Human-inspired compliance discrimination with a multi-degrees of freedom robotic manipulator

In humans, touch-mediated compliance perception integrates sensory feedback with adaptive motor control strategies that regulate internal muscle co-contraction. This mechanism enables the extraction of meaningful information from contact with objects, allowing for precise compliance discrimination. Inspired by this capability, in [1] we developed a biomimetic approach that combines a soft optical tactile sensor, the TacTip −which mimics the main structure of the human fingertip−, with a computational model of human touch (tactile flow) and a single degree of freedom (dof) Variable Stiffness Actuator (VSA), to infer the compliance of the explored specimen. By mapping human muscular co-contraction patterns to the control of the VSA −which emulates the agonist-antagonist behaviour of human muscles–, we demonstrated that our model-based estimation approach−achieved high-accuracy results. In this work, we demonstrate the effectiveness of our method using multi-dofs robotic platforms. The goal is to provide a contribution towards the deployment of robots with advanced perceptual and motor capabilities, working alongside and with humans. We considered a 7-dofs robotic manipulator, the Franka Emika Panda, and mapped human co-contraction profiles through Cartesian Impedance regulation. We achieved a maximum compliance estimation error of 6%, with no statistically significant differences compared to the results obtained with the single-dof VSA, confirming the robustness and generalizability of our technique to more complex robotic systems.