Intelligent coordinated control of an autonomous tractor-trailer and a combine harvester

This paper addresses the tracking control of an autonomous tractor-trailer robot with a desired distance and orientation angle relative to a combine harvester in the presence of model uncertainties for the autonomous unloading of the harvested cereals in agriculture applications. A coordinate transformation and the prescribed performance technique are employed to develop a second-order Euler-Lagrange formulation of the tracking errors. Then, a neural adaptive proportional-integral-derivative (PID) tracking controller is proposed to guarantee that the tracking errors exponentially converge to an arbitrary small ultimate bound with a pre-specified maximum overshoot and convergence rate. By an effective application of the prescribed performance technique, the controller non-singularity, the collision avoidance and connectivity between two vehicles are preserved continuously. The model uncertainties including unknown vehicle parameters, variable trailer mass and moment of inertia during the crop collection, surface friction, climate and crop conditions and external disturbances are compensated by an effective combination of a multi-layer neural network and an adaptive robust control law. Lyapunov's direct method is employed to prove that the tracking errors are semi-globally uniformly ultimately bounded and converge to a neighborhood of the origin with a prescribed performance. Finally, the computer simulation results are presented to demonstrate the effectiveness of the proposed controller. (c) 2021 European Control Association. Published by Elsevier Ltd. All rights reserved.