Characterizing Multidimensional Capacitive Servoing for Physical Human–Robot Interaction

Toward the goal of robots performing robust and intelligent physical interactions with people, it is crucial that are able to accurately sense human body, follow trajectories around track motion. This study introduces a capacitive servoing control scheme allows robot navigate limbs during close interactions. Capacitive leverages temporal measurements from multielectrode sensor array mounted on robot's end effector estimate relative position orientation (pose) nearby limb. then uses these pose estimates data-driven estimator within feedback loop in order maneuver surface We provide design overview sensors for human–robot interaction investigate performance generalization through an experiment 12 participants. The results indicate multidimensional enables move proximally or distally along while adapting pose. Using cross-validation experiment, further show generalizes well across people different body size.