Knowing When Not to Help: Active Estimation of Human Reachability for Just-Right Robot Assistance

Robots that physically interact with humans must decide not only how and when to help, but also when not to help. In physical caregiving and collaborative manipulation, robots can over-assist by misestimating user capability or defaulting to helping when users can act independently. Physical functionality is highly individual, partially observable, difficult to specify a priori, and assistance policies are often not grounded in user-specific ability, making calibrated intervention challenging.

We address this by actively inferring human joint-space reachability from sparse interaction. Our framework represents reachability using a compositional parametric model where a box constraint is deformed by local Gaussian primitives. We learn a latent space that decodes to these parameters and structure it using biomechanical anchors from musculoskeletal simulation and clinical anchors from retrieval-augmented reasoning over rehabilitation literature. The robot maintains a belief over this manifold and actively selects calibration queries to infer user-specific functionality.

We evaluate through computational experiments and real-robot studies with participants wearing resistance bands. Our method achieves approximately 0.50 IoU within 20 queries. In sandwich making, reachability-aware assistance significantly improves user perception of physical engagement without increasing workload. In ARAT-inspired manipulation, we demonstrate online adaptation.