Abstract
Collaborative control of a dual-arm robot refers to collision avoidance and working together to accomplish a task. To prevent the collision of two arms, the control strategy of a robot arm needs to avoid competition and to cooperate with the other one during motion planning. In this paper, a dual-arm deep deterministic policy gradient (DADDPG) algorithm is proposed based on deep reinforcement learning of multi-agent cooperation. Firstly, the construction method of a replay buffer in a hindsight experience replay algorithm is introduced. The modeling and training method of the multi-agent deep deterministic policy gradient algorithm is explained. Secondly, a control strategy is assigned to each robotic arm. The arms share their observations and actions. The dual-arm robot is trained based on a mechanism of “rewarding cooperation and punishing competition”. Finally, the effectiveness of the algorithm is verified in the Reach, Push, and Pick up simulation environment built in this study. The experiment results show that the robot trained by the DADDPG algorithm can achieve cooperative tasks. The algorithm can make the robots explore the action space autonomously and reduce the level of competition with each other. The collaborative robots have better adaptability to coordination tasks.
Highlights
The rapid development of deep reinforcement learning (DRL) has provided new ideas for robot control strategies [1,2,3]
The dual-arm deep deterministic policy gradient (DADDPG) algorithm was proposed in combination with multi‐agent deep rein‐
Forcement learning, and the Hindsight Experience Replay algorithm (HER) algorithm was used to solve the problem of sparse robot rewards
Summary
The rapid development of deep reinforcement learning (DRL) has provided new ideas for robot control strategies [1,2,3]. The breakthrough of multiagent deep reinforcement learning provides a new method for multi-robot collaborative control, especially for the grasping objects that needed two-arm cooperation [14]. In order to mitigate the problem of difficult modelling and poor portability in the dualarm robot cooperative control, the dual-arm deep deterministic policy gradient algorithm was proposed. This algorithm is based on the MADDPG algorithm. Experiments show that the dual-arm deep deterministic policy gradient algorithm can improve the speed of learning from sparse reward signals, and the dual-arm robot trained by this algorithm can achieve cooperative tasks
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have