Search papers, labs, and topics across Lattice.
Beijing Institute for General Artificial Intelligence (BIGAI), Beijing University of Aeronautics and Astronautics ∗*Equal contribution
4
0
4
3
Joint pretraining on Ego2Robot-synthesized data boosts robot generalization, achieving unprecedented scale and diversity in training datasets.
Explicitly incorporating contact priors into visuo-tactile policies can boost manipulation success rates by over 21% in real-world scenarios.
HandTouch outperforms existing tactile encoders, achieving an 85.23% Recall@5 in similarity retrieval—an improvement of over 10%—demonstrating the power of combining egocentric vision with tactile data.
Achieving a 27% real-world grasp success rate for blind grasping with dexterous hands using only tactile feedback marks a significant leap in robotic manipulation capabilities.
