Search papers, labs, and topics across Lattice.
5
0
4
15
A new SF-GVF with prescribed physical speed (PPS) that converge exponentially to the desired path from any initial condition in the higher-dimensional space (including virtual dimension); more importantly, the robot's physical speed converges to the PPS, while the path-error dynamics remain invariant under regular reparameterizations of the desired path.
Achieving simultaneous arrival for multi-robot systems with curvature and speed constraints could revolutionize cooperative tasks in dynamic environments.
Achieving a 37% improvement in success rates for dexterous manipulation tasks, DexPIE redefines the role of real-world experience in policy training.
Humanoid robots can now sprint at 6 m/s with zero-shot sim-to-real transfer, thanks to a surprisingly data-efficient approach using frequency-domain priors learned from just five human motion sequences.
Achieve more accurate and autonomous 3D reconstruction of complex industrial parts by using reinforcement learning to optimize robotic viewpoint planning.
