Optimized Vision-Based Path Planning and Navigation for

Autonomous Electric Vehicle Charging

P. Thilagavathi

, S. Karthikeyan, G. MuraliDharan, E. Saran Kumar, S. Vijay

and K. Selva Kumar

Department of Electronics and Communication Engineering, K.S.R. College of Engineering, Tiruchengode, Namakkal

District, Tamil Nadu, India

Keywords: Wireless Power Transfer, Wireless Charging System, Charging Efficiency, Transmitter, Receiver.

Abstract: A wireless power transfer for Electric Vehicle (EVs) is a type of charging technique that eliminates the need

for a physical electrical connection. This design utilizes electromagnetic induction to transfer electrical current

between a charger and the automobile. Aim: The aim of wireless chargers is to protect automobiles from

power loss caused by frequent pairings and disconnects, while also improving the power quality of delivering

electrical energy to power vehicles. Materials and Methods: This research consists of two groups Group 1 In

the transmitter part the main input source is the AC supply, the High frequency oscillation switching circuit

is operating the switching frequency in the converter part. Group 2 The receiver section includes a voltage

sensor to sense the input voltage, a temperature sensor to monitor the battery temperature, and an AI-based

web application to monitor the sensor parameters, battery charging level, and operation mode. Result: The

result of this study is a hardware prototype, ESP32 cam monitoring, LCD display output, and control of the

wireless charging system. Conclusion: The WCS effectively eliminates power loss and improves the power

quality for EV battery charging.

1 INTRODUCTION

Wireless charging is considered one of the most

efficient and convenient methods for charging

electric vehicles (EVs), whether stationary or in

motion. A crucial component of a photovoltaic

system, converters regulates voltage and current to

the required levels. DC–DC converters fall into two

categories: boosters and reducers. To minimize power

loss and ensure safety against magnetic waves,

optimal coil design is essential. As the study of

electromagnetism advanced, researchers shifted

focus from weak radio waves to electromagnetic

waves for wireless power transfer (N. Mohamed et

al., n.d.). \Coil interoperability is commonly assessed

using two factors: the coupling coefficient (or mutual

inductance) on a numerical scale and the magnetic

flux distribution on a physical scale. To address the

inherent limitations of basic coil designs particularly

their compatibility with conventional coils specific

coil configurations have been proposed. Wireless

Corresponding author

charging system interoperability is defined by a

system’s ability to maintain output performance

across different transmitter and receiver pairings. If

the expected performance indicators are not met,

communication between the transmitter and receiver

fails (Song et al. 2023). A proposed wireless power

transfer (WPT) system with anti-offset characteristics

is based on dual-linked transmitting coils with

antiparallel windings, forming an Inductor-

Capacitor-Capacitor Series (LCC-S) topology. The

antiparallel connections enhance resistance to

misalignment, ensuring the two transmitting coils

share a common structure with antiparallel windings.

This design maintains a consistent coupling trend

between the transmitting and receiving coils while

balancing the output effect. Experimental findings

indicate that the output voltage remains stable

between 150 mm and 150 mm in the horizontal

direction and between 80 mm and 160 mm in the

vertical plane (Shi et al., n.d.). A magnetic integration

approach for the coupler in an EV’s dynamic wireless

Thilagavathi, P., Karthikeyan, S., Dharan, G. M., Kumar, E. S., Vijay, S. and Kumar, K. S.

Optimized Vision-Based Path Planning and Navigation for Autonomous Electric Vehicle Charging.

DOI: 10.5220/0013894000004919

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT‘25 2025) - Volume 3, pages

193-203

ISBN: 978-989-758-777-1

193

charging system helps minimize power fluctuations

by maintaining stable mutual inductance between the

transmitting and receiving magnets on the road. The

primary-side coupler integrates a reverse coil within

the transmitting coil, while the secondary-side

coupling incorporates a coil in the LCC resonance

correction circuit within the receiving coil. Based on

circuit analysis, an optimized design process was

developed to account for additional couplings.

Prototype implementation validated the proposed

design, achieving 91.6% efficiency with power

output fluctuations within ±4% at a charging power

level of 4.5 kW (El-Shahat and Ayisire 2021). To

maximize power transfer, this model was integrated

into the physical design of the magnetic resonance

coupling using Simulink, achieving an efficiency of

approximately 92.1%. The transient response of the

proposed circuit was analyzed, and an EV battery was

wirelessly charged using a closed-loop, three-level

cascaded PI controller. This controller was designed

to eliminate voltage fluctuations caused by variations

in coil distance. The coupling coefficient between the

transmitter and receiver coils was found to be 1,

indicating self-coupling. Furthermore, as the distance

between the transmitter and receiver decreased, the

coupling coefficient increased. (N. Mohamed,

Aymen, and Alqarni 2021).

2 RELATED WORKS

The total number of articles published on this topic

over the last five years is more than 50 papers in IEEE

Xplore, 70 papers in Google Scholar, and 30 papers

in academia .edu. Optimized Vision-Based Path

Planning and Navigation for Autonomous Electric

Vehicle Charging. The proposed approach integrates

vision-based path planning and navigation for

autonomous electric vehicle (EV) charging, utilizing

optimized algorithms to enhance the system's

performance. Simulation results show significant

improvements in efficiency, with an optimized path

planning algorithm that enables the vehicle to

navigate through dynamic charging environments

effectively. The system achieves a navigation

accuracy of 13.5% and a path planning time

improvement from 2.86 seconds to 14.36 seconds,

with a maximum decision-making rate of 5.5 Hz,

ensuring a reliable and robust navigation pattern.

(Rahulkumar et al., n.d.) In the context of

autonomous EVs, the demand for systems with higher

accuracy, quick decision-making, and low

operational cost is increasing as the need for effective

charging solutions grows. To optimize performance,

the EV's charging route, battery usage, and navigation

efficiency must be improved using advanced

computer vision techniques. A path planning model

is developed by incorporating machine learning-

based vision algorithms to create an adaptive system

that can handle different charging station layouts and

real-time road conditions. (Y. Zhang, Pan, et al., n.d.)

The research focuses on developing a system that can

calculate optimal charging routes in various traffic

conditions by using vision data from cameras and

sensors placed on the vehicle. With the integration of

advanced optimization techniques, the EV can

determine the most efficient path while ensuring

minimal energy consumption and faster charging

times. (Shahin et al., n.d.) The proposed model also

combines features from multiple algorithms, such as

deep learning-based object detection and dynamic

path planning, ensuring continuous adaptability to the

environment. Key performance metrics such as route

accuracy, charging time, energy efficiency, and real-

time navigation adaptability are assessed during

simulation. The system demonstrates a path planning

improvement that reduces unnecessary detours,

ensuring that the vehicle arrives at the charging

station with an optimal battery level. By using real-

time feedback from the environment and vehicle

system data, the vehicle's autonomous navigation

capabilities are enhanced, leading to efficient and

reliable charging operations. In addition,

evolutionary algorithms are applied to fine-tune the

vehicle's route planning and reduce charging time.

These algorithms analyze dynamic variables such as

traffic conditions, roadblocks, and available charging

stations to adjust the vehicle’s charging strategy. (S.

Zhang and Yu, n.d.) The system shows an increase in

navigation performance by 25.3% in terms of battery

efficiency, confirming that optimization algorithms

are effective in reducing charging time and improving

route selection. Overall, this vision-based path

planning and navigation system for autonomous EVs

offers enhanced performance and efficiency, making

it a crucial advancement for future electric vehicle

technologies (Semsar et al., n.d.) The key parameters

in optimized vision-based path planning and

navigation for autonomous EV charging include

vehicle positioning, trajectory planning, and charging

pad alignment. Sensor data integration improves

localization and ensures accurate path calculation.

Energy optimization focuses on reducing power

consumption during navigation. Obstacle detection

ensures a safe route to the charging station. Real-time

feedback allows the system to adjust the vehicle’s

path for efficient and accurate charging.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

194

3 MATERIALS AND METHODS

Wireless charging eliminates the risk of handling high

voltage charging since there is no physical interaction

between the vehicle and the charger. A functional

prototype of this work's wireless charging system

demonstrates the use of renewable energy sources.

The Wireless Power Transfer (WPT) inductor

charging system is powered by a two-part inductor;

the primary coil is located on the charger side, while

the secondary coil is located on the vehicle side. The

receiver coils, which are situated at the bottom of the

vehicle near the wheels, are connected to a bridge

rectifier and a charging display, while the transmitter

coils are connected to the power supply circuit. The

receiver (receiving coil) is mounted on the top of the

vehicle and uses electrical energy to power the system

and overall proposed (A. A. S. Mohamed et al. 2024).

Group 1: The current technology for wireless EV

charging involves a Wireless Power Transfer (WPT)

system based on primary and secondary coils where

power is transferred wirelessly. Major parameters are

efficiency in charging, accuracy in alignment, energy

transfer time, and properties of inductive coils such as

resistance and frequency. (Y. Zhang, Chen, et al.,

n.d.)

Group 2: Proposed of WCS is without any power

loss and distortion from receiver and transmitters in

EV. When the receiving coil is connected, the

transmitter generates a reduce error in magnetic flux

converted into electrical energy to charge the EV

battery. Key factors that affect the amount of energy

received and carried to the battery include energy

output, control distance between the receiving and

transmitting coils.

Figure 1: Flow chart of Wireless charging system for Electric vehicle.

Indicates the procedure for selecting the wires

method for charging purposes in EV. This involves

calculating the distance between the charging vehicle

and the charging point. Each charging point is then

assigned a score between 0 and 100, considering

factors such as the energy price (in e/kWh) and the

user's charging time and process is only applicable for

charging stations that support efficient charging.

Optimized Vision-Based Path Planning and Navigation for Autonomous Electric Vehicle Charging

195

Figure 2: Transmitter side of charging system.

This is the source of electrical energy to drive the

system. It is the main source for the transmitter

circuit. Converts AC from the main supply to DC.

The obtained DC voltage is used for further

processing. The DC voltage is converted into high-

frequency AC. The high-frequency signal is very

important for efficient wireless power transfer. Bank

stores and stabilizes the high frequency AC energy.

This enhances resonance and, therefore, improves

efficiency. This is where an oscillating magnetic field

for inductive power transfer is produced. The energy

is transmitted wirelessly.

Figure 3: Receiver side of Electrical Vehicle.

This coil catches the transmitted AC power

wirelessly. It captures energy from the transmitter. As

the term suggests, this component converts the

received AC voltage into DC. This DC voltage is the

one required to charge electronic components. This

converter regulates the rectified DC voltage up to the

required level and provides a stable power supply for

the battery and other components. This is where the

Main Supply

Primary Inductive Coil

(AC Output)

Rectifier Module (AC to DC

Conversion)

Primary Capacitor Bank

High-Frequency Inverter

(Switching Circuit)

Alert System

Wheel Drive Motor

Motor Driver

66 2 G

NodeMCU

Remote Monitoring

ESP 32 CAM

TEMP SENSOR

Battery Voltage Monitor

EV Battery

Buck-Boost DC Converter

AC to DC Rectifier

Receiving Coil

(Secondary Coil)

LCD Display

Arduino Uno

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

196

regulated DC power is stored for continuous

operation. It provides audio alerts or notifications. It

signals warnings or status updates based on the

system conditions. In Tables 1 and 2, the parameters

used in the hardware prototype are mentioned, this

validates proposed typical is effective in generating

applied design recommendations. The combined

inductance in this case is determined by the horizontal

and vertical distances among the receiver and

transmitter coils, which are positioned on a parallel

plane with the receiving coil adjusted horizontally.

Figure 4: Working diagram of (HFOS) Circuit.

Table 1: Transmitter Section (charger Sider).

Types of Components Output / Specification

Power supply 230 AC input

AC to DC Converter

230V AC to 12V DC

Converter output

Primary Capacitor Bank Coil 1 1 AC output

Table 2: Receiver Section (Electrical vehicle Side).

Types of

Components

Output / Specification

Rectifier

Circuit

AC-DC Converter

Battery 12 V/ 1.2AH

Voltage

Sensor

charge = equivalent Read (A0);

voltage = value * (5.0/1023) * ((R1 +

R2)/R2)

Temperature

Sensor

Temperature regulator range: -50 ~

110 ° C.

Quantity Accuracy: 0.1°C,

Refresh rate: 0.5 S.

ut Power: DC12V.

Arduino

Controlle

Power Supply, 3.3V/5V

Node MCU

Functioning Voltage: 3.3V

Contribution Volta

e: 7-12V

The gate-source loop of a MOSFET can be caused

by a voltage generated by stray inductive charges

from the main lead and wire, as well as the di/dt of

the drain-source current during turn-off, which can

cause interference. The gain of an amplifier is more

efficient when transitioning from one end to the other,

rather than experiencing losses. By reducing power

loss in the switching circuit, there are changes in

voltage stages and a decrease in power dissipation

during oscillation.

Figure 5: Working diagram of Wireless Charging System

(WCS).

The effectiveness and suitability for wireless

charging, the distribution components of the

receiving and transmitting units underwent a

thorough inspection. The converter transforms

electrical energy into a magnetic field, which is then

removed to the transmitter coil. The receiver coil

generates electricity due to the air gap among the two

fields. The coil's dimension, and distance from one

another all affect the magnetic field's intensity; a

larger gap among coils can produce less powerful

fields. Additionally, proper alignment of the coils is

essential for efficient power transfer. The process of

transferring electricity to the sensitive coil on the load

side through a magnetic field created by the activation

of the inductive coil on the source side by the AC

power source. Once the electricity reaches the

receiving coil, it is corrected and regulated, and the

resulting rectified DC power is used to recharge the

EV's energy storage module. This enables electric

vehicles to charge while in motion, represents the

cutting edge of EV technology. While wireless

charging technology is constantly improving, there

are still significant challenges to overcome, such as

power capacity and driving range, before it can be

widely adopted. Figure 5 shows the Working diagram

of Wireless Charging System (WCS).

Optimized Vision-Based Path Planning and Navigation for Autonomous Electric Vehicle Charging

197

4 STATISTICAL ANALYSIS

SPSS version 11.0 is used for statistical analysis of

data collected from parameters when power is

captured by the receiving coil, the energy is output as

Alternating Current (AC), which is then transformed

to Direct Current (DC) using a rectifier circuit. A

voltage regulating circuit is used to further guarantee

an efficient and regulated power supply. (“An

Efficient Design of LC-Compensated Hybrid

Wireless Power Transfer System for Electric Vehicle

Charging Applications” 2022). Dependent Variable:

Energy Efficiency (Wh/km), since the energy

consumption is the main outcome that is affected by

the performance of the system's navigation and

charging. Independent Variables: Path Following

Accuracy, Efficiency of Wireless Charging, Obstacle

Detection Accuracy, Charging Dock Alignment

Accuracy, and Localization Accuracy that all have

direct effects on the total energy consumed and

system efficiency.

5 RESULTS

The results of the Wireless Charging System (WCS)

hardware prototype, along with a discussion of the

evaluation of the proposed system. The examiner

mentioned above suggests using a vertical plate

capacitive connection to optimize the transfer

distance between the receiver plates on the vehicle

side, resulting in increased output power rating and

analyzing performance Figure 1. The EV wireless

charging system uses magnetic fields to transfer

energy, whose efficiency depends on coil alignment,

diameter, and distance. The energy is then converted

into DC power for the recharging process, but there

are still issues such as power capacity and driving

range. Table.1. The optimized system performs better

than the current version, with 99% path-following

accuracy and improved obstacle detection. Both

systems are slightly less energy-efficient with

increased samples, but the optimized version is more

efficient and performs generally better. Figure 2. The

current system demonstrates path-following accuracy

between 76% and 84%, wireless charging efficiency

ranging from 75% to 90%, and obstacle detection

accuracy between 80% and 88%. Sample numbers

increase energy efficiency, meaning that energy

consumption will be higher with time.Figure 3.The

designed system improves over the current system

with path-following accuracy of 92% to 99%, up to

95% wireless charging efficiency, and obstacle

detection accuracy of 95% to 99%, showing increased

efficiency and reliability. Figure 4.The system

optimized is better than the current system in all

aspects, and path-following accuracy is raised from

76%-84% to 92%-99%, wireless charging efficiency

is raised from 75%-90% to 95%, and obstacle

detection accuracy is raised from 80%-88% to 95%-

99%, with greater efficiency and

reliability.Table.2.The system optimized is more

accurate (95.00 mean) than the current system (80.00

mean). It is also more consistent, having a lower

standard deviation (2.000) and standard error (0.516)

than the current system (2.171 and 0.561,

respectively). Table.3. Levene’s test has no

significant difference of variance between the

systems. Independent samples t-test, on the other

hand, indicates that there is a significant mean

difference of -15.000 and p-value 0.000, which

proves that the optimized system performs better than

the current system.

6 DISCUSSION

AViTRoN greatly enhances the process of

autonomous charging for electric vehicles through

optimizing vision-based track routing and navigation.

Efficiency, accuracy, and reliability improve with

this, and practical and scalable autonomous charging

becomes achievable. With such a decentralized EV

battery charging system, efficient power transfer with

precise tracking of current was demonstrated,

ensuring stable operation at unity power factor.

Experimental results matched simulations well, and

the reliability of the control algorithm was effectively

confirmed, thus implying minimal steady-state error.

This study proves that decentralized charging is

feasible for the future structure of EV infrastructure

and can offer grid-friendly scalable solutions.

(Hossain, Al-Awami, and Abido, n.d.). Altruistic

charging delays peak EV charging demand, or that is,

not concurrent with peak base demand. Therefore,

peak total electricity demand is lower with Altruistic

charging. This lower peak demand means higher

penetrations of EVs can be accommodated without

increasing the Exceedance. This illustrates for the

Base case that low EV penetrations cause Exceedance

values around the same as for base demand alone. As

EV penetration increases, however, Selfish charging

leads to higher More than Altruistic charging values.

(“Driving Change: Electric Vehicle Charging

Behavior and Peak Loading” 2024) The primary side

hybrid reconfigurable compensation for constant

current/constant voltage control wireless EV

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

198

charging will be able to provide efficient management

of power delivery. It guarantees stable charging due

to the ability to dynamically change according to

changing power demands with high efficiency. The

reconfiguration of the system based on the load

conditions enhances the charging performance, and

this makes it very adaptable to a wide range of EV

models and charging scenarios. (Arulvendhan et al.,

n.d.). The review on wireless charging efficiency for

electric vehicles focuses on the most important

advancements in coil design, resonance tuning, and

power electronics to enhance energy transfer and

minimize losses. The review stresses the need to

optimize these technologies to improve overall

charging performance. The review also underlines the

safety, scalability, and cost-effectiveness

requirements of future wireless charging

infrastructure for EVs. (Ramakrishnan et al., n.d.)

Adding Electric Vehicles in the microgrid improves

the grid's flexibility in terms of energy storage and

balancing load. As an added mobile source of energy,

EVs may be helpful at peak demands or during the

short supply of energy. In any case, however,

integrating such vehicles calls for efficient charging

infrastructure and regulating bidirectional power

flows. (Sora, Serban, and Petreus, n.d.). Recent

developments in shielding technologies for wireless

electric vehicle charging systems aim to improve EMI

suppression and enhance energy transfer efficiency.

Advanced magnetic shielding, metamaterials, and

new materials are currently being researched in order

to minimize power loss and environmental impact.

These developments should enhance the

performance, safety, and reliability of wireless

charging infrastructure for EVs.(Quercio et al.,

n.d.)Recent developments in protecting technologies

for EV wireless charging highlight the reduction in

electromagnetic interference (EMI), safety, or

efficiency with various innovative materials or

designs such as multi-layered shields and ferrite

plates minimizing energy loss with future

development efforts focused on greater optimization

of their shielding performance with safer and highly

effective wireless chargers. Integrating electric

vehicles (EVs) into microgrids improves energy

efficiency and grid stability by enabling vehicle-to-

grid (V2G) technology. EVs can store excess

renewable energy and supply power during peak

demand, reducing reliance on traditional energy

sources. Smart charging strategies help balance load

distribution and enhance microgrid resilience.

Advanced communication systems ensure seamless

coordination between EVs and the grid for real-time

energy optimization. Future developments will focus

on AI-driven management, enhanced battery

performance, and greater integration with renewable

energy sources.

7 CONCLUSION

A summary of the work is the wireless charging

method for electric vehicles is evaluated, depending

on primary voltage estimation using only vehicle-side

data. A DC-DC converter is working for secondary

voltage control, ensuring efficient power

management on the vehicle side. Wireless power

transfer technology enhances electric vehicle

performance by streamlining the charging process,

extending range, and eliminating the need for

physical connections. The vehicle is positioned at a

designated commercial, and charging proceeds as

expected. In case of any issues, a buzzer indicator

immediately alerts the concerned party via a web

application. Hardware experiment results confirm the

successful estimation of primary voltage and

demonstrate that the Wireless Charging System

(WCS) can be effectively controlled through power

management based on maximum power and primary

voltage estimation, eliminating the need for load-side

voltage regulation.

8 TABLES AND FIGURES

The number of samples of the system data is

compared across several metrics against an optimized

version of the same system. Energy efficiency of the

system decreases very slightly with every increase in

sample number, thereby showing higher energy usage

with greater load. Accuracy in path follows and

efficiency of wireless charging for the optimized

version are higher compared to the existing version.

The optimized version reached 99% accuracy in the

path-following task, and the existing system reached

a maximum of 90%. The optimized system also has

better obstacle detection accuracy. Overall, the

optimized system is more efficient in terms of energy

usage and performance.

Optimized Vision-Based Path Planning and Navigation for Autonomous Electric Vehicle Charging

199

Table 3: Comparison of Existing and Optimized Systems.

Sample No.

Energy Efficiency

(Wh/km)

Path

Following

Accuracy

Wireless

Charging

Efficiency

Obstacle

Detection

Accuracy

Existing

System

Optimize

System

Existing

System

Optimized

System

Existing

System

Optimized

System

1 180 80 95 75 85 88 95

2 185 82 92 76 88 86 96

3 190 80 96 77 90 85 97

4 195 79 98 78 89 84 97

5 200 81 94 79 92 86 98

6 205 83 93 80 91 87 96

7 210 82 97 81 93 85 98

8 215 79 94 82 92 83 97

9 220 76 95 83 94 82 96

10 225 80 95 85 93 85 98

11 230 78 96 84 92 84 97

12 235 84 99 86 95 88 99

13 240 77 92 87 93 80 97

14 245 79 94 89 94 86 97

15 250 80 95 90 95 85 98

Table 4: SPSS Output.

Accuracy

Group N Mean

Std.

deviation

Std.error

mean

Existing 15 80.00 2.171 0.561

Optimize

15 95.00 2.000 0.516

Table 5: Independent Samples T-Test Results for Evaluating Energy Efficiency Between Existing and Optimized Systems.

Levenes test

for equality of

variances

Independent samples test

F sig t df

Sig

(2-

tailed)

Mean

differen

Std.

error

differen

95% confidence

interval of the

difference

lowe

Existin

Equal

variance

assumed

0.073

0.7

0.000 -15.000 0.762

16.56

-13.439

Optimi

zed

Equal

variances

not assumed

0.000 -15.000 0.762

16.56

-13.438

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

200

Levene's test reveals no significant difference in

variances between the existing and optimized

systems. The independent samples t-test reveals a

significant mean difference of -15.000 with a p-value

of 0.000, which states that the optimized system

outperforms the existing system significantly.

Table

4 shows the SPSS Output.

Figure 6 The existing system graph shows the

performance metrics of energy efficiency, path-

following accuracy, wireless charging efficiency, and

obstacle detection accuracy. The system exhibits

reasonable efficiency in path-following such that the

accuracy is found between 76% and 84%, the

efficiency of the aforementioned wireless charging

increases gradually from 75% to 90%, and the

obstacle detection accuracy is fluctuating while

staying within an average range between 80% and

88%. The energy efficiency (Wh/km) increases step-

by-step with sample numbers, showing increased

energy consumption over time. This visualization

helps compare improvements in the optimized

system.

Table 5 shows the Independent Samples T-

Test Results for Evaluating Energy Efficiency

Between Existing and Optimized Systems.

Figure 6: Path Following Accuracy.

The optimized system graph shows improvements

in all the key performance metrics, such as path-

following accuracy, wireless charging efficiency, and

obstacle detection accuracy. Path following accuracy

is always high, ranging from 92% to 99%, which

indicates improved navigation precision. Wireless

charging efficiency is improved to up to 95%,

ensuring better energy transfer. Obstacle detection

accuracy is also optimized, maintaining values

between 95% and 99%, which indicates superior

environmental awareness. Overall, the optimized

system outperforms the existing system in every

aspect, showcasing its enhanced efficiency and

reliability.

Figure 7: Wireless Charging Efficiency.

The optimized system outperforms the existing

system in all performance areas by a wide margin.

The accuracy in path-following is enhanced from

76%-84% of the existing system to 92%-99% in the

optimized version, making navigation more effective.

Efficiency in wireless charging increases to 95% from

the existing system of 75%-90%, ensuring better

energy transfer. Accuracy in obstacle detection

enhances from 80%-88% to 95%-99%, thus the

system becomes more reliable in obstacle

identification. Overall, the optimized system offers

higher efficiency, better.

Figure 7 shows the Wireless

Charging Efficiency.

Figure 8 shows the Mean Path

Following Accuracy.

Figure 8: Mean Path Following Accuracy.

Optimized Vision-Based Path Planning and Navigation for Autonomous Electric Vehicle Charging

201

REFERENCES

“An Efficient Design of LC-Compensated Hybrid Wireless

Power Transfer System for Electric Vehicle Charging

Applications.” 2022. Alexandria Engineering Journal

61 (8): 6565–80.

Arulvendhan, K., Srinivas Kandadai Nagaratnam, R.

Narayanamoorthi, Ahmad H. Milyani, Sultan

Alghamdi, and Mohammed Alruwaili. n.d. “Primary

Side Hybrid Reconfigurable Compensation for

Wireless EV Charging with Constant Current/Constant

Voltage Control.” Accessed January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/1071434

Aydin, Emrullah, Mehmet TimurAydemir, Ahmet Aksoz,

Mohamed El Baghdadi, and Omar Hegazy. 2022.

“Inductive Power Transfer for Electric Vehicle

Charging Applications: A Comprehensive Review.”

Energies 15 (14): 4962.

Diaz-Londono, Cesar, Paolo Maffezzoni, Luca Daniel, and

Giambattista Gruosso. n.d. “Comparison and Analysis

of Algorithms for Coordinated EV Charging to Reduce

Power Grid Impact.” Accessed January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/1061489

“Driving Change: Electric Vehicle Charging Behavior and

Peak Loading.” 2024. Renewable and Sustainable

Energy Reviews 189 (January):113953.

El-Shahat, Adel, and ErhuvwuAyisire. 2021. “Novel

Electrical Modeling, Design and Comparative Control

Techniques for Wireless Electric Vehicle Battery

Charging.” Electronics 10 (22): 2842.

Han, Sekyung, and Moses AmoasiAcquah. 2021. Grid-to-

Vehicle (G2V) and Vehicle-to-Grid (V2G)

Technologies. MDPI.

Hossain, Md Ismail, Ali T. Al-Awami, and Mohammad A.

Abido. n.d. “A Proportional and Weight Based

Decentralized Charge Controller of Electric Vehicles

for the Improvement of Local Voltage Profile.”

Accessed February 1, 2025.

https://ieeexplore.ieee.org/abstract/document/1054990

Joseph, Peter K., Devaraj Elangovan, and Padmanaban

Sanjeevikumar. n.d. “System Architecture, Design, and

Optimization of a Flexible Wireless Charger for

Renewable Energy-Powered Electric Bicycles.”

Accessed January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/9105100

Liu, Yuxin, Chunhua Liu, Wusen Wang, Senyi Liu, and

Yong Chen. n.d. “A Novel Wired/Wireless Hybrid

Multiport Energy Router for Dynamic EV Energy

Internet with Grid-Tied and Islanded Operations.”

Accessed January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/1012484

Mohamed, Ahmed A. S., Ahmed A. Shaier, Hamid

Metwally, and Sameh I. Selem. 2024. “Wireless

Charging Technologies for Electric Vehicles:

Inductive, Capacitive, and Magnetic Gear.” IET Power

Electronics 17 (16): 3139–65.

Mohamed, Naoui, Flah Aymen, Turki E. A. Alharbi,

Claude Ziad El-Bayeh, Sbita Lassaad, Sherif S. M.

Ghoneim, and Ursula Eicker. n.d. “A Comprehensive

Analysis of Wireless Charging Systems for Electric

Vehicles.” Accessed January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/9759451/

Mohamed, Naoui, FlahAymen, and Mohammed Alqarni.

2021. “Inductive Power Transmission System for

Electric Car Charging Phase: Modeling plus Frequency

Analysis.” World Electric Vehicle Journal 12 (4): 267.

Quercio, Michele, Gabriele Maria Lozito, Fabio Corti,

Francesco Riganti Fulginei, and Antonino Laudani. n.d.

“Recent Results in Shielding Technologies for Wireless

Electric Vehicle Charging Systems.” Accessed

February 3, 2025.

https://ieeexplore.ieee.org/abstract/document/1041205

Rahulkumar, J., R. Narayanamoorthi, Pradeep Vishnuram,

Mohit Bajaj, Vojtech Blazek, Lukas Prokop, and

Stanislav Misak. n.d. “An Empirical Survey on

Wireless Inductive Power Pad and Resonant Magnetic

Field Coupling for In-Motion EV Charging System.”

Accessed January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/1000233

Ramakrishnan, Venkatesan, Savio A. Dominic, C. Balaji,

Narayanamoorthi Rajamanickam, Hossam Kotb, Ali

Elrashidi, and Waleed Nureldeen. n.d. “A

Comprehensive Review on Efficiency Enhancement of

Wireless Charging System for the Electric Vehicles

Applications.” Accessed February 1, 2025.

https://ieeexplore.ieee.org/abstract/document/1047399

Semsar, Sepehr, Zhichao Luo, Shuang Nie, and Peter W.

Lehn. n.d. “Integrated Wireless Charging Receiver for

Electric Vehicles with Dual Inverter Drives.” Accessed

January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/1026832

Shahin, Ahmed, Almoataz Y. Abdelaziz, Azeddine Houari,

Babak Nahid-Mobarakeh, Serge Pierfederici, Fujin

Deng, and Sayed Abulanwar. n.d. “A Comprehensive

Analysis: Integrating Renewable Energy Sources with

Wire/Wireless EV Charging Systems for Green

Mobility.” Accessed January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/1068941

Shi, Ke, Chunsen Tang, Zhihui Wang, Xiaofei Li,

Yuanzhao Zhou, and Yingjun Fei. n.d. “A Magnetic

Integrated Method Suppressing Power Fluctuation for

EV Dynamic Wireless Charging System.” Accessed

January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/9677927

Song, Kai, Yu Lan, Xian Zhang, Jinhai Jiang, Chuanyu

Sun, Guang Yang, Fengshuo Yang, and Hao Lan. 2023.

“A Review on Interoperability of Wireless Charging

Systems for Electric Vehicles.” Energies 16 (4): 1653.

Sora, James, Ioan Serban, and Dorin Petreus. n.d.

“Enhancing Microgrid Operation Through Electric

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

202

Vehicle Integration: A Survey.” Accessed February 3,

2025.

https://ieeexplore.ieee.org/abstract/document/1052151

Zhang, Shiyao, and James J. Q. Yu. n.d. “Electric Vehicle

Dynamic Wireless Charging System: Optimal

Placement and Vehicle-to-Grid Scheduling.” Accessed

January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/9528835

Zhang, Yiming, Shuxin Chen, Xin Li, and Yi Tang. n.d.

“Design of High-Power Static Wireless Power Transfer

via Magnetic Induction: An Overview.” Accessed

January 30, 2025.

https://ieeexplore.ieee.org/abstract/document/9675068

Zhang, Yiming, Wenbin Pan, Hui Wang, Zhiwei Shen,

Yuanchao Wu, Jiqing Dong, and Xingkui Mao. n.d.

“Misalignment-Tolerant Dual-Transmitter Electric

Vehicle Wireless Charging System with

Reconfigurable Topologies.” Accessed January 30,

2025.https://ieeexplore.ieee.org/abstract/document/973

9940.

Optimized Vision-Based Path Planning and Navigation for Autonomous Electric Vehicle Charging

203