An Integrated Framework for Time‐Sequential Trajectory Planning and Adaptive Control of a Transfer Manipulator

This paper presents an integrated framework for time‐sequential trajectory planning and adaptive control of a transfer manipulator operating in compact spaces, with the aim of ensuring the safety of operation, reducing total load transfer time, and improving efficiency. Unlike conventional approaches that treat trajectory planning and control as separate processes, this work proposes a tightly coupled framework that simultaneously optimizes both trajectory generation and motion control for enhanced performance. First, a radial basis function neural network (RBFNN) is employed to online approximate state‐dependent unknown nonlinearities in the system. Second, a composite nonlinear disturbance observer (NDO) incorporating RBFNN approximation results is designed to compensate for both external disturbances and approximation errors, thereby significantly reducing the system uncertainties. Third, an adaptive finite‐time prescribed performance (AFPP) control method is developed to guarantee output constraints, establishing fundamental safety conditions for time‐overlapped trajectory planning. Based on this high‐precision controller with guaranteed output constraints, time‐sequential trajectories with overlapping phases are optimally designed considering physical space constraints, which not only ensures operational safety in compact spaces but also substantially improves load transfer efficiency. The simulation results validate the robustness and effectiveness of the proposed approach, demonstrating significant improvements in both safety and control precision in highly constrained environments.