Search papers, labs, and topics across Lattice.
3
0
4
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.
VOIM achieves a remarkable 44.07 mIoU in 3D instance mapping without any training, outperforming traditional systems by deferring labeling decisions until sufficient evidence is gathered.
Robots can now adapt demonstrated skills to significantly different starting conditions thanks to a Gaussian Process representation that preserves kinematic profiles.
