An RBFNN-Based Prescribed Performance Controller for Spacecraft Proximity Operations with Collision Avoidance

In the mission scenario of On-Orbit Assembly (OOA), servicing spacecraft are frequently tasked with towing large-scale, flexible truss structures to designated assembly sites. This process involves complex coupled dynamics between the spacecraft and the flexible payload, which are often unmodeled or unknown, posing significant challenges to control precision. Furthermore, the proximity of other assembled structures in the construction area necessitates strict collision avoidance. To address these challenges, this paper proposes a novel adaptive robust controller for spacecraft thruster-based orbital control that integrates Prescribed Performance Control (PPC) with a Radial Basis Function Neural Network (RBFNN). The PPC framework ensures that the position tracking errors remain within user-predefined, time-varying boundaries, providing an intrinsic mechanism for collision avoidance during the towing of large flexible structures. Concurrently, the RBFNN is employed to approximate the entire unknown nonlinear dynamics of the combined spacecraft-truss system online, effectively compensating for uncertainties arising from the flexibility of the truss and external disturbances. The performance of the proposed controller is validated through both numerical simulations and hardware experiments on a ground-based air-bearing satellite simulator. Simulation results demonstrate the controller's superior tracking accuracy compared to a conventional PID controller, while strictly adhering to the prescribed error constraints. Experimental results further confirm its effectiveness, showing that the simulator can track a desired trajectory with high precision, with tracking errors converging to approximately 5 mm while consistently remaining within the predefined safety boundaries. The proposed approach provides a robust and safe control solution for complex proximity operations in on-orbit construction, eliminating the need for precise dynamic modeling of flexible payloads.