Adaptive Robust Controller Design-Based RBF Neural Network for Aerial Robot Arm Model

• DOI: 10.3390/electronics10070831
• Publication Date: 2021-03-31T14:24:33Z
• Authors: Izzat Al-Darraji; Dimitrios Piromalis; Ayad Kakei; Fazal Khan; Milos Stojmenovic; Georgios Tsaramirsis; Panagiotis Papage...
• Keywords: Payload (computing)

Aerial Robot Arms (ARAs) enable aerial drones to interact and influence objects in various environments. Traditional ARA controllers need the availability of a high-precision model avoid high control chattering. Furthermore, practical applications object manipulation, payloads that ARAs can handle vary, depending on nature task. The uncertainties due modeling errors an unknown payload are inversely proportional stability ARAs. To address issue stability, new adaptive robust controller, based Radial Basis Function (RBF) neural network, is proposed. A three-tier approach also followed. Firstly, detailed for derived using Lagrange–d’Alembert principle. Secondly, sliding mode, designed manipulate problem uncertainties, including errors. Last, higher RBF implemented with controller stabilize ARAs, avoiding issues. novelty proposed design it takes into account nonlinearities, coupling loops, errors, disturbances environmental conditions. was evaluated by simulation case study includes two trajectory tracking. results show validation notability presented algorithm.