Search papers, labs, and topics across Lattice.
4
0
5
7
Imagined tactile observations can boost robotic manipulation performance by over 44% without any physical tactile sensors.
DREAM-Chunk transforms action chunking by leveraging latent world models to enhance robustness against stochastic dynamics without the need for policy retraining.
Quadruped robots can now perform contact-rich manipulation with significantly improved dexterity by learning to "feel" their way through tasks.
Contact-rich robotic manipulation gets a 14% performance boost by adaptively ignoring force/torque signals when they're irrelevant, and fusing them intelligently with vision when contact matters.
