An RL-NSGA-DP algorithm for optimization of robot placement and trajectory allocation in mobile robotic grinding of wind turbine blades

Abstract

Mobile robot machining, offering a more flexible and reconfigurable approach compared to fixed-base robots, has therefore become a promising solution for efficiently machining large and complex wind turbine blades. In this context, determining proper machining placements and allocating machining trajectories are two pivotal factors in the mobile robotic automation grinding of wind turbine blades, directly affecting machining efficiency and quality. However, the highly nonlinear performance distribution of the robot in the task space, combined with the complexity of the machining surface, presents significant challenges. To address these challenges, this paper presents a general optimization model of this problem with the objectives of completion time and robot manipulability, considering singularity avoidance and collision avoidance. Based on this model, an improved non-dominated sorting genetic algorithm integrated with reinforcement learning and dual population co-evolution (RL-NSGA-DP) is developed. In RL-NSGA-DP, each solution is coded using a novel two-layer metavariable encoding scheme, and a tailored dominated-recessive crossover operator is designed. Moreover, a dual-population collaborative search strategy employing different operators and an adaptive switching environmental selection mechanism based on reinforcement learning are implemented to ensure the convergence and maintain population diversity. Comparative experiments on test instances and a practical case study demonstrate that RL-NSGA-DP outperforms five well-known multi-objective evolutionary algorithms, and effectively addresses robot placement and trajectory allocation problem in mobile robotic machining systems.