General Purpose Task and Motion Planning for Human-Robot Teams

Abstract

In the current industrial environment, product customization and process flexibility have taken a central role. Human-robot teams try to answer this demand by coupling human and robot skills. Recent developments in task planning often overlook the first step in task planning, task's discretization and formalization, which is mostly performed manually. Furthermore, resulting task plans alone may not translate into feasible solutions, due to environment constraints. Consequently, motion planning is essential for the evaluation of the tasks' validity and for obtaining appropriate outcomes. To combat this problem, a task-motion planning framework is proposed. The implementation uses a bottom-up approach for the formalization of the task, based on an input that holds an abstraction of the desired outcome. Subsequently planning graphs are generated based on the different formalizations, where task plans can be obtained and scrutinized by a motion planning module that simulates the robotic movements. The output should include the most time-efficient viable plans. This approach was tested using a furniture assembly case study. Results were taken from two prototypical objects suggested by this case study, with different levels of complexity.