Design and Development of Gesture Controlled Robotic Arm

Prashant Sharma; Jay Limbachiya; Dhruv P More; Harshgiri Bhaveshgiri Goswami; Apexa Purohit; Mayur Chavda; Mayank Dev Singh; Jai Bahadur Balwanshi

doi:10.69968/rbhdkb06

Authors

Prashant Sharma UG Student, Department of Mechatronics Engineering, ITM Vocational University, Vadodara, Gujarat, India
Jay Limbachiya UG Student, Department of Mechatronics Engineering, ITM Vocational University, Vadodara, Gujarat, India
Dhruv P More UG Student, Department of Mechatronics Engineering, ITM Vocational University, Vadodara, Gujarat, India
Harshgiri Bhaveshgiri Goswami UG Student, Department of Mechatronics Engineering, ITM Vocational University, Vadodara, Gujarat, India
Apexa Purohit Assistant Professor, Department of Mechatronics Engineering, ITM Vocational University, Vadodara, Gujarat, India
Mayur Chavda Assistant Professor, Department of Mechatronics Engineering, ITM Vocational University, Vadodara, Gujarat, India
Mayank Dev Singh Associate Professor, Department of Mechatronics Engineering, ITM Vocational University, Vadodara, Gujarat, India
Jai Bahadur Balwanshi Dean, Faculty of Engineering & Technology, ITM Vocational University, Vadodara, Gujarat, India

DOI:

https://doi.org/10.69968/rbhdkb06

Keywords:

Gesture Recognition, Human-Robot Interaction (HRI), Inertial Measurement Unit (IMU), Arduino Microcontroller, Kinematic Modeling, Embedded Automation, Telerobotics

Abstract

The integration of intuitive human-machine interfaces into industrial and assistive robotics represents a significant frontier in automation engineering. Traditional control mechanisms, such as teach pendants, joysticks, and automated pre-programmed sequences, often present steep learning curves and lack the dexterity required for dynamic, unstructured environments. This research paper delineates the design, development, kinematic modeling, and performance evaluation of a high-dexterity, gesture-controlled robotic arm. The core objective is to establish a seamless, real-time control system that maps human hand kinematics directly to a multi degree-of-freedom (DOF) mechanical manipulator. The methodology hinges on a master-slave architectural paradigm. The master subsystem comprises an ergonomic sensor glove integrated with Micro-Electro-Mechanical Systems (MEMS) based Inertial Measurement Units (IMUs), specifically the MPU6050, and flex sensors to capture complex spatial orientations and finger actuations. Signal processing, including Kalman filtering to mitigate drift and noise, is executed via an ATmega328P microcontroller. Data transmission utilizes low latency 2.4 GHz NRF24L01 transceivers, ensuring wireless fidelity. The slave unit reconstructs the spatial data using inverse kinematics equations to drive a 5-DOF articulated robotic manipulator equipped with high-torque MG996R servo motors. Empirical evaluations reveal a system latency of less than 45 milliseconds and an angular positional accuracy of 94.2% across dynamic operational ranges. The resultant prototype demonstrates substantial viability for deployment in hazardous material handling, telesurgery, and advanced manufacturing settings, bridging the gap between natural human biomechanics and robust robotic actuation..

References

S. B. Niku, Introduction to Robotics: Analysis, Control, Applications, 3rd ed., Hoboken, NJ: John Wiley & Sons, 2020.

[2] A. Billard and D. Kragic, 'Trends and challenges in robot manipulation,' Science, vol. 364, no. 6446, 2019.

[3] R. Kumar, S. Singh, and P. Sharma, 'Sensor fusion techniques for MEMS based IMUs in robotic teleoperation,' IEEE Transactions on Industrial Electronics, vol. 68, no. 5, pp. 4310-4321, 2021.

[4] M. T. Mason, 'Toward robotic manipulation,' Annual Review of Control, Robotics, and Autonomous Systems, vol. 1, pp. 1-28, 2018.

[5] Y. Zhang, M. Liu, and H. Wang, 'Vision-based gesture recognition for HRI: A comparative study,' IEEE Access, vol. 9, pp. 11234-11245, 2021.

[6] J. Smith and L. Davis, 'Edge-computed Kalman filtering for low-latency embedded systems,' Journal of Real-Time Image Processing, vol. 19, no. 2, pp. 345-356, 2022.

[7] T. Smith, K. Johnson, and M. Brown, 'RGB-D sensor based teleoperation of industrial manipulators,' IEEE International Conference on Robotics and Automation (ICRA), pp. 456-462, 2020.

[8] H. Zhang and W. Liu, 'CNN based static hand gesture classification using OpenCV,' International Journal of Computer Vision, vol. 129, no. 4, pp. 1010-1025, 2021.

[9] N. Patel, A. Desai, and S. Mehta, 'Development of a flex-sensor based robotic hand,' Proceedings of the IEEE Global Conference on Artificial Intelligence and Internet of Things, pp. 88-93, 2022.

[10] MIT Mechatronics Lab, 'High-fidelity spatial orientation using 9-axis IMUs and quaternion mathematics,' Technical Report TR-2021-04, Massachusetts Institute of Technology, 2021.

[11] V. Kumar, P. Reddy, and S. Rao, 'Arduino-based gesture controlled robotic arm using MPU6050 and Bluetooth,' IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), pp. 1-6, 2022.

[12] L. Chen, 'EMG-based teleoperation of heavy machinery: Challenges and solutions,' Robotics and Computer-Integrated Manufacturing, vol. 82, p. 102540, 2023.

[13] InvenSense, 'MPU-6050 Six-Axis (Gyro + Accelerometer) MEMS MotionTracking Devices,' Product Specification, Rev. 3.4, 2020.

[14] Nordic Semiconductor, 'nRF24L01+ Single Chip 2.4GHz Transceiver,' Product Specification, Rev. 1.0, 2020.

International Journal of Innovations In Science Engineering And Management

https://ijisem.com 277

[15] C. Lin and Y. Hsu, 'Trapezoidal velocity profile generation for servomotor control in embedded systems,' IEEE Transactions on Control Systems Technology, vol. 29, no. 3, pp. 1120-1130, 2021.

[16] TowerPro, 'MG996R High Torque Metal Gear Dual Ball Bearing Servo,' Technical Datasheet, 2021.

[17] A. Gupta and R. Sharma, 'Calibration techniques for low-cost hobby servos in academic robotics,' Journal of Mechatronics and Robotics, vol. 6, no. 2, pp. 45-55, 2022.

[18] M. Di Luca, 'New method to measure blind multisensory synchronization latency,' IEEE Transactions on Haptics, vol. 13, no. 1, pp. 105-115, 2020.

[19] F. Rahman, A. Khan, and M. Ali, 'Isolated RF architectures for safe teleoperation in hazardous environments,' IEEE Sensors Journal, vol. 23, no. 4, pp. 3400-3410, 2023.

[20] S. Gupta, 'Applications of teleoperated robotics in EOD and toxic environments,' Defense Science Journal, vol. 72, no. 3, pp. 415-422, 2022.

[21] H. Wu, J. Zhao, and L. Sun, 'AI-driven trajectory optimization for human-robot interaction,' IEEE Transactions on Robotics, vol. 39, no. 1, pp. 150-165, 2023.

[22] Y. Kim and S. Park, '5G-enabled ultra-low latency teleoperation for cloud robotics,' IEEE Communications Magazine, vol. 60, no. 5, pp. 60-66, 2022.