Search papers, labs, and topics across Lattice.
4
0
3
Dist-GPRL is presented, a distance-aware and safety-guided reinforcement learning framework for structured robot skill adaptation that sequentially adapts overlapping local windows of sparse trajectory via-points rather than modifying the complete skill at every policy step.
Real-time dynamic object tracking and reconstruction is now possible with unprecedented accuracy using DisFlow's innovative distance field approach.
Representing robot redundancy as an implicit field lets you smoothly interpolate between task solutions and generalize across related tasks, instead of just solving one-off problems.
Robots can now adapt demonstrated skills to significantly different starting conditions thanks to a Gaussian Process representation that preserves kinematic profiles.
