HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION PROJECT

ROVER ROBOT WITH ARM

LE QUANG TOAN
Student ID: 19119034
Major: COMPUTER ENGINEERING TECHNOLOGY

Ho Chi Minh City, January 2025

HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION PROJECT

ROVER ROBOT WITH ARM

LE QUANG TOAN
Student ID: 19119034
Major: COMPUTER ENGINEERING TECHNOLOGY
Advisor: TRUONG NGOC SON, Assoc. Prof.

Ho Chi Minh City, January 2025

THE SOCIALIST REPUBLIC OF VIETNAM
Independence – Freedom– Happiness

***

GRADUATION PROJECT ASSIGNMENT
Student name: Le Quang Toan

Student ID: 19119034

Major: Computer Engineering Technology

Class: 19119CLA2

Advisor: Assoc. Prof. Truong Ngoc Son
Date of assignment:
1. Project title: Rover Robot With Arm.
2. Initial materials provided by the advisor: None
3. Content of the project:
- Designing and assembling a rover robot with a robotic arm.
- Implementing hand gesture control using MediaPipe.
- Integrating WebSocket for wireless control of servos and DC motors.
4. Final product: Building a remote control system for the Rover Robot With
Arm using hand gesture recognition with MediaPipe.

CHAIR OF THE PROGRAM
(Sign with full name)

ADVISOR
(Sign with full name)

THE SOCIALIST REPUBLIC OF VIETNAM
Independence – Freedom– Happiness

***

ADVISOR’S EVALUATION SHEET
Student name: Le Quang Toan

Student ID: 19119034

Major: Computer Engineering Technology
Project title: Rover Robot With Arm.
Advisor: Assoc. Prof. Truong Ngoc Son
EVALUATION
2. Content of the project:
.............................................................................................................................
.............................................................................................................................
3. Strengths:
.............................................................................................................................
.............................................................................................................................
4. Weaknesses:
.............................................................................................................................
5. Approval for oral defense? (Approved or denied)
Approved for oral defense
6. Overall evaluation: (Excellent, Good, Fair, Poor)
...................................................................
...

...
varying environmental conditions
(e.g., low light, different viewing angles) remains an area for improvement.
Future research could explore and apply advanced deep learning models,
such as convolutional neural networks (CNNs) or other machine learning
models, to enhance recognition performance.



Enhancing automation and learning capabilities of the robot: Another
critical development direction is researching and applying machine learning
algorithms to enable the robot to autonomously learn and improve its ability
to perform complex tasks. This could include learning new skills from users
through gestures or adapting to real-world scenarios.

In summary, the current system has achieved encouraging results, but there are
still numerous opportunities to enhance and develop the system, expand its
applications across different fields, and a more complete and advanced
product in the future.

58

REFERENCES
[1]. Jain, A. K., &amp Zhong, J. (2019). A Survey of Hand Gesture Recognition
Techniques and Applications. International Journal of Computer Vision, 43(1), 3-19.
[2]. Singh, S., &amp Garg, S. (2020). Hand Gesture Recognition for Human-Robot
Interaction: A Review. Journal of Robotics and Automation, 3(1), 10-21.
[3]. MediaPipe Team, (2020). MediaPipe: A framework for building crossplatform multimodal applied machine learning pipelines. Google AI Blog. Retrieved
from https://ai.googleblog.com/2020/05/mediapipe-framework-for-building-cross.html
[4]. Gallo, B., San-Segundo, R., &amp Lucas, J. M. (2015). Gesture Control for
Robotic Arm using Image Recognition. IEEE Transactions on Robotics, 31(4), 989998.
[5] F. Zhang, V. Bazarevsky, A. Vakunov, A. Tkachenka, G. Sung, C.-L. Chang,
and M. Grundmann, MediaPipe Hands: On-device Real-time Hand Tracking, Google
Research, Mountain View, CA, USA.
[6]. Lee, S., &amp Yang, W. (2021). Deep Learning for Hand Gesture Recognition
using MediaPipe. International Conference on Advanced Robotics and Intelligent
Systems, 57-62.
[7]. Weng, Y., &amp Chen, J. (2018). Design and Development of a GestureControlled Robotic Arm. Journal of Mechanical Engineering, 35(2), 114-121.
[8]. Zhi, W., &amp Wang, C. (2017). Real-time Hand Gesture Recognition for Robotic
Arm Control. IEEE International Conference on Robotics and Automation, 45-50.

[9]. Abraham, B. (2024). Week 9: Output Devices. Fab Academy. Retrieved
December 23, 2024, from https://fabacademy.org/2024/labs/kochi/students/basilabraham/week-9.html

59