This paper aims to automatically plan sequence for complex assembly products and improve assembly efficiency.
An assembly sequence planning system for workpieces (ASPW) based on deep reinforcement learning is proposed in this paper. However, there exist enormous challenges for using DRL to this problem due to the sparse reward and the lack of training environment. In this paper, a novel ASPW-DQN algorithm is proposed and a training platform is built to overcome these challenges.
The system can get a good decision-making result and a generalized model suitable for other assembly problems. The experiments conducted in Gazebo show good results and great potential of this approach.
The proposed ASPW-DQN unites the curriculum learning and parameter transfer, which can avoid the explosive growth of assembly relations and improve system efficiency. It is combined with realistic physics simulation engine Gazebo to provide required training environment. Additionally with the effect of deep neural networks, the result can be easily applied to other similar tasks.
