ABSTRACT
In this paper, a novel nonlinear optimal controller based on adaptive dynamic programming (ADP) is proposed to enhance lateral stability of articulated heavy vehicles. The proposed ADP based optimal controller uses a single neural network (NN) called critic to approximate a value function, and permits online updating of the control law with varying vehicle dynamic characteristics. The proposed controller is designed such that the actual vehicle states are forced to track the desired values via active braking considering model uncertainties. A braking torque distribution algorithm is subsequently used to generate the desired corrective yaw moment established from the ADP based controller. The effectiveness of the proposed controller is demonstrated through simulation results obtained under lane change maneuver in a co-simulation environment involving Matlab/Simulink and TruckSim. The simulation results show that the proposed controller is very effective in terms of improving lateral stability of articulate heavy vehicles in limiting driving conditions.
