Interactive Quadruped Felid Class Robot with a Neural Processing Unit

The authors consider the urgent task of developing bionic robots, in particular robots on four legs. Their advantages are the ability to move on uneven terrain, to perform reconnaissance, rescue and other dangerous work, where they could replace humans. A review of the existing best-known and most functional bionic four-legged robots is given, with descriptions of their strengths and weaknesses, as well as peculiarities of their movement and use. The main problems in the development of such devices and their control systems are highlighted. The article provides information on the research and development of an interactive bionic robot of the felid class, whose skeletal structure control implementation is deeply explored. The features of hardware and software implementation of the robot are considered, and schematic and real images of the construction are presented. The application of a microcomputer device with a neural processing unit to solve the problem of machine vision is highlighted. The results of testing machine vision using the Yolo3 neural network in streaming video mode are presented. The average accuracy of the open face recognition as a result of the tests was 95 %. For different degrees of occlusion, the average score was 80 %, and occlusion variants in which the neural network was unable to recognize faces were also identified. The article concludes with a discussion of the advantages and disadvantages of the proposed robot and the possibility of its application in human life, including the solution of various practical tasks.

1. Arm P., Zenkl R., Sun B., Dietsche A. Spacebok: A dynamic legged robot for space exploration, International Conference on Robotics and Automation (ICRA), 2019, pp. 6288—6294, doi: 10.3929/ethz-b-000328593.

2. Hutter M., Gehring C., Lauber A., Gunther F. ANYmal — toward legged robots for harsh environments, Advanced Robotics, 2017, vol. 31, no. 17, pp. 918—931, doi: 10.1080/01691864.2017.1378591.

3. Chepur A. Evolution of Robots from Boston Dynamics, Computerra, 2019, available at: https://www.computerra.ru/237711/evolyutsiya-robotov-ot-boston-dynamics (accessed: 01.04.2023) (in Russian).

4. Bundin A. How Boston Dynamics created the world’s most famous robots and when they will start helping people, Forbes, 2019, available at: https://www.forbes.ru/biznes/384935-kakboston-dynamics-sozdala-samyh-znamenityh-robotov-v-mire-ikogda-oni-nachnut (accessed: 01.04.2023) (in Russian).

5. Guizzo E. Boston Dynamics Spot Robot Dog Goes on Sale, IEEE Spectrum, 2019, available at: https://spectrum.ieee.org/boston-dynamics-spot-robot-dog-goes-on-sale (accessed: 01.04.2023).

6. Boston Dynamics’ Spot is leaving the laboratory, available at: https://www.theverge.com/2019/9/24/20880511/boston-dynamics-spot-robot-mini-hands-on-lease-buy (accessed: 01.04.2023).

7. Vasilyev R., Petrovsky A. Automatic turtle, Radio Magazine, 1958, vol. 3, pp. 48—51 (in Russian).

8. Petoi Robot Cat Nybble, available at: https://www.petoi.com/products/petoi-nybble-robot-cat (accessed: 01.04.2023).

9. Kau N., Schultz A., Ferrante N., Slade P. Stanford doggo: An open-source, quasi-directdrive-quadruped, 2019, International Conference on Robotics and Automation (ICRA), 2019, pp. 6309—6315.

10. Wolf D. A. Software implementation of group control of collector motors, Proceedings of the 33rd International Scientific and Technical Conference “Extreme Robotics”. St. Petersburg: Central Research Institute of Robotics and Technical Cybernetics, 2022, iss. 33, pp. 206—212 (in Russian).

11. MotoDriver software library, available at: https://github.com/Runsolar/motodriver (accessed: 01.04.2023).

12. Obaida T., Hassan N. F., Jamil A. S. Comparative of ViolaJones and YOLO v3 for Face Detection in Real time, Iraqi Journal of Computers, Communications, Control and Systems Engineering, 2022, vol. 22(2), pp. 63—72, doi: 10.33103/uot.ijccce.22.2.6.

13. Liu W. Video face detection based on deep learning, Wireless Personal Communications, 2018, vol. 102, no. 4, pp. 2853—2868.

14. Hassan N. F., Abdulrazzaq H. I. Pose invariant palm vein identification system using convolutional neural network, Baghdad Science Journal, 2018, vol. 15, no. 4.

15. Dang K., Sharma S. Review and comparison of face detection algorithms, 7th International Conference on Cloud Computing, Data Science & Engineering-Confluence, IEEE, 2017, pp. 629—633.

16. Chenwei L., Jia L., Wei Qi Y. Human Action Recognition from Digital Videos Based on Deep Learning, Proceedings of the 5th International Conference on Control and Computer Vision, 2022, vol. 22, pp. 150—155.

17. File detect-camera.cpp, available at: https://github.com/khadas/OpenCV_NPU_Demo (accessed: 01.04.2023).

18. File flask-face.py, available at: https://github.com/khadas/ksnn (accessed: 01.04.2023).

19. Galin R. R., Meshcheryakov R. V., Mamchenko M. V. Simple Task Allocation Algorithm in a Collaborative Robotic System, Frontiers in Robotics and Electromechanics, Sankt-Petersburg: Springer, 2023, pp. 433—447.

20. Shirokov A. S., Salomatin A. A., Galin R. R., Zorin V. A. Modeling of Joint Motion Planning of Group of Mobile Robots and Unmanned Aerial Vehicle, Frontiers in Robotics and Electromechanics, Singapore, Springer, 2023, pp. 163—177.