Online Tuning of Control Parameters for Off-Road Mobile Robots Novel Deterministic and Neural Network-Based Approaches By Ashley Hill , Jean Laneurit, Roland Lenain , and Eric Lucet This article addresses the problem of online adaptation of control parameters, dedicated to a path tracking problem in off-road conditions. Two approaches are offered to modify the tuning gain of a previously developed adaptive and predictive control law. The first approach is a deterministic method based on dynamic equations of the system, allowing the adaptation of the settling distance with respect to robot capabilities depending on grip conditions and velocity. The second strategy uses a neural network trained with a covariance matrix adaptation evolution strategy (CMA-ES) algorithm to optimize the robot's behavior with respect to an objective (obj) function. Each approach uses as input dynamic pa - rameters, estimated from sliding angles and cornering stiffness observers. Both methods are described and Digital Object Identifier 10.1109/MRA.2022.3151067 Date of current version: 1 July 2022 44 IEEE ROBOTICS & AUTOMATION MAGAZINE SEPTEMBER 2023 1070-9932/22©2022IEEEhttps://orcid.org/0000-0002-8893-8348 https://orcid.org/0000-0003-0348-8673 https://orcid.org/0000-0002-9702-3473