Online Gain Tuning Using Neural Networks: A Comparative Study

• Published in: AgriEngineering Vol. 4; no. 4; pp. 1200 - 1211
• Main Authors: Hill, Ashley, Laneurit, Jean, Lenain, Roland, Lucet, Eric
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2022; MDPI
• Subjects: Agricultural sciences; Algorithms; Comparative studies; Control systems; Control theory; Deep learning; Experiments; Kinematics; Life Sciences; Machine learning; Methods; mobile robotic control; Neural networks; Objective function; optimal control; Parameter identification; path following; Predictive control; Reinforcement; reinforcement learning; Robotics; Robots; Sciences and technics of agriculture; Sensors; Steering; Terrain; Tracking errors; Tuning; Velocity; optimal control; mobile robotic control; path following; mobile robotic control path following reinforcement learning optimal control; reinforcement learning

This paper addresses the problem of adapting a control system to unseen conditions, specifically to the problem of trajectory tracking in off-road conditions. Three different approaches are considered and compared for this comparative study: The first approach is a classical reinforcement learning m...