Article

Research on Longitudinal Control Algorithm of Adaptive

Cruise Control System for Pure Electric Vehicles
Liang Chu, Huichao Li, Yanwu Xu, Di Zhao * and Chengwei Sun

College of Automotive Engineering, Jilin University, Changchun 130022, China

* Correspondence: dizhao@jlu.edu.cn

Abstract: The vehicle longitudinal control algorithm is the core function of the adaptive cruise control
system, whose main task is to convert vehicle acceleration and deceleration requirements into vehicle
driving and braking commands so that the vehicle can quickly and accurately track the desired
acceleration. Traditional longitudinal control algorithms rely on accurate vehicle dynamic modeling
or complex controller parameter calibrations. To overcome those difficulties, a longitudinal control
algorithm based on RBF-PID is proposed in this paper. The algorithm uses the RBFNN (radial basis
function neural network), which can simply and quickly approximate any complex nonlinear system,
to identify the Jacobian information of the vehicle and perform parameter tuning for PID control
and achieve vehicle longitudinal control with self-tuning capability. Finally, the algorithm of this
paper is verified by the joint simulation of Matlab/Simulink and Carsim. The results show that this
algorithm has a better response rate and anti-jamming capability than the traditional PID control and
can achieve accurate and rapid tracking of the desired acceleration.

Keywords: adaptive cruise control; RBFNN; vehicle longitudinal control

1. Introduction
With the rapid growth of production and ownership of automobiles, problems such
as environmental pollution, resource shortage [1], and traffic congestion that constrain
Citation: Chu, L.; Li, H.; Xu, Y.; Zhao,
economic development are becoming more and more serious [2]. A large amount of green-
D.; Sun, C. Research on Longitudinal
house gas emissions from automobiles is one of the major contributors to global climate
Control Algorithm of Adaptive
change and is considered one of the most serious challenges facing sustainable develop-
Cruise Control System for Pure
Electric Vehicles. World Electr. Veh. J.
ment [3]. Meanwhile, advanced driver assistance systems (ADAS) are treated as an effective
2023, 14, 32. https://doi.org/
way to solve the above problems ADAS can better protect us from some of the human
10.3390/wevj14020032
factors, and human error is the cause of most traffic accidents [4]. ADAS develops to under-
stand human behavior as well as to monitor health status [5] and potentially improve fuel
Academic Editor: Chunlin Chen
consumption and safety along with awareness of external driving conditions [6]. Besides,
Received: 30 November 2022 ADAS can also be applied to pure electric vehicles to optimize the driving experience [7].
Revised: 25 January 2023 Adaptive cruise control (ACC), one of the core functions of ADAS equipment, can
Accepted: 26 January 2023 monitor road conditions in real-time and control vehicle speed and acceleration on its
Published: 28 January 2023 own, which helps to save resources and ensure vehicle safety [8,9]. ACC systems are often
designed to be hierarchical, including three layers of perception, decision, and execution.
The decision algorithm uses environmental information obtained from the perception layer
and the state information of the vehicle itself to calculate the target acceleration. The vehicle
Copyright: © 2023 by the authors. longitudinal control algorithm is in the execution layer and is responsible for converting
Licensee MDPI, Basel, Switzerland. the target acceleration into demand driving and braking torque [10]. Due to the strong
This article is an open access article
coupling and nonlinear characteristics of the vehicle longitudinal dynamic systems, how to
distributed under the terms and
quickly and accurately obtain the mapping relationship is a critical and technical difficulty
conditions of the Creative Commons
that needs to be solved for the vehicle longitudinal control algorithm. Current researchers’
Attribution (CC BY) license (https://
analysis of the mapping relationship is divided into the following two main categories:
creativecommons.org/licenses/by/
model control and non-model control.
4.0/).

World Electr. Veh. J. 2023, 14, 32. https://doi.org/10.3390/wevj14020032 https://www.mdpi.com/journal/wevj

World Electr. Veh. J. 2023, 14, 32 2 of 19

In model-based control, some scholars built vehicle models to perform dynamics

control. Fritz used state-space equations to model the vehicle system and used a nonlinear
controller to control the vehicle model [11,12]. The 14 degrees of freedom (DOF) longi-
tudinal dynamics model of the Toyota Rav4EV 2012 was developed in the MapleSim by
Batra. M et al. software using the estimated parameters. The accuracy of the identified
parameters and the model was validated by comparing the model output against the
experimental data [13]. While in terms of non-model control, the main algorithms include
classical PID control, data look-up table, intelligent control, etc. Some scholars use PID
control methods. P. Shakouri et al. linearized the nonlinear dynamic models of the vehicle
at the selected operating point and used a PI controller to complete the control of the
throttle position [14]. Considering the nonlinear characteristics of the electronic throttle,
Feng Daoning et al. used various PID algorithms such as incremental, integral separation,
deadband, and feedforward compensation to improve the system response speed while
reducing the static difference. Those algorithms have been verified through experimental
bench and practical vehicle tests [15]. Some scholars use data lookup tables to follow the
desired acceleration while avoiding the recognition accuracy of vehicle dynamic parameters
affecting the control effect. Pei et al. established a three-dimensional look-up diagram of
throttle opening-vehicle speed-acceleration in the driving process and cooperating with
the control structure of feedforward plus proportional feedback to realize the control of
the acceleration process. Then they established a three-dimensional look-up diagram of
brake pressure-vehicle speed-deceleration in the braking process, cooperated with the
control structure of feedforward plus integral feedback to realize the control of the braking
process [16]. For intelligent control, Abdelkader El Kamel et al. used graded processing for
longitudinal control and fuzzy control for throttle/brake control. Acceleration error and
speed error as control inputs, while throttle opening variation and brake torque variation
as control outputs. Finally, the speed/vehicle distance following effect and the robustness
under the external environmental disturbance were verified for the control method [17].
A fuzzy longitudinal control system was proposed by Ching-Chih Tsai et al. The input
of the fuzzy longitudinal controller included the safety distance, actual vehicle distance,
and relative vehicle speed, and the output PWM signal controlled the output force of the
vacuum booster. The control algorithm has been tested in the Simulink simulation platform
at low-speed and high-speed conditions [18]. A robust control strategy based on nonlinear
model predictive control and Takagi-Sugeno (TS) fuzzy model was proposed by Khooban
et al., which was evaluated for various operating conditions of electric vehicles [19]. To per-
form adaptive speed control for highly nonlinear hybrid electric vehicles (HEVs) equipped
with the electronic throttle control system, Kumar et al. proposed fractional-order fuzzy
PD (FOFPD) controller and fractional-order fuzzy PI (FOFPI) controller as the primary and
secondary controllers of the cascade control loop, respectively [20].
It should be noted that the above control algorithms have limitations in their ap-
plication. Although the algorithm based on model control can reduce the number of
comparisons, it requires high modeling accuracy and accuracy of model parameters. In
terms of non-model control, the algorithm of classical PID control is stable, easy to adjust,
and does not depend on an accurate vehicle model. However, for nonlinear time-varying
systems, conventional PID control with three fixed parameters is difficult to meet the
requirements [21]. The look-up tables require extensive calibration experiments and long
development cycles, with bad portability. Intelligent control algorithms are complex and
have a great deal of calculation, so they are currently seldom used in practical applications.
Most of the longitudinal dynamics control methods are based on the vehicle body charac-
teristics to adjust the PID parameters or other control rules. If the external environment
(slope, wind speed, etc.) changes, it will have a great impact on the vehicle acceleration
control accuracy. At present, the longitudinal dynamics control algorithm for conventional
engine vehicles with adaptive cruise has been studied more. The longitudinal dynamics
control algorithm for pure electric vehicles is less researched. For the pure electric vehicle
adaptive cruise control system, the drive control mechanism is a motor. If considering the
World Electr. Veh. J. 2023, 14, 32 3 of 19

braking energy recovery characteristics, the pure electric vehicle braking control mech-
anism includes the motor and hydraulic braking system. Compared with conventional
vehicles, braking control is more complex [22]. Because the vehicle traction and brake
system are very complex, with strong nonlinearity and coupling, it is difficult to establish a
mathematical model to describe them accurately [23]. The current longitudinal dynamic
systems control is developing toward model-free and self-learning [24]. Neural network
(NN), as an intelligent algorithm with strong self-learning, self-adaptive and self-organizing
capabilities, is outstanding in the control of nonlinear systems [25]. The prediction model
built by RBFNN can approximate any nonlinear function with arbitrary accuracy and has
the advantages of simple structure and fast convergence [26]. It provides a new idea for
vehicle longitudinal control.
A longitudinal control algorithm applied to the ACC system for the pure electric
vehicle is proposed in this paper. The control method in this paper is a control algorithm
with adaptive capability. It optimizes the current control input based on past inputs and
the effect of the error following. The control method does not require an exact model of the
system itself and is highly adaptable to nonlinear and time-varying systems. The outputs of
the algorithm are the motor torque and total brake torque demands for driving and braking,
which are sent to the vehicle model so that the host vehicle can accurately track the desired
acceleration. If considering the braking energy recovery characteristics, the pure electric
vehicle braking control mechanism includes the motor and hydraulic braking system. The
total braking force demanded by the algorithm output can be used for regenerative braking
system design for the next step of braking force distribution, including front and rear axle
braking force distribution and hydraulic braking force, and motor regenerative braking
force distribution. It expands the application range of adaptive cruise control systems and
improves the performance index of the adaptive cruise control system. Compared with the
current work, the main contributions of this paper are as follows. The RBFNN is introduced
into the traditional PID control to realize the longitudinal control with self-adjustment
capability. The learning ability of RBFNN is applied to identify the vehicle longitudinal
dynamic systems and fine-tune the PID control parameters according to the control effect.
The control method in this paper can accurately and quickly convert the target acceleration
into the demand driving and braking torque, achieving accurate tracking of the target
acceleration with high robustness and portability. The rest of this paper is organized as
follows. Section 2 describes the vehicle platform and the control framework and explains
the longitudinal control algorithm based on RBFNN tuning PID control. Simulation results
and discussion are discussed in Section 3. Lastly, conclusions are drawn in Section 4.

2. Materials and Methods

2.1. Vehicle Platform and Control Framework
2.1.1. Vehicle Platform
As shown in Figure 1, the adaptive cruise longitudinal control algorithm proposed in
this paper is deployed on a front-wheel-drive electric vehicle. In addition to being equipped
with radars to detect the moving obstacles ahead, the vehicle’s traction system contains
a permanent magnet synchronous motor with a motor control unit (MCU), transmission,
and differential. The vehicle is also equipped with a high-voltage battery pack and battery
management system (BMS) to provide energy for the motor. The traction system model,
which accepts the desired motor torque and outputs the actual motor torque, is established
by Matlab/Simulink. The hydraulic brake system is established by Matlab/Simulink,
which contains the master cylinder, hydraulic regulation unit, disc brakes equipped on each
wheel, and brake control unit (BCU). BCU controls the solenoid valves in the hydraulic
regulation unit according to the desired pressure and outputs the hydraulic braking torque.
The vehicle dynamic model established by Carsim contains the wheel, suspension, and
spring-loaded mass models, which accept the actual motor torque and hydraulic braking
torque. At the same time, the vehicle dynamic model feeds the vehicle status back to the
ACC controller. When the ACC system works, the ACC controller continuously calculates
 brakes equipped on each wheel, and brake control unit (BCU). BCU controls the solenoid
valves in the hydraulic regulation unit according to the desired pressure and outputs the
hydraulic braking torque. The vehicle dynamic model established by Carsim contains the
World Electr. Veh. J. 2023, 14, 32 wheel, suspension, and spring-loaded mass models, which accept the actual motor torque4 of 19
and hydraulic braking torque. At the same time, the vehicle dynamic model feeds the
vehicle status back to the ACC controller. When the ACC system works, the ACC control-
ler continuously calculates the vehicle’s accelerating and braking demands based on the
the vehicle’s accelerating and braking demands based on the environmental information
environmental information from the radars. The MCU and BCU receive the correspond-
from the radars. The MCU and BCU receive the corresponding commands from the ACC
ing commands from the ACC system and control the actuators to execute. The specific
system and control the actuators to execute. The specific vehicle model development
vehicle model development process will not be discussed here.
process will not be discussed here.

Figure
Figure1.1.Structure
Structureofof
thethe
electric vehicle.
electric vehicle.

2.1.2.Control
2.1.2. ControlFramework
Framework
Thefundamental
The fundamental function
function of ofthetheACC ACC system
system is toisautomatically
to automatically regulate
regulate the hostthe host
vehicle’s speed to maintain safe vehicle spacing from the lead vehicle. As shown in Figure in
vehicle’s speed to maintain safe vehicle spacing from the lead vehicle. As shown
2,Figure 2, theframework
the control control framework
of the pureof the pure
electric vehicleelectric
ACCvehicle
system is ACC system
designed is designed
to be hierar- to
be hierarchical.
chical. In the control Inframework,
the controlthe framework,
perception the layerperception layer algorithm
algorithm analyzes the relativeanalyzes
state the
of the host
relative vehicle
state of theto host
the lead vehicle
vehicle to thebased
leadon the radar
vehicle basedsignal andradar
on the the vehicle
signal signal;
and thethe vehicle
decision algorithm
signal; the decision identifies
algorithmthe sliding
identifies acceleration
the sliding andacceleration
calculates the andtarget acceleration
calculates the target
toacceleration
determine whether the carwhether
to determine is in driving or braking
the car state according
is in driving or braking to state
the mode switch-to the
according
ing
modelogic [27]. The logic
switching above[27].
algorithms
The above are not introduced
algorithms areinnot
thisintroduced
paper. Thein inputs of the The
this paper.
pure electric
inputs of thevehicle adaptivevehicle
pure electric cruise longitudinal
adaptive cruise control algorithmcontrol
longitudinal designed in this paper
algorithm designed
in this
are the paper
target are the target aacceleration
acceleration a actual
t arg et and the target
and the actual of
acceleration acceleration
the vehicleof thea Then, aveh .
veh . vehicle

RBFNN is used to identify the vehicle system and calculate the adjustment quantity of quantity
Then, RBFNN is used to identify the vehicle system and calculate the adjustment the
of the
PID PID parameters
parameters to obtain to theobtain the PID parameters
PID parameters that are continuously
that are continuously optimized. Theoptimized.
out-
The outputs of the algorithm are the motor torque Tmotor_drive_req and total brake torque
puts of the algorithm are the motor torque Tmotor_drive_req and total brake torque Tbrake_all_req
Tbrake_all_req demands for driving and braking, which are sent to the vehicle model so that
demands
the host for driving
vehicle canand braking,track
accurately which aredesired
the sent toacceleration.
the vehicle model so that platform
The vehicle the host has
vehicle can accurately
been described track
in detail in the
Section desired
2.1.1.acceleration. The vehicle platform has been de-
scribed in detail in Section 2.1.1.
World Electr.
World Veh.Veh.
Electr. J. 2023, 14,14,
J. 2023, 32x FOR PEER REVIEW 5 of 519of 19

Figure2.2.Control
Figure Controlframework the ACC
framework of the ACCsystem
systemwith
withlongitudinal
longitudinal control
control algorithm.
algorithm.

2.2.
2.2.RBFNN-PID-Based
RBFNN-PID-Based Longitudinal ControlAlgorithm
Longitudinal Control Algorithm
Along
Alongwithwith the problemofofdifficulty
the problem difficultyinin building
building accurate
accurate mathematical
mathematical models,
models, it is it
isdifficult
difficulttotoachieve accurate control of nonlinear time-varying systems. Classical PID con-PID
achieve accurate control of nonlinear time-varying systems. Classical
control usually
trol usually fails
fails to implement
to implement the ideal
the ideal control
control effect.
effect.
InInthe
theparameter
parameter self-tuning methodofofPID,
self-tuning method PID,thetheearly
earlyrule-based
rule-based and
and model-based
model-based
PID
PIDparameter
parameter self-tuning
self-tuning has has gradually
graduallybecomebecomeunsuitable
unsuitable forfor complex
complex control
control condi-
condi-
tions.
tions. With
With thethe development
development of of intelligent
intelligentcontrol
controltechnology
technology andand advanced
advanced algorithm
algorithm
research,
research,intelligent
intelligent PIDPID controller
controller has hasattracted
attracteda alot
lotofofattention
attention [28].
[28]. Among
Among them,
them, thethe
expertadjusts
expert adjuststhethePIDPIDparameters
parametersby bystoring
storingthe
thereal-time
real-timeacquired
acquiredmeasurement
measurementdata dataand
and historical
historical experience
experience data in data
the in the database,
database, andselects
and then then selects the optimal
the optimal parameters
parameters based on
based on the heuristic reasoning mechanism [29]. The shortcomings
the heuristic reasoning mechanism [29]. The shortcomings of expert PID control are a large of expert PID control
are a large
amount amount of calculation
of calculation and theofdifficulty
and the difficulty obtaining of empirical
obtaining empirical
data. The data.
fuzzyThe
PIDfuzzy
control
PID control method also relies on the adjustment experience and
method also relies on the adjustment experience and technical knowledge of the operator technical knowledge of
the operator or expert and summarizes them into a fuzzy rule model.
or expert and summarizes them into a fuzzy rule model. Self-adjustment of PID parameters Self-adjustment of
isPID parameters
realized by usingis realized
fuzzy by using fuzzy
reasoning [30].reasoning
The use [30]. The use
of genetic of geneticcan
algorithm algorithm
optimize canthe
optimize
PID control theparameters
PID controlaccording
parameters toaccording
the output to of
thetheoutput of the controlled
controlled objectknowing
object without with-
out
all theknowing
informationall theofinformation
the controlled of the controlled
object, and theobject, andoptimal
global the global optimal
solution cansolution
be found
can be found by using the population optimization mechanism,
by using the population optimization mechanism, but there is a disadvantage of slow but there is a disad-
vantage of slow
convergence [31].convergence
In the control [31]. In the control
method based on method
neural based on neural
network tuning network
PID, thetuning
widely
PID, the widely used ones are mainly BP neural network
used ones are mainly BP neural network and RBF neural network. Both BP and RBF and RBF neural network. Bothare
BP and RBF are structurally divided into input, output, and hidden layers. The difference
structurally divided into input, output, and hidden layers. The difference is that the BP
is that the BP neural network may have multiple hidden layers, while the RBF has a single
neural network may have multiple hidden layers, while the RBF has a single hidden layer.
In the case of the same number of nodes in the hidden layer, the approximation effect of
RBF is better than that of BP, and the structure of BP neural network is more complex than
World Electr. Veh. J. 2023, 14, 32 6 of 19

that of RBF with the same number of samples and accuracy requirements. Considering the
slow convergence speed of BP neural network and the problem of local optimal solution,
the RBF neural network with higher approximation accuracy and faster convergence speed
is used to adjust the PID controller parameters online in real time [32].
Neural networks can be trained to approximate arbitrary complex nonlinear systems.
In this section, RBFNN is used to identify the Jacobian information of the controlled object,
and the gradient descent algorithm is used to calculate the adjustment quantity of the PID
parameters to obtain the continuously optimized PID parameters. The parameter-tuned
PID controller can adapt to environmental changes, making it have strong robustness and
high control accuracy for nonlinear systems. Finally, a pure electric vehicle adaptive cruise
longitudinal control algorithm is designed based on RBFNN tuning PID control.

2.2.1. Parameter Tuning of RBFNN-Based PID

PID control can realize the control of the error of the controlled system, with the
characteristics of simple algorithm structure and better robustness. The current commonly
used PID control method is digital PID control, which is divided into positional PID control
and incremental PID control, both of which use the deviation values of different sampling
points as control inputs.
The equation of the positional PID control is shown in Equation (1), which has a great
deal of calculation due to the need for the accumulation process of e(k).
( )
T k TD
TI j∑
u(k) = K p e(k) + e( j) + [e(k) − e(k − 1)] , (1)
=0
T

As shown in Equation (2), the essence of incremental PID control is not the control
quantity for the target, but the increment of the control quantity. Therefore, the incremental
PID control that facilitates quick results of requirements is less affected by system error
disturbances and has little calculation.

 ∆u(k) = K p ∆e(k) + K I e(k) + K D [∆e(k) − ∆e(k − 1)]



∆e(k) = e(k) − e(k − 1) , (2)

u(k) = u(k − 1) + ∆u(k)


Classical PID controllers are usually used to calibrate time-invariant systems, resulting
in fixed proportional-integral-differential coefficients. For nonlinear time-invariant systems,
the parameter calibration process using classical PID control methods is more complex and
requires extensive experience of the operators, whose control effect that can be achieved
is far from the ideal effect with the problem of control overshoot. The neural network
algorithm is outstanding in nonlinear system control, so it can be used to identify the
nonlinear system and continuously optimize the PID parameters. Thus, this paper proposes
PID control based on RBFNN tuning for the design of a longitudinal control algorithm.
In this paper, the PID control based on RBFNN tuning is shown in Figure 3. By
processing the input and output information of the controlled object, the PID proportional-
integral-differential coefficients are continuously optimized to make the actual output of
the controlled object as fast and smooth as possible to approach the control target output.
World Electr. Veh. J. 2023, 14, x FOR PEER REVIEW 7 of 19
World Electr. Veh. J. 2023, 14, 32 7 of 19

Figure 3. RBFNN-PID structure.

Figure 3. RBFNN-PID structure.
The incremental PID control algorithm was selected to facilitate the optimal design of
theThe
PIDincremental
coefficients by
PIDRBFNN.
control The controlwas
algorithm error can be expressed
selected to facilitateasthe
follows:
optimal design
of the PID coefficients by RBFNN. The control error can be expressed as follows:
error (k) = rin (k) − yout (k), (3)
error ( k ) = rin ( k ) − yout ( k ) , (3)
The rectification index of the neural network is selected, as shown in Equation (4).
The rectification index of the neural network is selected, as shown in Equation (4).
1 ) = 1 error
E ( k ) =E(kerror ( k ) , (k) ,
2 2
2 (4)(4)
2
The adjustment
The quantity
adjustment of the
quantity PIDPID
of the parameters are calculated
parameters usingusing
are calculated the gradient de-
the gradient
scent algorithm
descent as follows:
algorithm as follows:
∂E ∂E ∂E ∂y ∂E ∂Δu∂y ∂∆u ∂y
= −η=
Δk p ∆k
p k ∂−
= −η k = −η = η k error
k p k ∂k ∂y ∂Δku∂y∂k∂∆u
η = ( k ) errorxc
η (1)∂y, xc(1),
k ∂Δu ( k )
(5)(5)
p p ∂k p ∂∆u

∂E ∂E ∂E ∂y ∂E ∂Δu∂y ∂∆u ∂y
= −iη= = −ηi = −ηi = ηi error=( kη)i errorxc
(k)( 2 ) , xc(2),
∂y
Δki ∆k i − ηi (6)(6)
∂ki ∂k i ∂y ∂Δu∂y∂k∂∆u
i ∂k i ∂Δu ∂∆u

∂E ∂y ∂Δu ∂y (k) ∂y xc(3),

∂E ∂E ∂y ∂∆u
∂E
Δkd ∆k=−d η= − ηd= −η = − ηd
∂k ∂y ∂∆u = η∂kerror ( )
= kηd errorxc ( 3∂∆u
), (7)
(7)
d
∂kd d d ∂y ∂Δu ∂k
d
d d
∂Δ u
∂y
where ∂∂∆u y is the Jacobian information of the controlled object, η p , ηi , ηd is the learning rate
where is the Jacobian
of PID∂Δparameters, xc(1) = information
error (k ) − of the(kcontrolled
error − 1), xc(2object,
) = error η (p k, η , η(d3)is=the
), i xc learn-
error (k) −
u
2error (k − 1) + error (k − 2).
ing rate of PID parameters, xc ( 1) = error ( k ) − error ( k − 1) , xc ( 2 ) = error ( k ) ,
Based on the above work, the coefficients correction results were obtained as follows:
xc ( 3 ) = error ( k ) − 2error ( k − 1) + error
 ( k − 2) .
k p (k) = ∆k p + k p (k − 1)
Based on the above work, the coefficients k (k ) = ∆kcorrection results were obtained as follows:(8)
i + k i ( k − 1) ,
 i
 kp ( k )k= kp (dk+
k)kp=+ ∆k
d (Δ − 1k)d (k − 1)

2.2.2. Jacobian Information Recognition  ki ( k ) = Δki +Based
k i ( k − 1) , (8)
 k k = Δk + k k −on RBFNN
Based on the research content  d ( ) of the d(
d previous
1)
section, it is known that if we obtain the
real-time optimized feature parameters, then the Jacobian information of the controlled
object
2.2.2. needs Information
Jacobian to be obtained. Next, this
Recognition paper
Based will achieve the recognition of Jacobian
on RBFNN
information of the controlled object based on RBFNN.
Based on the research content of the previous section, it is known that if we obtain
The RBF network is a three-layer feedforward network, including an input layer, a
the real-time optimized feature parameters, then the Jacobian information of the con-
hidden layer, and an output layer, in which the transformation from the input layer to
trolled object needs to be obtained. Next, this paper will achieve the recognition of Jaco-
the hidden layer is nonlinear. The commonly used activation function of the hidden layer
bian information of the controlled object based on RBFNN.
is the Gaussian function, as shown in Equation (10), and the hidden layer to the output
The RBF network is a three-layer feedforward network, including an input layer, a
layer of the RBF neural network is a linear transformation, as shown in Equation (13).
hidden layer, and an output layer, in which the transformation from the input layer to the
The RBFNN structure is shown in Figure 4. RBF learning methods mainly include the
 World Electr. Veh. J. 2023, 14, x FOR PEER REVIEW 8 of 19

hidden layer is nonlinear. The commonly used activation function of the hidden layer is
the Gaussian function, as shown in Equation 10, and the hidden layer to the output layer
World Electr. Veh. J. 2023, 14, 32 8 of 19
of the RBF neural network is a linear transformation, as shown in Equation 13. The
RBFNN structure is shown in Figure 4. RBF learning methods mainly include the k-means
method, OLS (orthogonal least squares), and gradient descent method [33], etc. In the cur-
k-means
rent RBF method,
neural OLS (orthogonal
network leastthe
application, squares),
numberand gradientindescent
of neurons method
the hidden layer[33],
canetc.
be In
theselected
currentempirically.
RBF neuralIn network
addition,application, the number
there are three of neuronsthat
other parameters in the
needhidden layer can
to be learned
beinselected empirically.
the network, namely,Inthe
addition, there are
center vector of thethree other
radial parameters
basis function, that need of
the width to the
be learned
basis
in function, and the
the network, weight
namely, theofcenter
each connection
vector of the from the basis
radial hidden layer to the
function, the width
outputof layer. In
the basis
this paper,
function, and all
thethree
weightparameters are trained
of each connection fromusing
thesupervised
hidden layer learning methods,
to the output andInall
layer. this
parameters
paper, all threeundergo an error
parameters correction
are trained usinglearning process,
supervised and the
learning data taken
methods, forparameters
and all training
is also an
undergo theerror
errorcorrection
between the targetprocess,
learning value and andthe
theactual value for
data taken output by the
training system.
is also In
the error
this paper, the gradient descent method is used. Then the iterative algorithm
between the target value and the actual value output by the system. In this paper, the gradient for the out-
put weight,
descent method node center,
is used. andthe
Then node base width
iterative parameters
algorithm for theisoutput
calculated as shown
weight, in Equa-
node center, and
tions (15)–(19).
node base width parameters is calculated as shown in Equations (15)–(19).

Figure
Figure 4. 4. RBFNNstructure.
RBFNN structure.

T T
InInFigure
Figure4,4, where
where X = x[ x1 ,1x,2x,
X = 2 , ·, x· n· , xnis] the
is input vectorvector
the input of the network, in this paper
of the network, in this
paper the input
the input vector
vector is chosen
is chosen as follows: as follows:
T
X =Xdu
= ,[ydu,
k
, yyk −1, y , ] T , (9)(9)
k k −1
where du is the input value difference between the current and previous cycle of the
where du is the input value difference between the current and previous cycle of the
controlled object, y k is the output value of the current cycle, and yk −1 is the output value
controlled object, yk is the output value of the current cycle, and yk−1 is the output value of
of the previous cycle.
the previous cycle. T
=  hh1 , h, 2h, , h , , h  , where
T
The Radialbasis
basisvector
vectorof ofthe
the RBF
RBF network
network is H= hj is h

The Radial is H 1 2 , · · ·j , h j , ·m· · , hm , where j
is the Gaussian
Gaussianbasis
basisfunction.
function.
 X k−X 2
 k2
!
 C j− C j
exp− −
hhjj ==exp ( j = 1,(2,j 
= ,1,
m)2,, . . . , m), (10)
(10)
 2 2b2
 2b j j
 
 T
The center vector of the j th node of the network is Cj = c j1 , c j2 , . . . , c ji , . . . , c jn ,
where i = 1, 2, . . . , n.
Let the base width vector of the network be shown as follows:

B = [b1 , b2 , . . . , bm ] T , (11)

where b j is the base width parameter of node j.

World Electr. Veh. J. 2023, 14, 32 9 of 19

The weight vector of the network is as follows:

 T
W = w1 , w2 , . . . w j , . . . , w m , (12)

The output of the identification network is as follows:

y m ( k ) = w1 h 1 + w2 h 2 + . . . + w m h m , (13)

The performance function of the identifier is as follows:

1
J1 = (yout(k) − ym (k))2 , (14)
2
According to the gradient descent algorithm, the iterative algorithm for the output
weight, node center, and node base width parameters is calculated as follows:


w j (k ) = w j (k − 1) + η (yout(k ) − ym (k))h j + α w j (k − 1) − w j (k − 2) , (15)

k X − C j k2
∆b j = (yout(k) − ym (k))w j h j , (16)
b3j


b j (k) = b j (k − 1) + η∆b j + α b j (k − 1) − b j (k − 2) , (17)
x j − c ji
∆c ji = (yout(k) − ym (k ))w j , (18)
b2j


c ji (k ) = c ji (k − 1) + η∆c ji + α c ji (k − 1) − c ji (k − 2) , (19)
where α is the momentum factor, η is the learning rate.
The Jacobian array is obtained as follows:
m c ji − x1
∂y(k) ∂ym (k)
∂∆u(k)
≈
∂∆u(k)
= ∑ wj hj b2j
, (20)
j =1

where x1 = ∆u(k).

2.2.3. Longitudinal Control Algorithm

In the control framework, the perception layer algorithm analyzes the relative state
of the host vehicle to the lead vehicle based on the radar signal and the vehicle signal; the
decision algorithm identifies the sliding acceleration and calculates the target acceleration
to determine whether the car is in driving or braking state according to the mode switching
logic. The inputs of the pure electric vehicle adaptive cruise longitudinal control algorithm
designed in this paper are the target acceleration and the actual acceleration of the vehicle.
Then, RBFNN is used to identify the vehicle system and calculate the adjustment quantity
of the PID parameters to obtain the PID parameters that are continuously optimized. The
outputs of the algorithm are the motor torque and total brake torque demands for driving
and braking, which are sent to the vehicle model so that the host vehicle can accurately
track the desired acceleration. The pure electric vehicle in the driving process only needs
to achieve the target acceleration tracking by controlling the motor drive torque. Thus
according to the demand of the PID control algorithm based on RBFNN, as shown in
Figure 5, the difference between the selected target acceleration areq and the current actual
acceleration aveh is selected as the control algorithm input, with the motor demand drive
torque Tmotor_drive_req as the output of the driving process control algorithm.
 torque. Thus according to the demand of the PID control algorithm based on RBFNN, as
shown in Figure 5, the difference between the selected target acceleration and the
torque. Thus according to the demand of the PID control algorithm based onareq RBFNN, as
currentin
shown actual acceleration
Figure aveh is selected
5, the difference betweenasthe
theselected
control algorithm input, with
target acceleration areqtheand
motor
the
World Electr. Veh. J. 2023, 14, 32
demandactual
current torque Tmotor _adrive _ req
driveacceleration as the output
is selected as theof the driving
control process
algorithm control
input, withalgorithm.
the motor
10 of 19
veh

demand drive torque Tmotor _ drive _ req as the output of the driving process control algorithm.

Figure 5. Structure of RBFNN-PID controller for driving process.

FigureWhen
Figure 5.5. Structure
Structure RBFNN-PID
of RBFNN-PID
the braking controller for
fordriving
controllerthe
system performs drivingprocess.
braking process.
response to track the target accelera-
tion, it is necessary to first confirm the magnitude of the total demand braking torque
When the the braking systemperforms
performsthethebraking
braking responseto to track
thethe target acceler-
TbrakeWhen braking system response track target
. Thus, the difference between the target acceleration areq and the actual accelera-
accelera-
ation, it
_ all is necessary to first confirm the magnitude of the total
tion, it is necessary to first confirm the magnitude of the total demand braking torque demand braking torque
TTtion a
brake_allveh . can
Thus, be
theselected as
difference the control
between algorithm
the target input and
acceleration the
a total
and demand
the actual
. Thus, the difference between the target acceleration areq reqand the actual accelera- braking
accelera-
brake _ all
tion aveh can
torque T be selected as the control
as the control algorithm
algorithm output,input and the
as shown in total
Figuredemand brakingtotorque
6, according the
aveh brake
Ttion
brake_all as can_ allbe selected as the control algorithm input and the total demand braking
the control algorithm output, as shown in Figure 6, according to the demand of
demand of the RBFNN-tuned PID control algorithm.
torque
the RBFNN-tunedTbrake _ all as PID
the control
control algorithm
algorithm.output, as shown in Figure 6, according to the
demand of the RBFNN-tuned PID control algorithm.

Figure6.6.Structure
Figure Structureof
of RBFNN-PID
RBFNN-PID controller
controller for
for braking
brakingprocess.
process.

3.Figure
Results and Discussion
6. Structure of RBFNN-PID controller for braking process.
In the driving and braking process control, to verify the effectiveness, fast response,
and anti-jamming of the control algorithm, based on the research in Section 2, this paper
uses Matlab/Simulink and Carsim platform to build the longitudinal control model based
on RBFNN-PID, and verify the drive and brake control effect. The control method of this
paper and the traditional PID control are used to simulate the braking system and drive
system models by responding to step signals and fighting against external disturbances,
and the control effects of both are compared to prove that the control method of this paper
has better control effects.
To verify the effectiveness of the longitudinal control algorithm, several experiments
are conducted utilizing Matlab/Simulink (v.9.5, MathWorks, Natick, MA, USA) and Carsim
(v.2016, MSC, The Ann Arbor, MI, USA). The main parameters used in the simulations are
set in Table 1.
World Electr. Veh. J. 2023, 14, 32 11 of 19

Table 1. Main parameters used in the simulations.

Para. Value Units

Vehicle weight 1450 kg
Rolling resistance coefficient 0.015
Gravity acceleration 9.8 m/s2
Aerodynamic drag coefficient 0.3
Mass density of air 1.29 kg/m3
Vehicle frontal area 1.2258 m2
Vehicle transmission ratio 8.28
Transmission efficiency 0.9
Wheel radius. 0.334 m
Height of mass center 530 mm
Wheelbase 2800 mm
Tread 1500 mm
η p , ηi , η d 0.2, 0.0005, 0
n 3
m 6
η 0.25
α 0.05
k p , k i , k d in driving process 0.4, 0.7, 0
k p , k i , k d in braking process 2.2, 1.5, 0
Sampling time 0.001 s

3.1. Results and Discussion of the Driving Process

3.1.1. Step Response of the Driving Process
As shown in Figure 7, it can be seen that the initial vehicle speed is 10 km/h, and
the vehicle speed increases continuously with a certain slope to respond to the target
acceleration. The specific acceleration response effect is shown in Figure 8, and the control
effect is evaluated in terms of system response rapidity and smoothness. The settling
time, i.e., the time required to reach the allowable error range, is used to evaluate the
rapidity of the system response. The settling time of the traditional PID control algorithm
is 1.41 s, while the algorithm of this paper is 0.459 s. It can be seen that the response rate of
this paper is significantly faster than the effect of traditional PID control. The maximum
overshoot, which is the ratio of the difference between the maximum peak value and the
steady-state value to the steady-state value, is used to evaluate the smoothness of the
system response. The maximum overshoot of the conventional PID control algorithm is
39.9%, while the method in this paper is 6%. It can be seen that the response process of this
algorithm is smoother. Because the vehicle traction and brake system are very complex,
with strong nonlinearity and coupling, it is difficult to establish a mathematical model to
describe them accurately. As for acceleration fluctuations after 5 s in Figure 8, due to the
inevitable errors in the established motor and battery model system in Matlab/Simulink,
the acceleration simulation results inevitably fluctuate, and it is hard to get close to the
target value without error. The acceleration error variation is shown in Figure 8, and it
can be seen that both control methods have almost no static difference under steady-state
conditions. The control effect of the PID control based on RBFNN can meet the control
requirements and has an excellent control effect in the driving process. In a contrast, the
conventional PID controller parameters are set to similar values to the last stable value of
the RBFPID controller parameters. The change in the coefficients of the RBFPID controller
is shown in Figure 9, whose initial values are 0.2, 0, and 0. The parameter Ki was adjusted
the fastest, reaching a stable value for the first time in 0.362 s, with a final stable value of
0.7094. Additionally, the parameter Kp and parameter Kd finally stabilized at 0.4213 and
0.0024, respectively.
 has an excellent control effect in the driving process. In a contrast, the conventional PID
controller parameters are set to similar values to the last stable value of the RBFPID con-
troller parameters. The change in the coefficients of the RBFPID controller is shown in
Figure 9, whose initial values are 0.2, 0, and 0. The parameter Ki was adjusted the fastest,
reaching a stable value for the first time in 0.362 s, with a final stable value of 0.7094. Ad-
World Electr. Veh. J. 2023, 14, 32 12 of 19
ditionally, the parameter Kp and parameter Kd finally stabilized at 0.4213 and 0.0024, re-
spectively.

World Electr. Veh. J. 2023, 14, x FOR PEER REVIEW 13 of 19

Figure7.7.Target
Figure Targetacceleration
accelerationand
andvehicle
vehiclespeed.
speed.

Figure 8. Acceleration variation and acceleration error variation.

Figure 8. Acceleration variation and acceleration error variation.
World Electr. Veh. J. 2023, 14, 32 13 of 19
Figure 8. Acceleration variation and acceleration error variation.

Figure9.9.Kp,
Figure Kp,Ki,
Ki,and
andKd
Kdvariation.
variation.

3.1.2.
3.1.2.Response
Responseunder
underPerturbation
Perturbationofofthe
theDriving
DrivingProcess
Process
As
As shown in Figure 10, an external disturbanceofofamplitude
shown in Figure 10, an external disturbance amplitude0.5
0.5m/s2
m/s2isisadded
addedtotothe
the
target
target acceleration at 10 s during the response of the drive system to the stepsignal.
acceleration at 10 s during the response of the drive system to the step signal.The
The
vehicle speed rises essentially at a constant slope and is largely unaffected by disturbances.
It can be seen from Figure 11 that the conventional PID takes 1.56 s to reach the steady state
after the external disturbance, while the control method in this paper is shortened to 1.13 s,
which shows a better anti-jamming performance.

3.2. Results and Discussion of the Braking Process

3.2.1. Step Response of the Braking Process
From Figure 12, it can be seen that the initial vehicle speed is 100 km/h, and the vehicle
speed decreases continuously with a certain slope to respond to the target acceleration.
The specific deceleration response effect is shown in Figure 13, and the system shows an
overdamping state. Similarly, the settling time is used to evaluate the system response
rapidity. The simulation results show that the settling time of the traditional PID is 1.051 s
and the method of this paper is 0.521 s. Obviously, the response rate of the proposed
algorithm in this paper is faster during the braking process. By observing the variation of
acceleration error in Figure 13, it can be clearly seen that under steady-state conditions, both
control algorithms have almost no static difference. The control effect of the PID control
based on RBFNN can meet the control requirements and also has an excellent control effect
for the braking process.
 World Electr. Veh. J. 2023, 14, x FOR PEER REVIEW 14 of 19

vehicle speed rises essentially at a constant slope and is largely unaffected by disturb-
vehicle speed rises essentially at a constant slope and is largely unaffected by disturb-
ances. It can be seen from Figure 11 that the conventional PID takes 1.56 s to reach the
ances. It can be seen from Figure 11 that the conventional PID takes 1.56 s to reach the
World Electr. Veh. J. 2023, 14, 32 steady state after the external disturbance, while the control method in this paper is short-
14 of 19
steady state after the external disturbance, while the control method in this paper is short-
ened to 1.13 s, which shows a better anti-jamming performance.
ened to 1.13 s, which shows a better anti-jamming performance.

Figure 10. Target acceleration and vehicle speed.

Figure10.
Figure 10.Target
Targetacceleration
accelerationand
andvehicle
vehiclespeed.
speed.

Figure 11.Acceleration
Acceleration variationand
and acceleration error
error variation.
variation.
Figure 11. Accelerationvariation
Figure11. variation and acceleration
acceleration error variation.

3.2. Results and Discussion of the Braking Process

3.2. Results and Discussion of the Braking Process
3.2.1. Step Response of the Braking Process
3.2.1. Step Response of the Braking Process
From Figure 12, it can be seen that the initial vehicle speed is 100 km/h, and the vehi-
From Figure 12, it can be seen that the initial vehicle speed is 100 km/h, and the vehi-
cle speed decreases continuously with a certain slope to respond to the target acceleration.
cle speed decreases continuously with a certain slope to respond to the target acceleration.
The specific deceleration response effect is shown in Figure 13, and the system shows an
The specific deceleration response effect is shown in Figure 13, and the system shows an
overdamping state. Similarly, the settling time is used to evaluate the system response
overdamping state. Similarly, the settling time is used to evaluate the system response
rapidity. The simulation results show that the settling time of the traditional PID is 1.051
rapidity. The simulation results show that the settling time of the traditional PID is 1.051
 s and the method of this paper is 0.521 s. Obviously, the response rate of the proposed
algorithm in this paper is faster during the braking process. By observing the variation of
acceleration error in Figure 13, it can be clearly seen that under steady-state conditions,
both control algorithms have almost no static difference. The control effect of the PID con-
World Electr. Veh. J. 2023, 14, 32 15 of 19
trol based on RBFNN can meet the control requirements and also has an excellent control
effect for the braking process.

Figure 12. Target acceleration and vehicle speed.

Figure 12. Target acceleration and vehicle speed.

Figure13.
Figure 13.Acceleration
Accelerationvariation
variationand
and acceleration
acceleration error
error variation.
variation.

3.2.2.
3.2.2.Response
Responseunder
underPerturbation
Perturbation ofof the
the Braking
Braking Process
AsAsshown
shownininFigure
Figure14,14,an
anexternal
externaldisturbance
disturbance ofof amplitude m/s2isisadded
amplitude 0.5 m/s2 addedtotothe
the
target
targetacceleration
accelerationat at55ssduring
during the
the response
response of of the
the brake system
system toto the
the step
step signal.
signal.As
As
shown
showninin Figure
Figure14,14,
thethe
vehicle speed
vehicle decreases
speed essentially
decreases at a constant
essentially slope slope
at a constant and isand
largely
is
unaffected by disturbances.
largely unaffected It can be Itseen
by disturbances. canfrom Figure
be seen from15Figure
that the
15conventional PID takes
that the conventional
0.67
PIDs takes
to reach
0.67the
s tosteady
reach state after the
the steady external
state disturbance,
after the while the control
external disturbance, while themethod
controlin
this paper is shortened to 0.5 s, which also shows a better anti-jamming performance in the
braking process.
 World
WorldElectr.
Electr.Veh.
Veh.J.J.2023,
2023,14,
14,xxFOR
FORPEER
PEERREVIEW
REVIEW 16
16 of
of 19
19

World Electr. Veh. J. 2023, 14, 32 method 16 of 19

method in
in this
this paper
paper is
is shortened
shortened to
to 0.5
0.5 s,s, which
which also
also shows
shows aa better
better anti-jamming
anti-jamming perfor-
perfor-
mance
mance in
in the
the braking
braking process.
process.

Figure
Figure
Figure 14.
14.
14. Target
Target
Target acceleration and
accelerationand
acceleration vehicle
andvehicle speed.
vehiclespeed.
speed.

Figure
Figure 15.
15.
Figure 15. Acceleration
Acceleration variation
Accelerationvariation and
variationand acceleration
andacceleration error
accelerationerror variation.
errorvariation.
variation.

4.4.
Conclusions
4. Conclusions
Conclusions
The
The
Themain
mainperformances
main performancesin
performances inthe
in thesimulations
the simulationsare
simulations areshown
are shownin
shown in Table
in Table2.
Table 2.
2.
This paper proposes an adaptive cruise longitudinal control algorithm, specifically
including
Table
Table 2. the design
2. Main
Main of adaptive
parameters
parameters used
used in
in the
thecruise driving and braking control algorithm based on
simulations.
simulations.
RBFNN tuning PID control. Finally, a joint simulation using Matlab/Simulink and Carsim
Para.
Para. Value
Value Units
Units
platforms is conducted to verify the target acceleration tracking effect in drive and brake
Settling time of PID in driving
Settling time of PID in driving process
process 1.14
1.14 ss
control. The control algorithm of this paper and the traditional PID control were simulated
Settling
Settling time
time of
of RBF-PID
RBF-PID in
in driving
driving to compare the control effects of both, whose conclusions were drawn as follows:
separately 0.459
0.459 ss
process
process
(1) In response to the step signal in the driving case, the control method in this paper
reaches the steady state with no static difference faster than the traditional PID control
in the steady state condition, and the time required is reduced by about two-thirds.
In addition, the maximum overshoot of this control algorithm is smaller, only about
one-seventh of the traditional PID control, so the system response process is smoother.
World Electr. Veh. J. 2023, 14, 32 17 of 19

When adding disturbances, the control method used in this paper takes about three-
tenths of the time to restore the steady state than the traditional PID control, showing
a better anti-jamming ability;
(2) In response to the step signal during the braking process, the response speed of this
control algorithm is doubled compared with the traditional PID control. Similarly,
when adding disturbances, this control algorithm takes less time to restore the steady
state, which is about three-tenths less than the traditional PID control. The control
algorithm has a better anti-jamming ability.

Table 2. Main parameters used in the simulations.

Para. Value Units

Settling time of PID in driving process 1.14 s
Settling time of RBF-PID in driving process 0.459 s
Maximum overshoot of PID in driving process 39.9 %
Maximum overshoot of RBF-PID in driving process 6 %
Time to steady of PID under disturbance in driving process 1.56 s
Time to steady of RBF-PID under disturbance in driving process 1.13 s
Settling time of the PID in braking process 1.051 s
Settling time of the RBF-PID in braking process 0.521 s
Maximum overshoot of the PID in braking process 0 %
Maximum overshoot of the RBF-PID in braking process 0 %
Time to steady of PID under disturbance in braking process 0.67 s
Time to steady of RBF-PID under disturbance in braking process 0.5 s

The control method in this paper is a control algorithm with adaptive capability.
It optimizes the current control input based on past inputs and the effect of the error
following. The control method does not require an exact model of the system itself and
is highly adaptable to nonlinear and time-varying systems. The outputs of the algorithm
are the motor torque and total brake torque demands for driving and braking, which
are sent to the vehicle model so that the host vehicle can accurately track the desired
acceleration. If considering the braking energy recovery characteristics, the pure electric
vehicle braking control mechanism includes the motor and hydraulic braking system. The
total braking force demanded by the algorithm output can be used for regenerative braking
system design for the next step of braking force distribution, including front and rear axle
braking force distribution and hydraulic braking force, and motor regenerative braking
force distribution. By responding to step signals and fighting against external disturbances,
the control algorithm in this paper exhibits higher robustness, better control accuracy, and
stronger anti-jamming capability in driving and braking situations. It has proved that the
adaptive cruise longitudinal control algorithm for pure electric vehicles proposed in this
paper has a good control effect. It also expands the application range of adaptive cruise
control systems and improves the performance index of the adaptive cruise control system.

Author Contributions: Conceptualization, L.C. and D.Z.; methodology, software, validation, H.L.,
Y.X., D.Z. and C.S.; investigation, resources, writing—original draft preparation, writing—review and
editing, visualization; supervision; project administration, L.C., H.L., Y.X., D.Z. and C.S. All authors
have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Gao, J.; Chen, H.; Li, Y.; Chen, J.; Zhang, Y.; Dave, K.; Huang, Y. Fuel consumption and exhaust emissions of diesel vehicles
in worldwide harmonized light vehicles test cycles and their sensitivities to eco-driving factors. Energy Convers. Manag. 2019,
196, 605–613. [CrossRef]
2. Li, Q.; Tian, S.; Wang, W. Environmental and Social Problems and Countermeasures in Transportation System under Resource
Constraints. Complexity 2020, 2020, 6629119. [CrossRef]
World Electr. Veh. J. 2023, 14, 32 18 of 19

3. Liu, Z.; Feng, K.; Davis, S.J.; Guan, D.; Chen, B.; Hubacek, K.; Yan, J. Understanding the energy consumption and greenhouse gas
emissions and the implication for achieving climate change mitigation targets. Appl. Energy 2016, 184, 737–741. [CrossRef]
4. Ziebinski, A.; Cupek, R.; Grzechca, D.; Chruszczyk, L. Review of advanced driver assistance systems (ADAS). AIP Conf. Proc.
2017, 1906, 120002.
5. Izquierdo-Reyes, J.; Ramirez-Mendoza, R.A.; Bustamante-Bello, M.R. A study of the effects of advanced driver assistance systems
alerts on driver performance. Int. J. Interact. Des. Manuf. IJIDeM 2017, 12, 263–272. [CrossRef]
6. Marina Martinez, C.; Heucke, M.; Wang, F.-Y.; Gao, B.; Cao, D. Driving Style Recognition for Intelligent Vehicle Control and
Advanced Driver Assistance: A Survey. IEEE Trans. Intell. Transp. Syst. 2018, 19, 666–676. [CrossRef]
7. Divakarla, K.P.; Emadi, A.; Razavi, S. A Cognitive Advanced Driver Assistance Systems Architecture for Autonomous-Capable
Electrified Vehicles. IEEE Trans. Transp. Electrif. 2019, 5, 48–58. [CrossRef]
8. Arnaout, G.M.; Arnaout, J.-P. Exploring the effects of cooperative adaptive cruise control on highway traffic flow using microscopic
traffic simulation. Transp. Plan. Technol. 2014, 37, 186–199. [CrossRef]
9. Akhegaonkar, S.; Nouveliere, L.; Glaser, S.; Holzmann, F. Smart and Green ACC: Energy and Safety Optimization Strategies for
EVs. IEEE Trans. Syst. Man Cybern. Syst. 2018, 48, 142–153. [CrossRef]
10. Li, S.; Li, K.; Rajamani, R.; Wang, J. Model Predictive Multi-Objective Vehicular Adaptive Cruise Control. IEEE Trans. Control Syst.
Technol. 2011, 19, 556–566. [CrossRef]
11. Fritz, A.; Schiehlen, W. Automatic Cruise Control of a Mechatronically Steered Vehicle Convoy. Veh. Syst. Dyn. 1999, 32, 331–344.
[CrossRef]
12. Schiehlen, W.; Fritz, A. Nonlinear Cruise Control Concepts for Vehicles in Convoy. Veh. Syst. Dyn. 2019, 33, 256–269. [CrossRef]
13. Batra, M.; McPhee, J.; Azad, N.L. Parameter identification for a longitudinal dynamics model based on road tests of an
electric vehicle. In Proceedings of the ASME 2016 International Design Engineering Technical Conferences and Computers and
Information in Engineering Conference, Charlotte, NC, USA, 21–24 August 2016; p. V003T001A026.
14. Shakouri, P.; Ordys, A.; Laila, D.S.; Askari, M. Adaptive Cruise Control System: Comparing Gain-Scheduling PI and LQ
Controllers. IFAC Proc. Vol. 2011, 44, 12964–12969. [CrossRef]
15. Feng, D.N.; Liu, Z.D.; Pei, X. Precise electric throttle openness control for vehicle adaptive cruise control system. Trans. Beijing
Inst. Technol. 2011, 31, 528–532.
16. Pei, X.F.; Liu, Z.D.; Ma, G.C.; Qi, Z.Q. An adaptive cruise control system based on throttle/brakes combined control. Automot.
Eng. 2013, 35, 375–380.
17. Zhao, J.; El Kamel, A. Coordinated throttle and brake fuzzy controller design for vehicle following. In Proceedings of the 13th
International IEEE Conference on Intelligent Transportation Systems, ITSC 2010, Funchal, Portugal, 19–22 September 2010;
pp. 659–664.
18. Tsai, C.-C.; Hsieh, S.-M.; Chen, C.-T. Fuzzy Longitudinal Controller Design and Experimentation for Adaptive Cruise Control
and Stop&Go. J. Intell. Robot. Syst. 2010, 59, 167–189. [CrossRef]
19. Khooban, M.H.; Vafamand, N.; Niknam, T. T-S fuzzy model predictive speed control of electrical vehicles. ISA Trans. 2016,
64, 231–240. [CrossRef]
20. Kumar, V.; Rana, K.P.S.; Mishra, P. Robust speed control of hybrid electric vehicle using fractional order fuzzy PD and PI
controllers in cascade control loop. J. Frankl. Inst. 2016, 353, 1713–1741. [CrossRef]
21. Zhan, J.; Zhang, T.; Shi, J.; Guan, X.; Nan, Z.; Zheng, N. A Dual Closed-loop Longitudinal Speed Controller Using Smooth
Feedforward and Fuzzy Logic for Autonomous Driving Vehicles. In Proceedings of the 2021 IEEE International Intelligent
Transportation Systems Conference (ITSC), Indianapolis, IN, USA, 19–22 September 2021; pp. 545–552.
22. Sun, C.; Chu, L.; Guo, J.; Shi, D.; Li, T.; Jiang, Y. Research on adaptive cruise control strategy of pure electric vehicle with braking
energy recovery. Adv. Mech. Eng. 2017, 9, 1687814017734994. [CrossRef]
23. Chu, L.; Li, T.; Sun, C. A Research on Adaptive Cruise Longitudinal Control Scheme for Battery Electric Vehicles. Qiche
Gongcheng/Automot. Eng. 2018, 40, 277–282 and 296.
24. Gheisarnejad, M.; Mirzavand, G.; Ardeshiri, R.R.; Andresen, B.; Khooban, M.H. Adaptive Speed Control of Electric Vehicles
Based on Multi-Agent Fuzzy Q-Learning. IEEE Trans. Emerg. Top. Comput. Intell. 2022, in press. [CrossRef]
25. Li, Y.; Wu, G.; Wu, L.; Chen, S. Electric power steering nonlinear problem based on proportional–integral–derivative parameter
self-tuning of back propagation neural network. Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci. 2020, 234, 4725–4736. [CrossRef]
26. Fan, X.; Meng, F.; Fu, C.; Luo, Z.; Wu, S. Research of Brushless DC Motor Simulation System Based on RBF-PID Algo-
rithm. In Proceedings of the 2009 Second International Symposium on Knowledge Acquisition and Modeling, Wuhan, China,
30 November–1 December 2009; pp. 277–280.
27. Xu, Y.; Chu, L.; Zhao, D.; Chang, C. A Novel Adaptive Cruise Control Strategy for Electric Vehicles Based on a Hierarchical
Framework. Machines 2021, 9, 263. [CrossRef]
28. Chopra, V.; Singla, S.K.; Dewan, L. Comparative Analysis of Tuning a PID Controller using Intelligent Methods. Acta Polytech.
Hung. 2014, 11, 235–249.
29. Luo, Z.; Wei, L. Tracking of Mobile Robot Expert PID Controller Design and Simulation. In Proceedings of the International
Symposium on Computer, Consumer and Control, Taichung, Taiwan, 10–12 June 2014.
30. Liu, B.; Yao, G.; Xiao, X.; Yin, X. The Research on Self-adaptive Fuzzy PID Controller. In Proceedings of the 2013 International
Conference on Mechatronics, Robotics and Automation (ICMRA 2013), Guangzhou, China, 13–14 June 2013; pp. 1462–1465.
World Electr. Veh. J. 2023, 14, 32 19 of 19

31. Niu, X.-j. The optimization for PID controller parameters based on Genetic Algorithm. In Proceedings of the 2014 International
Conference on Advances in Materials Science and Information Technologies in Industry, Xi’an, China, 11–12 January 2014;
pp. 4102–4105.
32. Xiong, J.J.; Liu, J.Y. Neural Network PID Controller Auto-tuning Design and Application. In Proceedings of the 2013 25th Chinese
Control and Decision Conference (CCDC), Guiyang, China, 25–27 May 2013; pp. 1370–1375.
33. Chng, E.S.; Yang, H.H.; Bos, S. Orthogonal least-squares learning algorithm with local adaptation process for the radial basis
function networks. IEEE Signal Process. Lett. 1996, 3, 253–255. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.