Online Learning of Human Constraints from Feedback in Shared Autonomy

arXiv:2403.02974v1 Announce Type: cross
Abstract: Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to divide and distribute the subtasks between the participating agents to carry out the main task. In contrast, we propose to learn a human constraints model that, in addition, considers the diverse behaviors of different human operators. We consider a type of collaboration in …

abstract agents arxiv autonomy behavior challenges collaboration constraints cs.hc cs.lg cs.ro diverse feedback focus human humans online learning patterns real-time safety type