Path tracking of highly dynamic autonomous vehicle trajectories via iterative learning control

Abstract

Iterative learning control has been successfully used for several decades to improve the performance of control systems that perform a single repeated task. Using information from prior control executions, learning controllers gradually determine open-loop control inputs whose reference tracking performance can exceed that of traditional feedbackfeedforward control algorithms. This paper considers iterative learning control for a previously unexplored field: autonomous racing. Racecars are driven multiple laps around the same sequence of turns while operating near the physical limits of tire-road friction, where steering dynamics become highly nonlinear and transient, making accurate path tracking difficult. However, because the vehicle trajectory is identical for each lap in the case of single-car racing, the nonlinear vehicle dynamics and unmodelled road conditions are repeatable and can be accounted for using iterative learning control, provided the tire force limits have not been exceeded. This paper describes the design and application of proportional-derivative (PD) and quadratically optimal (Q-ILC) learning algorithms for multiplelap path tracking of an autonomous race vehicle. Simulation results are used to tune controller gains and test convergence, and experimental results are presented on an Audi TTS race vehicle driving several laps around Thunderhill Raceway in Willows, CA at lateral accelerations of up to 8 m/s 2 . Both control algorithms are able to correct transient path tracking errors and improve the performance provided by a reference feedforward controller.

A survey of deep learning techniques for autonomous driving

“…Learning techniques are commonly used to learn a dynamics model which in turn improves an a priori system model in iterative learning control (ILC; Kapania & Gerdes, ; Ostafew, Schoellig, & Barfoot, ; Panomruttanarug, ; Z. Yang, Zhou, Li, & Wang, ) and model predictive control (MPC; Drews, Williams, Goldfain, Theodorou, & Rehg, 2017; Lefevre, Carvalho, & Borrelli, ; Lefèvre, Carvalho, & Borrelli, ; Ostafew et al, , ; Pan et al, , ; Rosolia, Carvalho, & Borrelli, ).…”

Learning How to Autonomously Race a Car: A Predictive Control Approach

“…This strategy is extended in [17] to design a racing controller which guarantees recursive constraint satisfaction. Also in [18] the control problem is divided in two steps. First, a reference trajectory is computed using the method proposed in [19].…”

Cautious NMPC with Gaussian Process Dynamics for Autonomous Miniature Race Cars

“…In addition, iteratively learning the racing task on a lap-by-lap basis, as considered e.g. in [6], suffers from poor generalization and does typically not allow for maintaining high performance for dynamic racing tasks, such as obstacle avoidance or overtaking. This paper addresses these challenges by learning the dynamics model from data and considering model uncertainty to ensure constraint satisfaction in a nonlinear model predictive control (NMPC) approach, offering a flexible framework for racing control.…”