A Task Allocation Approach for Human-Robot Collaboration in Product Defects Inspection Scenarios

The presence and coexistence of human operators and collaborative robots in\nshop-floor environments raises the need for assigning tasks to either operators\nor robots, or both. Depending on task characteristics, operator capabilities\nand the involved robot functionalities, it is of the utmost importance to\ndesign strategies allowing for the concurrent and/or sequential allocation of\ntasks related to object manipulation and assembly. In this paper, we extend the\n\\textsc{FlexHRC} framework presented in \\cite{darvish2018flexible} to allow a\nhuman operator to interact with multiple, heterogeneous robots at the same time\nin order to jointly carry out a given task. The extended \\textsc{FlexHRC}\nframework leverages a concurrent and sequential task representation framework\nto allocate tasks to either operators or robots as part of a dynamic\ncollaboration process. In particular, we focus on a use case related to the\ninspection of product defects, which involves a human operator, a dual-arm\nBaxter manipulator from Rethink Robotics and a Kuka youBot mobile manipulator.\n