Compensation for undefined behaviors during robot task execution by switching controllers depending on embedded dynamics in RNN
This addresses the challenge of robot recovery from disturbances in human-robot collaboration, but it appears incremental as it combines existing controller types.
The paper tackles the problem of robots compensating for undefined behaviors, such as collisions, during task execution by proposing a method that switches between learning-based and model-based controllers based on an RNN's internal representation. The results from simulations and a real robot show the method is effective and high-performing for a pick-and-place task.
Robotic applications require both correct task performance and compensation for undefined behaviors. Although deep learning is a promising approach to perform complex tasks, the response to undefined behaviors that are not reflected in the training dataset remains challenging. In a human-robot collaborative task, the robot may adopt an unexpected posture due to collisions and other unexpected events. Therefore, robots should be able to recover from disturbances for completing the execution of the intended task. We propose a compensation method for undefined behaviors by switching between two controllers. Specifically, the proposed method switches between learning-based and model-based controllers depending on the internal representation of a recurrent neural network that learns task dynamics. We applied the proposed method to a pick-and-place task and evaluated the compensation for undefined behaviors. Experimental results from simulations and on a real robot demonstrate the effectiveness and high performance of the proposed method.