Federated Subspace Guided Vision-Language-Action Policy Distillation for Non-IID Multi-Robot Manipulation
Federated learning offers a natural way for multiple robots to jointly improve manipulation policies without requiring centralized access to training demonstrations. However, non-IID task and environment distributions can induce representation drift and mutually incompatible robot-policy updates, making naive parameter...
Biprodip Pal, Kaushik Roy, Yan-Ming Zhu et al.
· 0 citations