The learning-based optimization algorithm for robotic dual peg-in-hole assembly

Purpose This paper aims to present an optimization algorithm combined with the impedance control strategy to optimize the robotic dual peg-in-hole assembly task, and to reduce the assembly time and smooth the contact forces during assembly process with a small number of experiments. Design/methodology/approach Support vector regression is used to predict the fitness of genes in evolutionary algorithm, which can reduce the number of real-world experiments. The control parameters of the impedance control strategy are defined as genes, and the assembly time is defined as the fitness of genes to evaluate the performance of the selected parameters. Findings The learning-based evolutionary algorithm is proposed to optimize the dual peg-in-hole assembly process only requiring little prior knowledge instead of modeling for the complex contact states. A virtual simulation and real-world experiments are implemented to demonstrate the effectiveness of the proposed algorithm. Practical implications The proposed algorithm is quite useful for the real-world industrial applications, especially the scenarios only allowing a small number of trials. Originality/value The paper provides a new solution for applying optimization techniques in real-world tasks. The learning component can solve the data efficiency of the model-free optimization algorithms.