Bilateral Control-Based Imitation Learning for Velocity-Controlled Robot
This work enables force-controlled manipulation for robots limited to velocity commands, addressing a practical bottleneck in deploying imitation learning on widely available commercial robots.
The authors tackled the problem of applying bilateral control-based imitation learning to velocity-controlled robots, which are common commercially but previously unsupported, and demonstrated its validity through a mopping task experiment.
Machine learning is now playing important role in robotic object manipulation. In addition, force control is necessary for manipulating various objects to achieve robustness against perturbations of configurations and stiffness. The author's group revealed that fast and dynamic object manipulation with force control can be obtained by bilateral control-based imitation learning. However, the method is applicable only in robots that can control torque, while it is not applicable in robots that can only follow position or velocity commands like many commercially available robots. Then, in this research, a way to implement bilateral control-based imitation learning to velocity-controlled robots is proposed. The validity of the proposed method is experimentally verified by a mopping task.