High-Speed Adaptive Nonlinear Predictive Control for Autonomous Tractor Navigation

In the presented paper a Moving Horizon Estimation(MHE)/Model Predictive Control(MPC) framework is employed to allow for the autonomous navigation of a small-scale tractor being equipped with a Real-Time Kinetic Global Positioning System(RTK-GPS). In the real-time experiments the objective is to manipulate a velocity and a steering actuator such that the tractor follows a curved trajectory on a wet and bumpy grass field. The nonlinear model is adaptive in a sense that slip parameters have to be identified online for longitudinal and side slipping respectively. Feedback times within 0.6-2.8 ms have been obtained with the code generation tool of the ACADO toolkit.