Search papers, labs, and topics across Lattice.
5
0
5
6
Imitation learning methods may shine in controlled environments, but they falter dramatically in real-world urban settings, revealing a stark trade-off in motion planning resilience.
Adding three in-hand degrees of freedom to a traditional gripper dramatically enhances dexterity and task feasibility in robotic manipulation.
Removing explicit gait priors leads to a 56% reduction in energy costs and significantly improved adaptability in quadrupedal locomotion.
Collision detection just got a major upgrade鈥攕moothly differentiable algorithms that enhance robot behavior in complex environments.
By strategically guiding self-play with challenging real-world examples, GASP unlocks a 2.5% performance boost in coding LLMs and conquers previously unsolvable problems.
