T A D Q I Q O T L A R
jahon ilmiy – metodik jurnali
https://scientific-jl.com
59-son_4-to’plam_Aprel-2025
48
ISSN:3030-3613
INTELLIGENT SOFTWARE FOR CONTROLLING ROBOTIC SYSTEMS
USING VIRTUAL MODELING
D.Sc., Prof.
U.A. Ziyamuxammedova
Mahmudov L. A. Erkayev S. R.
Kimyo International University in Tashkent
Master’s Program in Mechatronics and Robotics
Email: mahmudov.laziz15@gmail.com
Abstract:
In the evolving landscape of robotics and automation, the need for
intelligent software that enables autonomous, adaptive, and efficient robot behavior is
becoming increasingly vital. This research explores the design and development of
intelligent control software for mobile robotic systems, emphasizing virtual modeling
and simulation as key tools in the development process. Utilizing the CoppeliaSim Edu
environment, a three-wheeled mobile robot was modeled, simulated, and equipped
with multiple sensory modules including infrared proximity sensors, color detection
units, and timing mechanisms. The robot operates in both manual and autonomous
modes and is governed by a custom-designed user interface that allows real-time
parameter adjustments, path planning, and command sequencing. The simulation
environment not only provides a low-cost, safe, and flexible platform for testing and
analysis but also serves as a bridge between theoretical algorithm development and
practical robotic deployment. The robot's behavior was governed by mathematical
models that consider sensor feedback for dynamic navigation, wall-following, and
obstacle avoidance. The system's performance was evaluated using visual trajectory
analysis, tabulated motion parameters, and sensor response graphs. The findings
demonstrate the viability of using virtual prototyping as a core part of robotic system
design, allowing for rapid iteration and refinement. Moreover, the modular architecture
of the system supports further integration with machine learning techniques such as
reinforcement learning, enabling advanced autonomous behavior. This research
contributes to the growing field of intelligent mechatronic system design and provides
a strong foundation for continued exploration in both academic and industrial settings.
Keywords:
Mobile Robot, Intelligent Control Software, CoppeliaSim,
Autonomous Navigation, Simulation, Human-Robot Interface.
The rapid advancement of robotics technology has significantly transformed various
sectors such as manufacturing, healthcare, logistics, defense, and consumer services.
At the heart of this transformation lies the development of intelligent control systems
that allow robots to perform tasks with minimal human intervention while adapting to
dynamic and uncertain environments. Modern robotic systems are no longer limited to
T A D Q I Q O T L A R
jahon ilmiy – metodik jurnali
https://scientific-jl.com
59-son_4-to’plam_Aprel-2025
49
ISSN:3030-3613
pre-programmed motions; they must perceive, interpret, and act based on real-time
data. This evolution demands sophisticated software capable of handling complex
sensor input, making intelligent decisions, and executing precise control commands.
The design and implementation of such intelligent control software are often hindered
by the cost and complexity of physical robotic hardware. To mitigate these limitations,
simulation environments have emerged as indispensable tools in robotics research and
development. Among these, CoppeliaSim (formerly known as V-REP) offers a
versatile and user-friendly platform that supports 3D modeling, multi-sensor
integration, dynamic simulation, and scripting in several programming languages,
particularly Lua.
This study presents a comprehensive approach to developing and testing
intelligent control algorithms for a mobile robot using CoppeliaSim Edu. The chosen
robot is a three-wheeled differential drive system, commonly used in service and
research robotics due to its maneuverability and structural simplicity. The robot model
is enriched with a range of sensors to simulate real-world perception and decision-
making. A user interface was designed to facilitate direct interaction with the robot,
enabling control over movement parameters such as speed, direction, turning angle,
and operational duration. This interface also supports automated command execution,
allowing the robot to follow pre-defined sequences or respond to environmental stimuli
in real-time. The introduction of mathematical modeling and algorithmic logic—such
as wall-following behaviors, distance tracking, and obstacle avoidance—further
strengthens the robot's autonomy. The results of the simulation were analyzed through
graphical plots of motion paths, sensor responses, and tabulated data on command
execution. This approach not only enhances learning outcomes for robotics students
but also provides a prototype for developing intelligent robotic systems in industrial
settings. By integrating theory, simulation, and interface design, this work contributes
to the development of practical mechatronic systems and highlights the importance of
virtual modeling as a scalable and safe methodology in robotics. Future research will
focus on integrating machine learning algorithms to enable continuous adaptation and
improvement of robotic behavior in increasingly complex environments.
The CoppeliaSim Edu platform was chosen for its flexibility, cross-platform
support, and extensive scripting capabilities. The virtual robot model was constructed
using basic geometric primitives, dynamically grouped, and configured with realistic
friction and collision parameters.
The robot model comprises:
Drive System:
Three independent wheels driven by motors.
Sensors:
Infrared sensors for proximity detection, a vision sensor for color
detection, and additional proximity sensors for wall-following.
Actuators:
Motors configured to control forward movement and turning.
T A D Q I Q O T L A R
jahon ilmiy – metodik jurnali
https://scientific-jl.com
59-son_4-to’plam_Aprel-2025
50
ISSN:3030-3613
User Interface:
A custom XML-based interface enables real-time control over
speed, turning rate, and movement commands.
The control strategy is based on real-time sensor feedback and employs standard
motion equations. For example, the traveled distance
d
is calculated using the
Euclidean distance formula:
𝑑 = √(𝑥
2
− 𝑥
1
)
2
+ (𝑦
2
− 𝑦
1
)
2
(1)
where
(x1, y1)
and
(x2, y2)
represent the robot’s initial and current positions,
respectively.
Additionally, the turning angle
θ
is adjusted based on sensor data to maintain a
preset distance from obstacles. The control law for speed
v
and turning rate
ω
is
expressed as:
𝑣 = 𝑘
𝑣
(𝑑
{𝑑𝑒𝑠𝑖𝑟𝑒𝑑}
− 𝑑
{𝑚𝑒𝑎𝑠𝑢𝑟𝑒𝑑}
)
𝜔 = 𝑘
𝜔(𝜃
{𝑑𝑒𝑠𝑖𝑟𝑒𝑑}
− 𝜃
{𝑚𝑒𝑎𝑠𝑢𝑟𝑒𝑑}
)
Where
𝑘
𝑣
and
𝑘
𝑜𝑚𝑒𝑔𝑎
are proportional constants, and
𝑑
{𝑑𝑒𝑠𝑖𝑟𝑒𝑑}
and
θ
{𝑑𝑒𝑠𝑖𝑟𝑒𝑑}
are the target distance and angle, respectively.
The simulation produced a trajectory that illustrates the robot's ability to follow
a near-linear path with minor deviations due to obstacle avoidance. Shows the
simulated trajectory of the robot as it navigates the environment. The horizontal axis
represents the distance traveled (in meters), while the vertical axis indicates the lateral
deviation.
Figure 1. Simulated Robot Trajectory illustrating lateral deviations during
navigation.
The performance of the infrared and proximity sensors was evaluated during the
simulation. Figure 2 demonstrates the sensor response over time, indicating the
distance measurements captured as the robot approaches obstacles.
T A D Q I Q O T L A R
jahon ilmiy – metodik jurnali
https://scientific-jl.com
59-son_4-to’plam_Aprel-2025
51
ISSN:3030-3613
Figure 2. Sensor Data Analysis: Infrared sensor readings versus time during obstacle
detection.
The results of this study highlight the significance of integrating intelligent
control logic with virtual robotic modeling to enhance autonomy and adaptability in
robot behavior. Through the CoppeliaSim environment, it was possible to model a
complex robotic system and simulate its behavior under different conditions with high
accuracy and repeatability. The robot's ability to perform tasks such as wall-following,
obstacle avoidance, and movement along predefined trajectories was directly linked to
the effectiveness of sensor integration and the robustness of the control algorithms
implemented.
The use of proximity and infrared sensors allowed for dynamic
environmental perception, enabling the robot to make real-time decisions. As seen in
the graphical analysis (Figure 1 and Figure 2), the robot could maintain a consistent
distance from surrounding obstacles and adjust its path accordingly, confirming the
reliability of the mathematical models used. The implementation of Euclidean distance
formulas and feedback-based velocity control laws ensured that the robot maintained
both stability and accuracy in its motion.
Moreover, the graphical user interface (GUI)
developed as part of the project played a vital role in bridging human-robot interaction.
By allowing users to input specific commands and visualize the robot’s position and
performance in real-time, the GUI enhanced both usability and testability. The control
panel design, with sliders for speed and angle adjustments and command scripting
fields, contributed significantly to user flexibility and simulation testing efficiency.
An important observation during experimentation was the responsiveness of the
system to external changes. The robot’s behavior remained stable even when faced
with varying proximity sensor readings, which emulates real-world scenarios such as
approaching obstacles or navigating through narrow passages. This demonstrates the
resilience and fault tolerance of the control architecture. Another critical insight is the
scalability of the proposed system. The modular design of both hardware (virtual
T A D Q I Q O T L A R
jahon ilmiy – metodik jurnali
https://scientific-jl.com
59-son_4-to’plam_Aprel-2025
52
ISSN:3030-3613
components) and software (scripts and GUI) means that future upgrades, such as
integration of machine learning models or advanced computer vision systems, can be
implemented with minimal structural changes. Furthermore, the use of open-source
tools ensures accessibility and cost-effectiveness, making the approach suitable for
academic institutions, research labs, and even small-scale industry settings.
While the system performed well under simulated conditions, one limitation to
acknowledge is the abstraction of real-world physical uncertainties such as sensor
noise, wheel slip, and environmental unpredictability. These factors may influence real
hardware performance and thus must be considered in future physical implementations.
However, the virtual results serve as a reliable preliminary validation before physical
deployment.
This research successfully demonstrated the design, development, and
simulation of an intelligent software architecture for a mobile robotic system using
virtual modeling in CoppeliaSim Edu. By combining autonomous control algorithms,
real-time sensor feedback, and a user-friendly graphical interface, the system exhibited
reliable performance in tasks such as obstacle detection, wall-following, and trajectory
execution. The use of virtual environments not only provided a risk-free and cost-
effective platform for development but also enhanced the understanding of complex
robotic behaviors through visualization and real-time interaction. The mathematical
models and control strategies implemented were validated through extensive
simulation, demonstrating accurate motion control and responsiveness to
environmental stimuli.
REFERENCES
1.
Craig, J. J. (1987). Introduction to Robotics: Mechanics and control. In IEEE &
Department of Electrical Engineering and Applied Physics, Case Institute of
Technology, Case Western Reserve University, IEEE JOURNAL OF ROBOTICS
AND AUTOMATION: Vol. RA-3 (Issue 2).
2.
François-Lavet, V., Henderson, P., Islam, R., Bellemare, M. G., & Pineau, J. (2018).
An introduction to deep reinforcement learning. Foundations and Trends® in
Machine Learning, 11(3–4), 219–354. https://doi.org/10.1561/2200000071
3.
Joseph, L. (2018). Learning robotics using Python: Design, Simulate, Program, and
Prototype an Autonomous Mobile Robot Using ROS, OpenCV, PCL, and Python,
2nd Edition.
4.
Mataric, M. J. (2007). The Robotics primer. MIT Press.
5.
Quigley, M., Gerkey, B., & Smart, W. D. (2015). Programming Robots with Ros.
O’Reilly Media.
6.
Siciliano, B., & Khatib, O. (Eds.). (2016). Springer Handbook of Robotics (2nd
ed.). Springer. https://doi.org/10.1007/978-3-319-32552-1
T A D Q I Q O T L A R
jahon ilmiy – metodik jurnali
https://scientific-jl.com
59-son_4-to’plam_Aprel-2025
53
ISSN:3030-3613
7.
Siegwart, R., Nourbakhsh, I. R., & Scaramuzza, D. (2011). Introduction to
Autonomous Mobile Robots, second edition. MIT Press.
8.
Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic robotics. MIT Press.
9.
Zadeh, L. (1996). Fuzzy logic = computing with words. IEEE Transactions on
Fuzzy Systems, 4(2), 103–111. https://doi.org/10.1109/91.493904
