A Mobile Robot Based on Edge AI
Resumo
Recent advancements in technology have enabled the emergence of Industry 4.0, this term is used to describe the integration of various advanced technologies such as artificial intelligence and robotics in industrial settings. The presence of defective products during production incurs additional costs, and traditional manual methods of equipment inspection prove to be inefficient in such a dynamic environment. In this study, we introduce a robot designed specifically for this scenario, capable of performing tasks that require autonomous movement to specific areas of an industrial plant. To achieve this, we employ the concept of Edge AI, applying artificial intelligence on a localized edge computing device. The robot utilizes computer vision through the state-of-the-art YOLOv7 CNN and incorporates feedback control to facilitate its locomotion. The hardware components of this robot include a Jetson Xavier NX, Raspberry Pi 4, a camera, and a LIDAR. Additionally, we conducted a comprehensive performance analysis of the object detection method, measuring metrics such as frames per second (FPS), CPU and GPU consumption, and RAM usage.
Referências
Albawi, S., Mohammed, T. A., and Al-Zawi, S. (2017a). Understanding of a convolutional neural network. In 2017 international conference on engineering and technology (ICET), pages 1–6. Ieee.
Albawi, S., Mohammed, T. A., and Al-Zawi, S. (2017b). Understanding of a convolutional neural network. In 2017 International Conference on Engineering and Technology (ICET), pages 1–6.
Arulprakash, E. and Aruldoss, M. (2022). A study on generic object detection with emphasis on future research directions. Journal of King Saud University-Computer and Information Sciences, 34(9):7347–7365.
Chen, J. and Ran, X. (2019). Deep learning with edge computing: A review. Proceedings of the IEEE, 107(8):1655–1674.
Cheng, M. and Xiang, D. (2020). The design and application of a track-type autonomous inspection robot for electrical distribution room. Robotica, 38(2):185–206.
Dandurand, P., Beaudry, J., Hébert, C., Mongenot, P., Bourque, J., and Hovington, S. (2022). All-weather autonomous inspection robot for electrical substations. In 2022 IEEE/SICE International Symposium on System Integration (SII), pages 303–308. IEEE.
Ebayyeh, A. A. R. M. A. and Mousavi, A. (2020). A review and analysis of automatic optical inspection and quality monitoring methods in electronics industry. IEEE Access, 8:183192–183271.
Florescu, A. and Barabas, S. A. (2020). Modeling and simulation of a flexible manufacturing system—a basic component of industry 4.0. Applied sciences, 10(22):8300.
Hassoun, A., Aı̈t-Kaddour, A., Abu-Mahfouz, A. M., Rathod, N. B., Bader, F., Barba, F. J., Biancolillo, A., Cropotova, J., Galanakis, C. M., Jambrak, A. R., et al. (2022). The fourth industrial revolution in the food industry—part i: Industry 4.0 technologies. Critical Reviews in Food Science and Nutrition, pages 1–17.
Hercik, R., Byrtus, R., Jaros, R., and Koziorek, J. (2022). Implementation of autonomous mobile robot in smartfactory. Applied Sciences, 12(17):8912.
Ishikawa, S. (1991). A method of indoor mobile robot navigation by using fuzzy control. In Proceedings IROS’91: IEEE/RSJ International Workshop on Intelligent Robots and Systems’ 91, pages 1013–1018. IEEE.
Krogh, A. (2008). What are artificial neural networks? Nature biotechnology, 26(2):195–197.
Li, E., Zeng, L., Zhou, Z., and Chen, X. (2019). Edge ai: On-demand accelerating deep neural network inference via edge computing. IEEE Transactions on Wireless Communications, 19(1):447–457.
Salimpour, S., Queralta, J. P., and Westerlund, T. (2022). Self-calibrating anomaly and change detection for autonomous inspection robots. arXiv preprint arXiv:2209.02379.
Szrek, J., Jakubiak, J., and Zimroz, R. (2022). A mobile robot-based system for automatic inspection of belt conveyors in mining industry. Energies, 15(1):327.
Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y. M. (2022). Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696.
Wang, X., Han, Y., Wang, C., Zhao, Q., Chen, X., and Chen, M. (2019). In-edge ai: Intelligentizing mobile edge computing, caching and communication by federated learning. IEEE Network, 33(5):156–165.
