For high-precision attitude adjustment tasks of a six-degree-of-freedom (6-DOF) wave-compensation parallel robot in shipborne applications, strong non-stationary wave excitations, abrupt load changes, and broadband disturbances jointly challenge tracking accuracy and smoothness. To address these challenges, this paper proposes a tuna swarm optimization (TSO)-tuned triple-loop Fractional-Order PI control strategy (TSO-FOPI). The proposed approach combines TSO-based offline parameter tuning with a triple-loop FOPI control structure to improve compensation accuracy and robustness, and a closed-loop stability analysis is provided. Power spectral density analysis under swept-frequency excitation indicates that TSO-FOPI effectively suppresses residual vibrations of the robot in the dominant wave-frequency band and achieves better wideband disturbance rejection against injected high-frequency perturbations. Furthermore, under random wave excitation corresponding to sea state 4, the proposed control strategy reduces the overall compensation error by about 59% and 36.4% compared with PI and FOPI controllers, respectively, and improves the overall compensation smoothness by about 65% and 30.25%. In summary, the proposed method shows potential for engineering implementation for high-precision motion control of 6-DOF wave-compensation parallel robots and onboard precision equipment in disturbance-intensive environments.
To improve the accuracy and robustness of target grasp detection and classification for robotic manipulators in unstructured environments such as workshops, a multi-task grasp detection algorithm based on a global channel–spatial attention mechanism is proposed. Through the global channel attention module, the network is able to extract richer semantic information while reducing redundant feature information, thereby improving overall performance. The effectiveness of the proposed algorithm is validated on the Cornell dataset and a self-built dataset. The grasp prediction accuracy reaches 99.5% on the Cornell dataset, while on the self-built dataset the grasp detection accuracy reaches 98.5% and the object classification accuracy reaches 99.5%. To further verify the effectiveness of the algorithm, grasping experiments are conducted on an AUBO-i3 robotic manipulator. The results show that the average grasping accuracy reaches 95% for unseen daily items and common workshop objects, which is 8.75% higher than the baseline GGCNN network. These results indicate that the proposed algorithm can effectively perform grasping tasks for robotic manipulators in unstructured environments.