Suitable posture configurations are urgently requested to ensure capabilities, such as maneuverability of robotic machining, especially for complex operation tasks with mobile robots. Traditional configuration optimization methods are mainly studied for unilateral performance constraint, which are not applicable to large complex components (LCCs). This work proposes a novel global configuration method for mobile robotic grinding of LCCs that solves the optimal redundant parameters while enhancing the configuration performance, collision avoidance, and reachability. First, a robot configuration performance index (RCPI) is proposed by integrating the joint performance, singularity constraint, and collision constraint indexes based on consistency mapping. Next, the configuration optimization model for individual trajectory points is constructed, consisting of the RCPI objective function with redundant parameters and constraints taking into account the collision and reachability. Subsequently, a global configuration optimization method is developed based on an improved particle swarm optimization with compression factor, where the comprehensive fitness function is designed with the consideration of global configurations and trajectory continuity. Finally, the effectiveness and superiority of the proposed method are verified by applying optimal configuration to the mobile robotic grinding of the high-speed train body.

Accurate prediction of material removal depth and averaged surface roughness is crucial for evaluating the performance of robotic belt grinding (RBG). Nevertheless, the machining parameters of RBG across different spaces exhibit various data distributions, which often results in prediction shifts on unseen machining parameters when using conventional approaches. In this article, we introduce a pairwise domain adaptation-assisted dual-task learning (PW-DA-DTL) method for copredicting material removal depth and averaged surface roughness with regard to new RBG machining parameter spaces. The multigate mixture-of-experts method is employed as the foundational framework for dual-task learning, effectively capturing and modeling the relationships between material removal depth and average surface roughness by leveraging their inherent task interdependencies. The pairwise domain adaptation strategy is put forward to simultaneously enhance sample diversity and mitigate cross-domain data distribution discrepancy between the existing and new RBG machining parameter spaces. Comparative experiments are presented to demonstrate the effectiveness and superiority of the proposed PW-DA-DTL method.