Search papers, labs, and topics across Lattice.
5
0
6
9
TeleDexter achieves a remarkable 75% success rate in dexterous teleoperation tasks, where existing systems fail, showcasing a leap towards human-level control in robotic manipulation.
HUGS achieves a remarkable balance between grasp success and diversity, synthesizing 3.2 million grasps that can adaptively handle objects from screws to large boxes.
Steering embodiment-agnostic policies with joint-space guidance can slash collision rates by over 90% in real-world robotic tasks.
Robot RL training can be dramatically sped up (3-10x) by decoupling CPU-based simulation from GPU-based learning, challenging the assumption that GPU-resident physics is essential for efficiency.
Key contribution not extracted.
