Search papers, labs, and topics across Lattice.
4
0
3
9
StereoPatch is introduced, a patch-aligned RGB-depth representation that binds registered metric geometry directly to the RGB patches used for action prediction and suggests that resolving control-relevant geometric ambiguity benefits from aligning depth directly with the visual features used for action prediction.
NestDex transforms how robots learn dexterous manipulation by enabling operators to focus on arm control while the system autonomously manages intricate finger movements.
ContactGuard can predict manipulation failures before contact, enabling robots to abort actions and avoid costly mistakes in real-time.
Achieving 90.8% semantic accuracy, SemAnCorr revolutionizes zero-shot manipulation by enabling reliable skill transfer across diverse object geometries with just one demonstration.
