A major goal of current robotics research is to enable robots to become co-workers that collaborate with humans efficiently and adapt to changing environments or work-flows.
The talk presents an approach utilizing the physical interaction capabilities of compliant robots with data-driven and model-free learning in a coherent system in order to make fast reconfiguration of redundant robots feasible. Analytic approaches for solving the inverse kinematics of redundant robots under specific constraints usually require expert knowledge, the availability of rigorous kinematic models of the robot and tedious manual programming.
In order to minimize manual programming effort, the presented system shows a programming-by-demonstration approach for redundancy resolution based on physical human-robot interaction (pHRI), neural learning and a hybrid control scheme. Users with no particular robotics knowledge can perform this task in physical interaction with the compliant robot, for example to reconfigure a work cell due to changes in the environment.
For fast and efficient learning of the respective null-space constraints, a reservoir neural network is employed. It is embedded in the motion controller of the system, hence allowing for execution of arbitrary motions in task space. The presented approach allows a single human tutor to efficiently teach a compliant robot several null-space constraints in different areas of the workspace. The contribution is a system for easy reconfiguration of robotic systems through integration of learning technology, physical interaction and advanced robotics technology.
The talk presents the exploration and execution phase, the control architecture as well as an evaluation on the KUKA Light-Weight Robot. The evaluation results show that the learned model solves the redundancy resolution problem under the given constraints with sufficient accuracy and generalizes to generate valid jointspace trajectories even in untrained areas of the workspace.