Continual Hand-Eye Calibration for Open-world Robotic Manipulation

ArXi:2604.15814v1 Announce Type: new Hand-eye calibration through visual localization is a critical capability for robotic manipulation in open-world environments. However, most deep learning-based calibration models suffer from catastrophic forgetting when adapting into unseen data amongst open-world scene changes, while simple rehearsal-based continual learning strategy cannot well mitigate this issue.