An Iterative LQR Controller for Off-Road and On-Road Vehicles using a Neural Network Dynamics Model
This work addresses trajectory tracking for wheeled mobile robots in both off-road and on-road environments, representing an incremental improvement by combining existing methods like ILQR and neural network models.
The paper tackled trajectory tracking for off-road and on-road vehicles using an Iterative Linear Quadratic Regulator (ILQR) controller with a neural network dynamics model, achieving performance evaluated on human-driven reference trajectories at speeds of 3-4 m/s for an off-road robot and 7-10 m/s for an on-road vehicle.
In this work we evaluate Iterative Linear Quadratic Regulator(ILQR) for trajectory tracking of two different kinds of wheeled mobile robots namely Warthog (Fig. 1), an off-road holonomic robot with skid-steering and Polaris GEM e6 [1], a non-holonomic six seater vehicle (Fig. 2). We use multilayer neural network to learn the discrete dynamic model of these robots which is used in ILQR controller to compute the control law. We use model predictive control (MPC) to deal with model imperfections and perform extensive experiments to evaluate the performance of the controller on human driven reference trajectories with vehicle speeds of 3m/s- 4m/s for warthog and 7m/s-10m/s for the Polaris GEM