Article

How Human Corrections Travel Across Robots: Safety Issues in Federated VLA Adaptation

Regarding the prospects of combining federated learning with VLA policies, the research points out that sharing human-correction adaptations across tasks, environments, people, and robot embodiments carries safety risks: a shared update that raises average task success may suppress rare safety interventions or produce unsafe responses on another robot.

Part of the event: Study proposes safety requirements for federated VLA adaptation

This page provides a summary and source link only.