably thanks to a novel constrained reinforcement learning approach that tames destabilizing forces in complex fluid environments.
A surgical robot now delivers instruments with 83% accuracy using vision-language models to interpret surgeon requests and avoid collisions in real-time.
