Designing of Robotic Arm Decoding Hand Gestures

using Arduino Nano

2023 Second IEEE International Conference on Measurement, Instrumentation, Control and Automation (ICMICA) | 979-8-3503-5504-8/24/$31.00 ©2024 IEEE | DOI: 10.1109/ICMICA61068.2024.10732788

Shital Pawar Kshitija Dupare Tushar Ganvir

Department of Electronics & Department of Electronics & Department of Electronics &
Telecommunication Engineering Telecommunication Engineering Telecommunication Engineering
Vishwakarma Institute of Technology Vishwakarma Institute of Technology Vishwakarma Institute of Technology
Pune, India. Pune, India. Pune, India.
[email protected] [email protected] [email protected]

Abstract— The work focuses on developing a versatile The aim of this study is to create a functional robot arm
robotic arm, combining digital design, hardware construction, capable of performing assigned tasks. The methodology
and programming using Arduino Nano. The process begins with involves the utilization of an Arduino Nano microcontroller
the comprehensive design and prototyping of the robotic arm along with a flex sensor, a device designed to measure and
using Autodesk Fusion 360, a parametric modeling tool. The respond to a physical quantity. The study outlines a
robotic arm features and key components such as servo motors, comprehensive approach to translating human finger and hand
and its construction is systematically detailed. Integration of the movements into commands for the designed robotic arm.
Arduino Nano is explored for seamless system connectivity, with
a gesture-controlled circuit diagram. The programming logic, II. LITERATURE REVIEW
illustrated governs the robotic arm's response to input data
from sensors, particularly a gyroscope and a flex sensor. The The approach by P. Sihombing, et al. proposed integration
robotic arm displays movements across axes: forward (0 to 60 of hand gestures, flex sensors, and fuzzy logic in a novel
degrees) and reverse (300 to 360 degrees) in motions in X-Axis robotic arm control system has demonstrated intuitive and
governed by Motor 1; leftward (0 to 60 degrees) and rightward precise control over the arm's movements, making it
(300 to 360 degrees) motions in Y-Axis Motion governed by accessible and suitable for hazardous tasks. Moreover, the
Motor 4; upward (300 to 360 degrees) and downward (0 to 60 wireless control capability enhances the efficiency and
degrees) motions in Z-Axis governed by Motor 2. Gripper usability of the system, offering potential applications in
Control governed by Motor 3, manages gripper closure beyond replacing dangerous human tasks and accommodating
a flex sensor input of 750 and maintains an open position below various servo motor setups [1]. Another notable contribution
this threshold. These precise movements showcase the robotic comes from an intelligent mobile robotic arm system that
arm's versatility and controlled response to specific angle ranges utilizes gesture control. Through effective integration of
showcasing the system's performance, and effective control over hardware and software components, this system enables
different movements, gripper regulation, and lateral motion. precise and efficient gesture-based control, presenting
exciting possibilities for remote robotic operations and
Keywords— Robotic Arm, Gesture Control, Arduino Nano,
hazardous task applications [2]. Another paper explores an
MPU6050, Flex Sensor, Servo Motors, Human-Machine
intelligent mobile robotic arm system that utilizes gesture
Interface, Fusion 360, Gesture Recognition, Programming Logic,
Low-Cost Robotics.
control for its operation. This system acquires gesture data
through a specialized sensor and then analyzes it on a
I. INTRODUCTION computer to derive control parameters for both the robotic
arm and an accompanying car. The results of experimental
The human hand serves as a remarkable medium for
tests showcase the successful control of various robotic arm
communication, expressing different meanings through
motions and car movements through hand gestures. The
gestures that are deeply ingrained in our daily interactions.
seamless integration of hardware and software components
Including these gestures for robotic arm interfaces has the
allows for precise and efficient gesture-based control,
potential to revolutionize human-robot interaction. Robust
presenting exciting possibilities for remote robotic
decoding mechanisms enable natural communication,
operations. Furthermore, the paper emphasizes the potential
impacting healthcare, manufacturing, and assistive
application of this system in hazardous tasks, expanding the
technology. This integration holds significant societal
scope of its usability and highlighting its adaptability and
potential, particularly in enhancing accessibility for
low-cost construction [3]. In the domain of virtual robotic
individuals with physical disabilities. In healthcare, gesture-
arms, real-time control using surface electromyography
controlled robotic arms aid delicate procedures and
(sEMG) signals for hand gesture detection has been explored.
rehabilitation. In manufacturing, streamlined interaction
While successful in identifying different hand poses, further
improves efficiency and safety. Human-robot collaboration
improvements are required to address instability in certain
benefits from natural communication, enhancing user-
arm poses [4]. The proposed enhancements, such as limiting
friendliness and acceptance. In education, gesture-based
arm movement to two degrees and incorporating forward and
control simplifies learning, contributing to workforce
inverse kinematics, show promise for improving the system's
development. In entertainment, these arms revolutionize
control accuracy [4]. The development of a portable robotic
interactive experiences. Additionally, in scenarios like
arm with four degrees of freedom showcases the potential for
disaster response, gesture-controlled robotic arms facilitate
creating a versatile robotic arm that imitates human arm
precise remote control, exemplifying broad societal impact
movements with minimal delay, making it suitable for
from daily assistance to high-stakes scenarios.
various lightweight tasks [5].

Authorized licensed use limited to: Nirma University Institute of Technology. Downloaded on January 06,2025 at 12:43:22 UTC from IEEE Xplore. Restrictions apply.
 Low-cost construction and design have been investigated, III. METHODOLOGY
aiming to provide an affordable robotic arm solution for The methodology unfolds in four distinct stages. The
third-world countries facing budget constraints. The
initial phase consists the design of the prototype. The second
utilization of recycled materials and PC-based control using
stage involves integration of the real hardware. The 3D
parallel communication have resulted in a practical and viable
solution for industrial automation needs in resource-limited printed robotic ARM is used with 4 servo motors for robotic
settings [6]. The use of sensors, robotic control through ARM movement. The third stage integrates the Arduino
gestures, microcontrollers and their applications [7], [8]. Nano microcontroller with various components essential for
Another study extended the discourse by outlining the use of the gesture control mechanism, including the Arduino Nano
Arduino microcontrollers and sensors for the control of itself, a Flex Sensor, a 10k Resistor, MPU6050, Hand Glove,
robotic arms [9]. Advancements in control techniques are Connecting Wires, and a Breadboard. The final stage centers
discussed which delves into the complexities of utilizing five around the establishment of programming logic and motion
axes to enhance robotic arm control [10]. control.
A method that utilizes sensors on human fingers to A. Designing the Robotic Arm Prototype
directly control a robot arm, suggesting significant The initial phase involved the comprehensive design and
advancements in creating more natural human-robot prototyping of the robotic arm using computer-aided design
interactions is discussed [11]. The work on myoelectric arms (CAD) software. The design process was executed in
takes a prominent role in specialized applications, Autodesk Fusion 360, a parametric modelling tool known for
contributing to the progress of robotic prosthetics [12]. its versatility in creating intricate 3D models. This digital
Another innovative approach is discussed which involves design phase served as a crucial step before actual hardware
designing a glove-based controller tailored to assist implementation, allowing planning, simulation, and iteration.
individuals with physical disabilities [13]. The researchers Utilizing Fusion 360's robust features, the conceptualization
apply robotic arms to fluid control systems in an application, and refinement of the robotic arm's structure, joints, and
which emphasized the importance of integrating components were conducted in a virtual environment. The
microcontrollers and sensors for precise control in these software facilitated the visualization of the arm's kinematics,
specific environments [14]. Advanced algorithms and aiding in the optimization of its range of motion and structural
techniques were explored, discussing the implementation of integrity. The digital prototype generated in Fusion 360 is
a modified filter algorithm for fetal electrocardiogram signals illustrated in Fig 1, providing a visual representation of the
[15]. Another work presents a study on interaction techniques proposed arm architecture. Subsequently, the finalized digital
for tracing finger movements and translating hand gestures model acted as a blueprint for the subsequent hardware
swiftly and accurately in robot controlling [16]. construction and testing phases.
Authors during their work in [17], [18] provides a
comprehensive overview of the interdisciplinary research
endeavors aimed at advancing robotic arm technology. By
synthesizing findings from a range of papers [19], [20], [21],
and [22], it underscores the importance of integrating state-
of-the-art technologies and methodologies to enhance the
performance, versatility, and applicability of robotic arms in
diverse domains.
Significant research gap lies in the gesture recognition
algorithms, enhance generalization capabilities, and explore
broader gesture recognition capabilities [4]. The potential for
gesture-controlled robotic arms in various fields, including
hazardous tasks and remote operations, requires further
investigation and validation [5]. To improve how well gesture
recognition technology works it is important to choose the
most appropriate hardware components, gesture recognition
robustness, stability, and cost-effectiveness These steps are Fig 1. Digital Prototype of the Robotic Arm in Fusion 360.
crucial for making the technology better and more reliable.
B. Hardware Implementation
The methodology discussed throughout this work directly
addresses these research gaps by providing a comprehensive The design and construction of the robot arm comprises a
approach to designing and implementing a gesture-controlled systematic approach to realizing a programmable mechanical
robotic arm system. By integrating sensors like the MPU6050 arm with functionalities analogous to human arms. This
gyroscope and accelerometer and the flex sensor, along with section outlines the key components, assembly model, and
an Arduino Nano microcontroller, our methodology enables structural elements involved in the development of the robot
precise control over the robotic arm's movements. The arm. The choice of motors emerged as a pivotal decision,
incorporation of hand gestures, flex sensors, and fuzzy logic where after careful evaluation of various motor types, the
in controlling robotic arms proves effective, especially for servo motor was deemed the most fitting for our application.
hazardous tasks. Intelligent mobile robotic arm systems To provide transparency in this selection process, a
employing gesture control present promising opportunities comparative table is presented below, showcasing key
for remote operations. parameters such as precision, speed, torque, and power
consumption. Table I. illustrates these critical parameters.

Authorized licensed use limited to: Nirma University Institute of Technology. Downloaded on January 06,2025 at 12:43:22 UTC from IEEE Xplore. Restrictions apply.
 TABLE I. COMPARATIVE ANALYSIS OF MOTOR TYPES sensor is used to control the gripper of the robotic arm. When
Motor Precision Speed Torque Power the flex sensor on the hand glove is bent, the servo motor
Type Usage attached to the gripper rotates and the gripper opens.
Servo High Medium High Medium The basic circuit diagram for the gesture-controlled
Stepper High Low High Medium robotic arm is presented in Fig 3. This diagram provides an
overview of the circuit connections, offering a fair
DC Medium High Medium High understanding of the coordination between the Arduino
Brushless High High Medium Low microcontroller and the various components involved in the
DC gesture control mechanism.
This deliberate selection, particularly the use of servo
motors, was driven by their superior performance in meeting
the specific requirements of the robotic arm design. This form
the foundational framework for the hardware design of robot
arm. The hardware implementation, featuring the integration
of four servo motors, is visually represented in Fig 2.

Fig 3. Circuit Diagram for Gesture-Controlled Robotic Arm.

3) Circuit Connection between MPU6050 and Arduino

Nano: The essential connections between the MPU6050 and
Arduino Nano components are given in Table II.
Fig 2. Hardware Implementation with Four Servo Motors.
TABLE II. INTERFACING DETAILS: MPU6050 TO ARDUINO NANO
C. Arduino Nano Integration and System Connectivity MPU6050 Pins Arduino Nano Pins
VCC +5V
This section delves into the pivotal aspect of Arduino
Ground Ground
integration and system connectivity within the context of Serial Data Line (SDA) Analog pin 4
robotic arm design. The Arduino Nano microcontroller plays Serial Clock Line (SCL) Analog pin 5
a central role in coordinating the functionalities of the robotic
arm and ensuring seamless communication with Flex Sensor, 4) Circuit Connection between Servo Motors and
and MPU6050. A detailed insight into the individual key Arduino Nano: The servo motors are connected with the
components used and their functionalities are discussed. Arduino nano to make it functional. Table III. shows the key
1) MPU6050 Gyroscopic and Accelometer connections between the Arduino Nano, servo motors, and
Sensor:MPU6050 is based on Micro-Mechanical Systems the accompanying power adapter.
(MEMS) technology. This sensor has a 3-axis accelerometer,
a 3-axis gyroscope, and an in-built temperature sensor. It can TABLE III. INTERFACING DETAILS: SERVO MOTOR TO ARDUINO
NANO
be used to measure parameters like Acceleration, Velocity,
Orientation, Displacement, etc. Arduino Nano Pins Servo Motor Pins Power Adapter
Digital pin 2 Servo 1 Orange -
Features in MPU6050 Sensor: (PWM Pin)
• Communication: I2C protocol with configurable Digital pin 3 Servo 2 Orange -
I2C Address Input Power Supply: 3-5V. (PWM Pin)
Digital pin 4 Servo 3 Orange -
• Built-in 16-bit ADC provides high accuracy. (PWM Pin)
• Built-in DMP provides high computational power Digital pin 5 Servo 4 Orange -
(PWM Pin)
• Can be used to interface with other I2C devices like
Ground Servo 1, 2, 3, 4 Brown -
a magnetometer . (Ground Pin)
• In-built temperature sensor. Ground - -
+5V - Servo 1, 2, 3, 4 Red
2) Flex Sensor: Flex Sensors are nothing but a variable (+5V Pin)
resistor. The flex sensor resistance changes when the sensor
is bent. They are usually available in two sizes 2.2 inches and
4.5 inches. In the Gesture controlled Robotic Arm, a flex

Authorized licensed use limited to: Nirma University Institute of Technology. Downloaded on January 06,2025 at 12:43:22 UTC from IEEE Xplore. Restrictions apply.
 5) Circuit Connection between Flex Sensor and Arduino
Nano: The connection of flex sensor with Ardino Nano is
demonstrated in Table IV.

TABLE IV. INTERFACING DETAILS: SERVO MOTOR TO ARDUINO

NANO
Flex Sensor Pins Arduino Nano Pins
Pin 1 Analog 0 pin (with a 10k resistor)
Pin 2 Ground

The detailed connections described above collectively

serve as the foundation for the electronic framework of the
robotic arm, guaranteeing efficient communication and
coordination among the MPU6050, servo motors, flex sensor,
and the Arduino Nano.
The MPU6050 and Flex Sensor are mounted on to a hand
glove. A wired connection is used to connect Glove and
robotic arm as shown in Fig 4.

Fig 5. Flowchart of Robotic Arm System Logic.

IV. RESULTS AND DISSCUSSION

The section presents an exploration derived from the
implementation of a gesture-controlled robotic arm. The
Fig 4. Sensor Integration and Wired Connection. integration of gyroscope and flex sensor data with servo motor
control has been a pivotal aspect of this study, offering a novel
D. Programming Logic and Motion Control approach to translating human gestures into robotic
The programming logic that governs the functionality of movements. By examining forward and reverse motion,
the robotic arm system dictating how the Arduino Nano upward and downward movement, lateral motion, and gripper
interprets input data from sensors, processes it, and decodes regulation, this analysis seeks to provide a comprehensive
the corresponding movements of the servo motors is understanding of the system's performance and its potential
discussed in this section. The motion detection is facilitated applications in diverse scenarios.
through the utilization of a gyroscope and a flex sensor. These A. Forward and Reverse Motion (Motor 1)
sensors provide input data, which is then processed using an
Motor 1 effectively controls both forward (0 to 60 degrees)
Arduino Nano. The generated data controls the movement of and reverse motion (300 to 360 degrees) along the X-Axis,
a robotic arm equipped with servo motors. The first servo enabling successful execution of the robotic arm's movements
motor, designated as motor 1, operates based on the x-axis depicted in Fig 6.
values from 0 to 60 degrees, facilitating forward or reverse
motion of the arm. Meanwhile, servo motor 2 responds to x-
axis values ranging from 300 to 360 degrees, enabling
upward or downward movement of the arm. Servo motor 4
engages with y-axis values from 0 to 60 degrees for leftward
motion and from 300 to 360 degrees for rightward movement.
Lastly, servo motor 3 regulates the gripper of the arm: when
the input value from the flex sensor exceeds 750, the gripper
closes; otherwise, it remains open. The visual representation
of the entire procedural sequence of robotic arm system and
the intricate steps involved in the programming logic is
shown in Fig 5. which presents a comprehensive flowchart Fig 6. Forward and Reverse Motion Control.
showcasing the decision-making processes and sequential
operations that guide the behavior of the Arduino Nano, servo
motors, and other integrated components.

Authorized licensed use limited to: Nirma University Institute of Technology. Downloaded on January 06,2025 at 12:43:22 UTC from IEEE Xplore. Restrictions apply.
 B. Upward and Downward Movement (Motor 2) movements. The results are summarized in the following
Motor 2, responsible for managing upward motion (300 Table V:
to 360 degrees) and downward motion (0 to 60 degrees) along
the Z-Axis of the robotic arm is illustrated in Fig 7. TABLE V. ROBOTIC ARM MOTION CONTROL TEST RESULTS

Motion Type Total Accurate Failure Success

Tests Results Count Rate

Forward/ Reverse 15 14 1 93.33%

Motion

Upward/Downward 18 17 1 94.44%
Movement

Gripper Regulation 12 11 1 91.67%

Leftward/ Rightward 25 23 2 92.00%

Motion
Fig 7. Upward and Downward Motion Control.
Total 70 67 5 95.71%
C. Gripper Regulation (Motor 3)
Motor 3, responsible for regulating the gripper based on The accuracy was calculated by dividing the number of
flex sensor input, demonstrated a robust grip control accurate results by the total number of tests conducted and
mechanism. When the flex sensor input exceeded the multiplying by 100 to obtain the success rate. The data
threshold of 750, the gripper closed, showcasing a reliable demonstrates the system's success rate, with an overall
mechanism for gripping and releasing objects shown in Fig 8. accuracy of 95.71%, indicating coordination between input
data and servo motor responses. The system demonstrates its
effectiveness through precise coordination between input
data and servo motor responses, ensuring accurate translation
of user gestures into the desired arm movements.
V. CONCLUSION AND FUTURE SCOPE
The research focused on creating a versatile robotic arm
by combining advanced digital design, careful hardware
building, use of Arduino Nano, and detailed programming. A
software called Autodesk Fusion 360 is used to plan and
simulate the arm's movements before building it with key
components like servo motors. The Arduino Nano played a
crucial role in making everything work smoothly. The
Fig 8. Gripper Control Mechanism.
programming logic demonstrated how the arm responds to
D. Leftward and Rightward Motion (Motor 4) data from sensors. Additionally, the project's importance is
Utilizing Y-axis values from 0 to 60 degrees for leftward highlighted by successfully where the robotic arm is
effectively controlled using fingers, and hand gestures. The
motion and 300 to 360 degrees for rightward movement
use of sensors, Arduino, and a flex sensor on a finger glove
governed by Motor 4 showcased effective lateral control of
allowed users to control the robot's movements, adjusting its
the robotic arm illustrated in Fig 9, allowing it to navigate in shoulder and upper arm angles. This approach made the
horizontal directions. control system even more refined. The use of low-cost
materials makes the robotic arm accessible, with successful
demonstrations showing its potential to handle tasks
considered unsafe for human hands. The program's flexibility
allows for easy adaptation to various needs. This research not
only contributes to robotics but also suggests safer and more
efficient solutions for different applications.
The experimental evaluation of the implemented gesture-
controlled robotic arm system has provided valuable insights
into its performance across various motion types. The high
success rates observed in forward and reverse motion
(93.33%), upward and downward movement (94.44%),
Fig 9. Lateral Control of Robotic Arm. gripper regulation (91.67%), and leftward and rightward
motion (92.00%) highlight the effectiveness of the system in
The experimental evaluation of the implemented gesture-
executing diverse commands. The overall success rate of
controlled robotic arm system was conducted to assess its
95.71% across 70 tests underscores the robustness of the
performance across various motion types. A total of 70 tests implemented model. These results not only showcase the
were carried out to evaluate the system's accuracy and technical proficiency of the robotic arm but also emphasize
reliability in translating user gestures into robotic the successful coordination between input data and servo

Authorized licensed use limited to: Nirma University Institute of Technology. Downloaded on January 06,2025 at 12:43:22 UTC from IEEE Xplore. Restrictions apply.
 motor responses. The system's capacity to accurately interpret [6] S. Karmoker, M. M. H. Polash and K. M. Zakir Hossan, "Design of a
user gestures opens avenues for its application in various low cost PC interface Six DOF robotic arm utilizing recycled
materials," 2014 International Conference on Electrical Engineering
scenarios demanding controlled and efficient robotic and Information & Communication Technology, Dhaka, Bangladesh,
movements. The findings of this study contribute to the 2014, pp. 1-5, doi: 10.1109/ICEEICT.2014.6919073.
advancement of gesture-controlled robotic systems, offering a [7] R. V. Dharaskar. et.al., Robotic Arm Control Using Gesture and Voice.
promising solution for tasks requiring dexterous manipulation Int. Journal of Computer, Inf. Technology & Bioinformatics (IJCITB).
and precise motion control. As the system demonstrates a ISSN:2278-7593, Vol. 1, Issue-1. 2012.
remarkable overall accuracy of 95.71%, it stands as a [8] Abidhusain, et.al. “Flex Sensor Based Robotic Arm Controller Using
testament to its potential in real-world applications. Micro Controller” Journal of Software Eng. and Applications, Vol.5
No.5, 2012.
The future scope holds considerable potential for further [9] A. Rashmi, et.al. “Robotic Hand Controlling Using Flex Sensors and
advancements in the field of robotics and human-machine Arduino Uno”. Int. Research Journal of Eng. and Technology (IRJET)
interfaces. The current step involves a wired connection e-ISSN: 2395-0056. Vol. 06 Issue: 04, Apr 2019.
between the hand glove MPU6050 and Flex Sensor, and the [10] U. D. Meshram and R. Harkare, “FPGA Based Five-Axis Robot Arm
Controller,” Int. Journal of Electronics Engineering, Vol. 2, No. 1,
robotic arm, however implementing technologies such as RF
2010, pp. 209-211.
or Bluetooth connections could eliminate the need for wires,
[11] M. Bhusa, et.al. "Controlling Robot by Fingers Using Flex Sensors"
providing users with greater freedom of movement and Int. Journal of Computer Trends and Tech.67.8 (2019): 13-17.
convenience. It could explore enhanced sensor technologies [12] C. P. Shinde,” Design of Myoelectric Arm”, Int. Journal of Advanced
for more precise gesture recognition. Further refinements in Science, Engineering, and Technology. ISSN 2319-5924, V. 1, I. 1, pp
the programming logic and algorithmic approaches could lead 21-25. 2012.
to more complex and nuanced robotic movements, expanding [13] R. Singh, et.al, “Design and Development of a Data Glove for the
the range of applications. Additionally, the integration of Assistance of the Physically Challenged”. Int. Journal of Elect. and
artificial intelligence (AI) techniques could contribute to Communication Eng. and Tech. (IJECET).4(4), pp. 36–41. 2013.
adaptive learning and improved interaction capabilities, [14] L. Shrimanth Sudheer, Immanuel J., P. Bhaskar, and Parvathi C. S.
ARM 7 Microcontroller Based Fuzzy Logic Controller for Liquid
allowing the robotic arm to better understand and respond to Level Control System. International Journal of Electronics and
user intentions. Collaborations with healthcare professionals Communication Eng.& Tech. (IJECET).4(2), pp. 217–224. 2013.
could explore applications in rehabilitation and assistive [15] A. Turnip, et.al, An application of modified filter algorithm fetal
technology, while continued efforts in low-cost material electrocardiogram signals with various subjects, International Journal
utilization could make the technology more accessible to a of Artificial Intelligence, vol. 18, no. 1, pp. 207-217, 2020.
broader range of users. Overall, the future scope of this project [16] R. Deepan, Santhana Vikrama Rajavarman and K. Narasimhan., “Hand
envisions a pathway for continuous innovation, pushing the Gesture-Based Control of Robotic Hand using Raspberry Pi
boundaries of robotic capabilities and their integration into Processor”. Asian Journal of Scientific Research. Vol. 8, (I). 3. pp. 392-
402. 2015.
diverse real-world scenarios.
[17] Gaikwad, Vijay, Manasi Doiphode, Mandar Gatke, Gaurav Moona,
Chinmay Gavit, and Pranjal Ghuge. "Self-Regulated Robotic
REFERENCES Illuminant Using NodeMcu (ESP8266)." In 2023 International
[1] P. Sihombing, R. B. Muhammad, H. Herriyance and E. Elviwani, Conference on Emerging Smart Computing and Informatics (ESCI),
"Robotic Arm Controlling Based on Fingers and Hand Gesture," 2020 pp. 1-4. IEEE, 2023.
3rd International Conference on Mechanical, Electronics, Computer, [18] Madake, Jyoti, Prerana Zope, Isha Wargad, Shripad Bhatlawande, and
and Industrial Technology (MECnIT), Medan, Indonesia, 2020, pp. 40- Swati Shilaskar. "Vision-Based Detection of Water Hyacinth." In 2022
45, doi: 10.1109/MECnIT48290.2020.9166592. 5th International Conference on Computational Intelligence and
[2] H. He and Y. Dan, "The research and design of Smart mobile robotic Networks (CINE), pp. 1-5. IEEE, 2022.
arm based on gesture controlled," 2020 International Conference on [19] Bhorge, Siddharth, and Deepak Bedase. "Multi view human action
Advanced Mechatronic Systems (ICAMechS), Hanoi, Vietnam, 2020, recognition using HODD." In Advances in Computing and Data
pp. 308-312, doi: 10.1109/ICAMechS49982.2020.9310156. Sciences: Second International Conference, ICACDS 2018, Dehradun,
[3] S. Bularka, R. Szabo, M. Otesteanu and M. Babaita, "Robotic Arm India, April 20-21, 2018, Revised Selected Papers, Part I 2, pp. 499-
Control with Hand Movement Gestures," 2018 41st International 508. Springer Singapore, 2018.
Conference on Telecommunications and Signal Processing (TSP), [20] Karwande, Atharva, Pranesh Kulkarni, Pradyumna Marathe, Tejas
Athens, Greece, 2018, pp. 1-5, doi: 10.1109/TSP.2018.8441341. Kolhe, Medha Wyawahare, and Pooja Kulkarni. "Computer vision-
[4] B. Schabron, Z. Alashqar, N. Fuhrman, K. Jibbe and J. Desai, based wheat grading and breed classification system: a design
"Artificial Neural Network to Detect Human Hand Gestures for a approach." In Machine Learning and Information Processing:
Robotic Arm Control," 2019 41st Annual International Conference of Proceedings of ICMLIP 2020, pp. 403-413. Springer Singapore, 2021.
the IEEE Engineering in Medicine and Biology Society (EMBC), [21] Pawar, Shital, Jayant Meshram, Ajinkya Mondhe, Akash Nachan,
Berlin, Germany, 2019, pp. 1662-1665, doi: Tejas Nilangekar, and Aditya Patil. "Ripeness Detector for Vegetables
10.1109/EMBC.2019.8857264. and Fruits." In 2022 2nd International Conference on Intelligent
[5] P. Bora and V. Nandi, "Low cost shadow function based articulated Technologies (CONIT), pp. 1-5. IEEE, 2022.
robotic arm," 2015 International Conference on Energy, Power and [22] Barbadekar, Ashwini, Sarthak Bhake, and Sahil Parekh. "Design of a
Environment: Towards Sustainable Growth (ICEPE), Shillong, India, Cost-Effective Smart Mirror Using Raspberry Pi." In 2023
2015, pp. 1-4, doi: 10.1109/EPETSG.2015.7510079. International Conference for Advancement in Technology (ICONAT),
pp. 1-5. IEEE, 2023.

Authorized licensed use limited to: Nirma University Institute of Technology. Downloaded on January 06,2025 at 12:43:22 UTC from IEEE Xplore. Restrictions apply.