Incorporating Artificial Skin Signals in the Constraint-based Reactive Control of Human-Robot Collaborative Manipulation Tasks

Abstract

The aim of this work is to develop a control strategy for human-robot collaborative manipulation that can deal with the large amount of sensor data of an artificial skin. This artificial skin contains 373 interconnected cells of which proximity information is used. The robot and the operator accomplish an industrial task while interacting in a shared work space. The robot controller detects and avoids collisions based on the information from the artificial skin. To decrease the amount of data, a discrete optimization algorithm selects up to a specified number of cells based on the signal intensity and the spatial distribution of the activated cells. The robotic task is specified using eTaSL (expression graph specification language) which provides reactive control using a constraint-based optimization approach. Conflicting constraints can be handled by prioritizing in hard and soft constraints or by weighing the different constraints. Weak soft constraints (low weight) are specified to command the robot to move along a nominal path with constant velocity. Stronger soft constraints (higher weight) prevent collisions by means either of moving the end effector backwards along the path or circumventing an obstacle. The proposed approach is validated experimentally.