Skill generalization across different tasks is currently a challenging task for robots. As for recent works based on robot learning, substantial environmental interaction costs or abundant expert data are usually needed, thus causing great harm to the robot or the operating object. In this article, feature-selected adaptation transfer is proposed, aiming at accelerating the network learning process, and reducing the harm caused by the interaction process. Based on the domain adaptation, the source domain data with small maximum mean discrepancy to the target domain are extracted to pretrain the target domain policy. By extracting the shared features of the source domain and the target domain, the knowledge transfer between old task and new task is realized. Moreover, the data, more favorable to the target domain, are selected to update the network and further improve the stability of network training. Besides, a series of peg-in-hole tasks is conducted in simulation, and they can be transferred to the real world without directly interacting with the environment.

Given the problem of exploration and utilization, the high interaction cost of deep reinforcement learning is sometimes unacceptable. Moreover, the model trained by deep reinforcement learning cannot adapt to the complex and changeable assembly environment quickly owing to the weak generalization ability. Thus, the knowledge transfer framework is established for different robot peg-in-hole assemblies in this article to reinforce the generalization ability of the assembly model and the utilization efficiency of data. In the framework, the source domain model is trained through the Proximal Policy Optimization algorithm. The model accurately predicts environmental information and dynamically adjusts the robot’s movements based on the prediction. Combined with the PI controller, the flexible peg-in-hole assembly can be quickly achieved by the robot. The policy fusion between the source and target domain MDP is realized by the Policy Fusion Transfer algorithm designed in this article. The effectiveness of the algorithm is verified and discussed based on the transfer experiments, involving different assembly objects and different assembly environments. The training results demonstrate that the environment is explored by the Policy Fusion Transfer algorithm in a safe range at the initial stage of training by reusing the assembly policy of the source domain and that the faster model convergence speed is achieved. Furthermore, the testing results suggest that the assembly success rate is improved by 26% and the assembly force is reduced by 30N. Moreover, the knowledge transfer between different peg-in-hole assemblies is realized successfully.

Transfer learning and ensemble learning are currently emerging trends in robotics, playing a vital role in the generalization of robot skills for manipulation tasks. In the face of new tasks, previous methods either learn from scratch or require substantial data and experience specific to the target domain, significantly hindering the generalization of robot skills. In this article, an ensemble transfer learning method is proposed based on domain differences. First, a hybrid approach that combines sequential and parallel ensemble learning strategies is designed. The experience of strategies in different domains can be reused in the target domain through ensemble transfer. Second, a strategy weight adjustment method is designed by considering the differences among various domains. This allows the strategies of the source domains that are more similar to the target domain to be assigned greater weights, thus maximizing the utilization of the knowledge of the source domains. The ensemble strategy not only exhibits good generalization for new tasks but also has excellent memory for old tasks. This article combines sequential and parallel ensemble learning methods based on domain difference, which can quickly generalize strategies from multiple source domains to the target domain without learning in the target domain. The dominant base strategies are enhanced through weight adjustment, and the adverse impact of poor base strategies is avoided on the overall strategy. A series of simulation and real multiple peg-in-hole assembly experiments is conducted to verify the superiority of the proposed method.

Robot automatic assembly of weak stiffness parts is difficult due to potential deformation during assembly. The robot manipulation cannot adapt to the dynamic contact changes during the assembly process. A robot assembly skill learning system is designed by combining the compliance control and deep reinforcement, which could acquire a better robot assembly strategy. In this paper, a robot assembly strategy learning method based on variable impedance control is proposed to solve the robot assembly contact tasks. During the assembly process, the quality evaluation is designed based on fuzzy logic, and the impedance parameters in the assembly process are studied with a deep deterministic policy gradient. Finally, the effectiveness of the method is verified using the KUKA iiwa robot in the weak stiffness peg-in-hole assembly. Experimental results show that the robot obtains the robot assembly strategy with variable compliant in the process of weak stiffness peg-in-hole assembly. Compared with the previous methods, the assembly success rate of the proposed method reaches 100%.

A robot screwing skill learning framework based on teaching–learning is proposed to improve the generalization ability of robots for different scenarios and objects, combined with the experience of a human operation. This framework includes task-based teaching, learning, and summarization. We teach a robot to twist and gather the operation’s trajectories, define the obstacles with potential functions, and counter the twisting of the robot using a skill-learning-based dynamic movement primitive (DMP) and Gaussian mixture model–Gaussian mixture regression (GMM-GMR). The hole-finding and screwing stages of the process are modeled. In order to verify the effectiveness of the robot tightening skill learning model and its adaptability to different tightening scenarios, obstacle avoidance trends and tightening experiments were conducted. Obstacle avoidance and tightening experiments were conducted on the robot tightening platform for bolts, plastic bottle caps, and faucets. The robot successfully avoided obstacles and completed the twisting task, verifying the effectiveness of the robot tightening skill learning model and its adaptability to different tightening scenarios.