The Natural and Physical Effects on the Mobile Robot Designed to Recognize and Collect Objects

Year 2023, Volume: 11 Issue: 2, 62 - 71, 30.06.2023

Erdem Abat Metin Turan

Abstract

Today, studies are carried out in the field of robotics, such as the discovery of old or unknown places, their targeting, and object recognition. The designed robots can be dressed as cars, drones, people or arms for use. This common goal is to reduce humans work and to provide robots do everything what humans can do. These processes include hardware and software tasks. Artificial intelligence offers us the ability to teach and apply intelligence to the machines with the help of software. The aim of this study is to design a prototype mobile robot that can detect and recognize fruits that are far from the current location, but reachable by the robot, and can collect the fruits and transport them from one place to another. A prototype mobile robot was developed to obtain which conditions effects the robot purpose, when the environment was not planned for specific conditions. Experiments on the natural environment showed us that if sufficient light and angle were available then an average of 95% success rate in the correct recognition of objects and an average of 90% in detection achieved by the prototype robot. Moreover, the motor power and the arm handle area have very important role in the processes of the robot's hardware grasping and carrying the fruits. In addition, based on the observations obtained result of the experiments, ambient light is quite effective in capturing and detecting the object. The condition emerged result of an obstacle on the path was not considered in these experiments.

Keywords

Arduino, Artificial intelligence, Image processing, Mobile robot, Raspberry pi

References

• [1] Wührl, L., Pylatiuk, C., Giersch, M., Lapp, F., Rintelen V, T., Balke, M., Schmidt, S., Cerretti, P. ve Meier, R., “Robotic handling of small invertebrates with machine learning methods”, Molecular Ecology Resources, 0, 0, 2021, 3-8
• [2] Lary J., D., Schaefer, D., Waczak, J., Aker, A., Barbosa, A., Wijeratne H. O., L., Talebi, S., Fernando, B., Sadler, J., Lary, T. ve Lary D., M., “Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning”, Sensors: 20th Anniversary, 21, 6, 2021, 2-11
• [3] Rahman M., Q., Corke, P. ve Dayoub F., ”Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends”, IEEE Access, 9, 0, 2021, 20068-20073
• [4] Katija, K., Roberts D L, P., Daniels, J., Lapides, A., Barnard, K., Risi, M., Ranaan Y, B., Woodward G, B. ve Takahashi, J., “Visual tracking of deepwater animals using machine learning-controlled robotic underwater vehicles”, Winter Conference on Applications of Computer Vision, 0, 0, 2021, 861-867
• [5] Hiçdurmaz, A. ve Tuncer A., “Real-Time Obstacle Avoidance Based on Floor Detection for Mobile Robots”, Sakarya University Journal of Science, 24, 5, 2020, 847–851.
• [6] Ruby, J., Daenke, S., Yuan, Y., Harry, W., Tisa, J., Nedumaan, J., Yung, Y., Lepika, J., Binford, T., Kumar J. S., P. ve Hu, W., “Automatic Speech Recognition and Machine Learning for Robotic Arm in Surgery”, The American Journal of Surgery, 4, 0, 2020, 12-16
• [7] Kahya E. ve Arın S., “Design of a Robotic Pneumatic Pruner for Robotic Apple Harvesting”, European Journal of Engineering and Natural Sciences, 3, 2, 2019, 13–17.
• [8] Karakoç A., Doğan D. ve Akıncı T.C., “Robotic Arm Control Using The Brain Waves”, The Journal of Cognitive Systems, 2, 2, 2017, 52–54.
• [9] Aivaliotis, P., Zampetis, A., Michalos, G. ve Makris, S., “A machine learning approach for visual recognition of complex parts in robotic manipulation”, Procedia Manufacturing, 11, 0, 2017,424-429.
• [10] Gopalapillai, R., Guptab, D. ve TSB, S., “Pattern Identification of Robotic Environments using Machine Learning Techniques”, Procedia Computer Science, 115, 0, 2017, 64-69.
• [11] Fard J., M., Ameri, S., Chinnam B., R., Pandya K., A., Klein D., M., ve Ellis D., R., “Machine Learning Approach for Skill Evaluation in Robotic-Assisted Surgery”, The World Congress on Engineering and Computer Science, 1, 0, 2016.
• [12] Batur D.G. ve Erol S., “Using Simulated Annealing for Flexible Robotic Cell Scheduling”, Gazi University Journal of Science, 29, 3, 2016, 574-580.
• [13] Kahya E. ve Arın S., “Kivi Meyvesi Hasadında Robot Kullanımı Üzerine Bir Araştırma”, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 18, 3, 2015, 4-8.
• [14] Dr. Lukka J., T., Dr. Tossavainen, T., Dr. Kujala V., J., ve Dr. Raiko T., “Robotic Sorting using Machine Learning”, ZenRobotics Recycler, 0, 0, 2014, 2–7.
• [15] Perkowski, M., Sasao, T., Iseno, A., Wong, U. ve Lukac, M., “Use of Machine Learning Based on Constructive Induction in Dialogs with Robotic Heads”, The Eighth International Conference on Rehabilitation Robotics, 0, 0, 2003.