Abstract
In complex robot applications, such as human−robot interaction and robot machining, robots should interact with an unknown environment. To learn the interactive skill, a model-based actor−critic learning algorithm and a safety-learning strategy are proposed in this article to find the optimal impedance control, in which the learning process is safe and fully automatic and does not know the system parameter. In the learning algorithm, a critic is defined as a quadratic form of the system states and the external force. A modified deterministic policy gradient algorithm is presented to improve the learning efficiency. The proposed approach utilizes a model-based constraint and a highly efficient learning algorithm. In the safety-learning strategy, the robot is trained under a constant force, and the learned impedance control can transfer to different interaction situations by choosing the suitable impedance index. The effectiveness of the learning algorithm and the performance of the learned impedance control are validated in a UR5 robot. The robot can perform human−robot interaction and robot machining tasks after the training process with 100 s training time.
Highlights
With the increasing need for safe, reliable and efficient physical robot-environment interaction, impedance control is a permission tool to deal with different interaction tasks, such as robot assembly tasks [1], robot machining [2], human-robot interaction [3], collaborative manufacturing [4], robotic surgical procedures [5], and robotic manipulation [6]
They developed a robot controller that concurrently adapts to feedforward force, impedance, and reference trajectory when a robot interacts with an unknown environment [14]
The model-based AC learning of impedance control and the safety-learning strategy are investigated by the numerical simulation
Summary
With the increasing need for safe, reliable and efficient physical robot-environment interaction, impedance control is a permission tool to deal with different interaction tasks, such as robot assembly tasks [1], robot machining [2], human-robot interaction [3], collaborative manufacturing [4], robotic surgical procedures [5], and robotic manipulation [6]. The main difficulty in the impedance control of robots is to overcome the confliction between motion accuracy and interaction safety [9]. Li et al proposed impedance learning for robots interacting with unknown environments [13], which aims to adjust impedance parameters to achieve safe and stable contact with humans. They developed a robot controller that concurrently adapts to feedforward force, impedance, and reference trajectory when a robot interacts with an unknown environment [14]. To realize RL of robotic impedance control, a model-based actor-critic (AC) learning algorithm and a safety-learning strategy are proposed in this paper.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have