Event
Active Perception of Upper-Limb Range of Motion via Robot Object Handovers
1 reports · 1 sources
Francesco Semeraro and co-authors propose a method for actively perceiving upper-limb functional range of motion through human-robot object handovers: range-of-motion estimation is formulated as an active perception problem, in which an impairment coefficient parameterizes the reduction of healthy joint limits and is integrated into the human model used during robot interaction. The robot actively probes the user through repeated handover requests, progressively updating a Bayesian belief over the impairment coefficient. The authors report that simulation studies and a proof of concept on a robot platform show the pipeline can recover the impairment coefficient with reasonable accuracy in real human-robot handovers; the physical validation used simulated impairment rather than real patients.
Report timeline
- Active Perception of Upper-Limb Functional Mobility Through Human-Robot Handovers
This study formulates upper-limb functional mobility estimation as an active perception problem, parameterizing reductions in healthy joint limits with impairment coefficients and integrating this into a human model used during robot interaction. The authors propose an online active perception pipeline in which the robot actively probes the user through repeated handover requests while progressively updating a Bayesian belief over the impairment coefficients. Simulation studies and a proof of concept on a robotic platform show that the pipeline can recover the impairment coefficients with relatively high accuracy in real human-robot handovers.
arXiv cs.RO ·