IEEE Robotics & Automation Magazine - September 2023 - 45

compared to results obtained when using constant parameters
to identify their respective strengths and weaknesses.
They have been implemented and tested in real conditions
on an off-road mobile robot with varying terrain and trajectories.
An in-depth analysis of the proposed techniques is
done, and further insights are obtained in the context of
gain tuning for steering controllers in dynamic environments.
The performance and transferability of these methods
are demonstrated as well as their robustness to changes
in terrain properties. As a result, tracking errors are reduced
while preserving the stability and explainability of the control
architecture.
INTRODUCTION
The problem of tuning controller gains is crucial in robotics as
it defines the performances and the behavior of robots. As is
well known, it relies on low-level performances as well as
interaction conditions between robots and their environments.
It is especially the case in autonomous navigation of off-road
mobile robots as achievable performances (settling time or settling
distance of the robot, i.e., the time required to reach a
desired setpoint within a set margin) depend not only on actuator
delays but also on grip conditions and velocity. In the
framework of path tracking problems, the use of constant gains
for a robot able to move at different speeds, on several types of
grounds, and with complex trajectories leads to suboptimal
results with potentially important tracking errors. This is a
drawback, as accuracy is often crucial in off-road applications,
especially in agriculture, where a few centimeters of accuracy
is targeted, and robots may move on narrow paths, bordered by
a ditch.
Consequently, the use of an online gain adaptation arises as
an interesting approach to optimize robot behavior. Some methods
for gain tuning are mainly developed in the framework of
motor control (such as in [1], utilizing neural networks, or in [2],
using a performance index). In the framework of mobile robotics,
the adaptation is mainly focused on model parameter estimation
(such as in [3]) but is rarely devoted to gain tuning. However, some
recent works [4], [5] show that online gain tuning of
a path tracking control law may improve navigation
stability. An optimal solution to gain tuning is difficult
to obtain formally. A robot's behavior indeed
depends on many factors (e.g., grip conditions,
localization uncertainty, and noises), which can
be difficult to measure or estimate and are, moreover,
variable in off-road contexts [6]. As a result,
the online variation of control parameters has to be
done carefully as it can lead to unstable behavior.
In this article, an adaptive and predictive control
strategy, developed previously in [7] with constant
parameters, is used to achieve an accurate path
tracking. Therefore, an observation strategy [8] is
available to access the cornering stiffness, together
with the residual of a Kalman filter approach for
localization [9]. This allows for the explicit access
of information related to grip conditions and confidence
in the localization process to set online the
gains of an adaptive and predictive control law for
path tracking. The first method, based on a dynamic
model of the robot [10], is suggested to define an
explicit relationship between the control parameters
and the robot's state (velocity, contact properties,
and so on). Based on the estimation of the yaw rate
settling time, this first approach shows interesting
results but does not account for unexpected or nonmodeled
deviations, especially related to localization
accuracy.
Accordingly, the second approach, based on a
neural network [11], is offered in this article and
categorized as policy iteration reinforcement
learning (RL) [12]. This allows, with the help of
a training simulator, for optimization of a function,
accounting for both deviation and potential
oscillations. This way, control law gains may be
modified online to reduce the path tracking error
SEPTEMBER 2023 IEEE ROBOTICS & AUTOMATION MAGAZINE
45
IMAGE LICENSED BY INGRAM PUBLISHING

IEEE Robotics & Automation Magazine - September 2023

Table of Contents for the Digital Edition of IEEE Robotics & Automation Magazine - September 2023

Contents
IEEE Robotics & Automation Magazine - September 2023 - Cover1
IEEE Robotics & Automation Magazine - September 2023 - Cover2
IEEE Robotics & Automation Magazine - September 2023 - 1
IEEE Robotics & Automation Magazine - September 2023 - Contents
IEEE Robotics & Automation Magazine - September 2023 - 3
IEEE Robotics & Automation Magazine - September 2023 - 4
IEEE Robotics & Automation Magazine - September 2023 - 5
IEEE Robotics & Automation Magazine - September 2023 - 6
IEEE Robotics & Automation Magazine - September 2023 - 7
IEEE Robotics & Automation Magazine - September 2023 - 8
IEEE Robotics & Automation Magazine - September 2023 - 9
IEEE Robotics & Automation Magazine - September 2023 - 10
IEEE Robotics & Automation Magazine - September 2023 - 11
IEEE Robotics & Automation Magazine - September 2023 - 12
IEEE Robotics & Automation Magazine - September 2023 - 13
IEEE Robotics & Automation Magazine - September 2023 - 14
IEEE Robotics & Automation Magazine - September 2023 - 15
IEEE Robotics & Automation Magazine - September 2023 - 16
IEEE Robotics & Automation Magazine - September 2023 - 17
IEEE Robotics & Automation Magazine - September 2023 - 18
IEEE Robotics & Automation Magazine - September 2023 - 19
IEEE Robotics & Automation Magazine - September 2023 - 20
IEEE Robotics & Automation Magazine - September 2023 - 21
IEEE Robotics & Automation Magazine - September 2023 - 22
IEEE Robotics & Automation Magazine - September 2023 - 23
IEEE Robotics & Automation Magazine - September 2023 - 24
IEEE Robotics & Automation Magazine - September 2023 - 25
IEEE Robotics & Automation Magazine - September 2023 - 26
IEEE Robotics & Automation Magazine - September 2023 - 27
IEEE Robotics & Automation Magazine - September 2023 - 28
IEEE Robotics & Automation Magazine - September 2023 - 29
IEEE Robotics & Automation Magazine - September 2023 - 30
IEEE Robotics & Automation Magazine - September 2023 - 31
IEEE Robotics & Automation Magazine - September 2023 - 32
IEEE Robotics & Automation Magazine - September 2023 - 33
IEEE Robotics & Automation Magazine - September 2023 - 34
IEEE Robotics & Automation Magazine - September 2023 - 35
IEEE Robotics & Automation Magazine - September 2023 - 36
IEEE Robotics & Automation Magazine - September 2023 - 37
IEEE Robotics & Automation Magazine - September 2023 - 38
IEEE Robotics & Automation Magazine - September 2023 - 39
IEEE Robotics & Automation Magazine - September 2023 - 40
IEEE Robotics & Automation Magazine - September 2023 - 41
IEEE Robotics & Automation Magazine - September 2023 - 42
IEEE Robotics & Automation Magazine - September 2023 - 43
IEEE Robotics & Automation Magazine - September 2023 - 44
IEEE Robotics & Automation Magazine - September 2023 - 45
IEEE Robotics & Automation Magazine - September 2023 - 46
IEEE Robotics & Automation Magazine - September 2023 - 47
IEEE Robotics & Automation Magazine - September 2023 - 48
IEEE Robotics & Automation Magazine - September 2023 - 49
IEEE Robotics & Automation Magazine - September 2023 - 50
IEEE Robotics & Automation Magazine - September 2023 - 51
IEEE Robotics & Automation Magazine - September 2023 - 52
IEEE Robotics & Automation Magazine - September 2023 - 53
IEEE Robotics & Automation Magazine - September 2023 - 54
IEEE Robotics & Automation Magazine - September 2023 - 55
IEEE Robotics & Automation Magazine - September 2023 - 56
IEEE Robotics & Automation Magazine - September 2023 - 57
IEEE Robotics & Automation Magazine - September 2023 - 58
IEEE Robotics & Automation Magazine - September 2023 - 59
IEEE Robotics & Automation Magazine - September 2023 - 60
IEEE Robotics & Automation Magazine - September 2023 - 61
IEEE Robotics & Automation Magazine - September 2023 - 62
IEEE Robotics & Automation Magazine - September 2023 - 63
IEEE Robotics & Automation Magazine - September 2023 - 64
IEEE Robotics & Automation Magazine - September 2023 - 65
IEEE Robotics & Automation Magazine - September 2023 - 66
IEEE Robotics & Automation Magazine - September 2023 - 67
IEEE Robotics & Automation Magazine - September 2023 - 68
IEEE Robotics & Automation Magazine - September 2023 - 69
IEEE Robotics & Automation Magazine - September 2023 - 70
IEEE Robotics & Automation Magazine - September 2023 - 71
IEEE Robotics & Automation Magazine - September 2023 - 72
IEEE Robotics & Automation Magazine - September 2023 - 73
IEEE Robotics & Automation Magazine - September 2023 - 74
IEEE Robotics & Automation Magazine - September 2023 - 75
IEEE Robotics & Automation Magazine - September 2023 - 76
IEEE Robotics & Automation Magazine - September 2023 - 77
IEEE Robotics & Automation Magazine - September 2023 - 78
IEEE Robotics & Automation Magazine - September 2023 - 79
IEEE Robotics & Automation Magazine - September 2023 - 80
IEEE Robotics & Automation Magazine - September 2023 - 81
IEEE Robotics & Automation Magazine - September 2023 - 82
IEEE Robotics & Automation Magazine - September 2023 - 83
IEEE Robotics & Automation Magazine - September 2023 - 84
IEEE Robotics & Automation Magazine - September 2023 - 85
IEEE Robotics & Automation Magazine - September 2023 - 86
IEEE Robotics & Automation Magazine - September 2023 - 87
IEEE Robotics & Automation Magazine - September 2023 - 88
IEEE Robotics & Automation Magazine - September 2023 - 89
IEEE Robotics & Automation Magazine - September 2023 - 90
IEEE Robotics & Automation Magazine - September 2023 - 91
IEEE Robotics & Automation Magazine - September 2023 - 92
IEEE Robotics & Automation Magazine - September 2023 - 93
IEEE Robotics & Automation Magazine - September 2023 - 94
IEEE Robotics & Automation Magazine - September 2023 - 95
IEEE Robotics & Automation Magazine - September 2023 - 96
IEEE Robotics & Automation Magazine - September 2023 - 97
IEEE Robotics & Automation Magazine - September 2023 - 98
IEEE Robotics & Automation Magazine - September 2023 - 99
IEEE Robotics & Automation Magazine - September 2023 - 100
IEEE Robotics & Automation Magazine - September 2023 - 101
IEEE Robotics & Automation Magazine - September 2023 - 102
IEEE Robotics & Automation Magazine - September 2023 - 103
IEEE Robotics & Automation Magazine - September 2023 - 104
IEEE Robotics & Automation Magazine - September 2023 - 105
IEEE Robotics & Automation Magazine - September 2023 - 106
IEEE Robotics & Automation Magazine - September 2023 - 107
IEEE Robotics & Automation Magazine - September 2023 - 108
IEEE Robotics & Automation Magazine - September 2023 - 109
IEEE Robotics & Automation Magazine - September 2023 - 110
IEEE Robotics & Automation Magazine - September 2023 - 111
IEEE Robotics & Automation Magazine - September 2023 - 112
IEEE Robotics & Automation Magazine - September 2023 - 113
IEEE Robotics & Automation Magazine - September 2023 - 114
IEEE Robotics & Automation Magazine - September 2023 - 115
IEEE Robotics & Automation Magazine - September 2023 - 116
IEEE Robotics & Automation Magazine - September 2023 - 117
IEEE Robotics & Automation Magazine - September 2023 - 118
IEEE Robotics & Automation Magazine - September 2023 - 119
IEEE Robotics & Automation Magazine - September 2023 - 120
IEEE Robotics & Automation Magazine - September 2023 - 121
IEEE Robotics & Automation Magazine - September 2023 - 122
IEEE Robotics & Automation Magazine - September 2023 - 123
IEEE Robotics & Automation Magazine - September 2023 - 124
IEEE Robotics & Automation Magazine - September 2023 - 125
IEEE Robotics & Automation Magazine - September 2023 - 126
IEEE Robotics & Automation Magazine - September 2023 - 127
IEEE Robotics & Automation Magazine - September 2023 - 128
IEEE Robotics & Automation Magazine - September 2023 - 129
IEEE Robotics & Automation Magazine - September 2023 - 130
IEEE Robotics & Automation Magazine - September 2023 - 131
IEEE Robotics & Automation Magazine - September 2023 - 132
IEEE Robotics & Automation Magazine - September 2023 - 133
IEEE Robotics & Automation Magazine - September 2023 - 134
IEEE Robotics & Automation Magazine - September 2023 - 135
IEEE Robotics & Automation Magazine - September 2023 - 136
IEEE Robotics & Automation Magazine - September 2023 - 137
IEEE Robotics & Automation Magazine - September 2023 - 138
IEEE Robotics & Automation Magazine - September 2023 - 139
IEEE Robotics & Automation Magazine - September 2023 - 140
IEEE Robotics & Automation Magazine - September 2023 - 141
IEEE Robotics & Automation Magazine - September 2023 - 142
IEEE Robotics & Automation Magazine - September 2023 - 143
IEEE Robotics & Automation Magazine - September 2023 - 144
IEEE Robotics & Automation Magazine - September 2023 - 145
IEEE Robotics & Automation Magazine - September 2023 - 146
IEEE Robotics & Automation Magazine - September 2023 - 147
IEEE Robotics & Automation Magazine - September 2023 - 148
IEEE Robotics & Automation Magazine - September 2023 - 149
IEEE Robotics & Automation Magazine - September 2023 - 150
IEEE Robotics & Automation Magazine - September 2023 - 151
IEEE Robotics & Automation Magazine - September 2023 - 152
IEEE Robotics & Automation Magazine - September 2023 - 153
IEEE Robotics & Automation Magazine - September 2023 - 154
IEEE Robotics & Automation Magazine - September 2023 - 155
IEEE Robotics & Automation Magazine - September 2023 - 156
IEEE Robotics & Automation Magazine - September 2023 - 157
IEEE Robotics & Automation Magazine - September 2023 - 158
IEEE Robotics & Automation Magazine - September 2023 - 159
IEEE Robotics & Automation Magazine - September 2023 - 160
IEEE Robotics & Automation Magazine - September 2023 - 161
IEEE Robotics & Automation Magazine - September 2023 - 162
IEEE Robotics & Automation Magazine - September 2023 - 163
IEEE Robotics & Automation Magazine - September 2023 - 164
IEEE Robotics & Automation Magazine - September 2023 - 165
IEEE Robotics & Automation Magazine - September 2023 - 166
IEEE Robotics & Automation Magazine - September 2023 - 167
IEEE Robotics & Automation Magazine - September 2023 - 168
IEEE Robotics & Automation Magazine - September 2023 - Cover3
IEEE Robotics & Automation Magazine - September 2023 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2023
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2023
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2023
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2023
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2022
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2022
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2022
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2022
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2021
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2021
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2021
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2021
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2020
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2020
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2020
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2020
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2019
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2019
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2019
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2019
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2018
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2018
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2018
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2018
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2017
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2017
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2017
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2017
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2016
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2016
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2016
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2016
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2015
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2015
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2015
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2015
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2014
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2014
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2014
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2014
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2013
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2013
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2013
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2013
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2012
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2012
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2012
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2012
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2011
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2011
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_june2011
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_march2011
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_december2010
https://www.nxtbook.com/nxtbooks/ieee/roboticsautomation_september2010
https://www.nxtbookmedia.com