Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Abstract

Real-time systems are widely used in industry, including technological process control systems, industrial automation systems, SCADA systems, testing, and measuring equipment, and robotics. The efficiency of executing an intelligent robot’s mission in many cases depends on the properties of the robot’s sensor and control systems in providing the trajectory planning, recognition of the manipulated objects, adaptation of the desired clamping force of the gripper, obstacle avoidance, and so on. This paper provides an analysis of the approaches and methods for real-time sensor and control information processing with the application of machine learning, as well as successful cases of machine learning application in the synthesis of a robot’s sensor and control systems. Among the robotic systems under investigation are (a) adaptive robots with slip displacement sensors and fuzzy logic implementation for sensor data processing, (b) magnetically controlled mobile robots for moving on inclined and ceiling surfaces with neuro-fuzzy observers and neuro controllers, and (c) robots that are functioning in unknown environments with the prediction of the control system state using statistical learning theory. All obtained results concern the main elements of the two-component robotic system with the mobile robot and adaptive manipulation robot on a fixed base for executing complex missions in non-stationary or uncertain conditions. The design and software implementation stage involves the creation of a structural diagram and description of the selected technologies, training a neural network for recognition and classification of geometric objects, and software implementation of control system components. The Swift programming language is used for the control system design and the CreateML framework is used for creating a neural network. Among the main results are: (a) expanding the capabilities of the intelligent control system by increasing the number of classes for recognition from three (cube, cylinder, and sphere) to five (cube, cylinder, sphere, pyramid, and cone); (b) increasing the validation accuracy (to 100%) for recognition of five different classes using CreateML (YOLOv2 architecture); (c) increasing the training accuracy (to 98.02%) and testing accuracy (to 98.0%) for recognition of five different classes using Torch library (ResNet34 architecture) in less time and number of epochs compared with Create ML (YOLOv2 architecture); (d) increasing the training accuracy (to 99.75%) and testing accuracy (to 99.2%) for recognition of five different classes using Torch library (ResNet34 architecture) and fine-tuning technology; and (e) analyzing the effect of dataset size impact on recognition accuracy with ResNet34 architecture and fine-tuning technology. The results can help to choose efficient (a) design approaches for control robotic devices, (b) machine-learning methods for performing pattern recognition and classification, and (c) computer technologies for designing control systems and simulating robotic devices.

A Novel Method for Recognizing Physical Fitness Signals of Basketball Players Based on Photovoltaic Power Supply

“…Atamanyuk, I., et,al. [28] have discussed how Machine learning techniques, such as deep learning and reinforcement learning, can improve the efficiency of a robot's sensor and control information processing. These techniques allow the robot to learn and adapt to its environment, making quick and accurate decisions, reducing processing time, and increasing its overall performance.…”

“…Therefore, the Hamilton function can be defined as follows ( ) ( ) X vl NH vl PQ =+ (28) This can include terrain features, weather conditions, and enemy activity. Surveillance can be conducted through various means, such as aerial surveillance, ground patrols, and electronic surveillance.…”

“…While there are standardized tests and protocols in place to measure fitness levels, the interpretation of these signals may vary among coaches, trainers, and even the players themselves [9]. It can lead to discrepancies in the assessment of physical fitness and make it challenging to identify potential problem areas or areas of improvement [10]. Another issue is the complexity of physical fitness and its interrelation with other factors, such as skill level and playing style [11].…”

The recognition of speech defects using convolutional neural network

“…The speech activity of the child is associated with different areas of development that are responsible for the mental abilities of the child. Sign G includes the following signs, which are contained in formula (7):…”

ACNS Conference on Cloud and Immersive Technologies in Education: Report

“…• Marc Baaden, CNRS, France [14] • Pablo Garcia Bringas, University of Deusto, Spain [89] • Oleksandr Burov, Institute for Digitalisation of Education of the NAES of Ukraine, Ukraine & University of Vienna, Austria [27] • Nadire Cavus, Near East University, North Cyprus [137] • El-Sayed El-Horbaty, Ain Shams University, Egypt [88] • Ramón Fabregat, University of Girona, Spain [35] • Irina Georgescu, Bucharest University of Economics, Romania [43] • Mustansar Ali Ghazanfar, University of East London, United Kingdom [58] • Anita Goel, University of Delhi, India [16] • Carina Gonzalez, Universidad de La Laguna, Spain [45] • Sven Hartmann, Clausthal University of Technology, Germany [150] • Michail Kalogiannakis, University of Crete, Greece [52] • Yuriy Kondratenko, Petro Mohyla Black Sea State University, Ukraine [69] • Francesco Lelli, Tilburg University, Netherlands [40] • Chung-Sheng Li, PwC, United States [32] • Piotr Lipiński, Technical University of Lodz, Poland [93] • Jinwei Liu, Florida A&M University, United States [80] • Alessandra Lumini, University of Bologna, Italy [101] • Rashid Mehmood, King Abdulaziz University, Saudi Arabia [90] • Vincenzo Moscato, University of Naples "Federico II", Italia [98] • Thomas Moser, St. Pölten University of Applied Sciences, Austria [26] • Ranesh Kumar Naha, University of Tasmania, Australia [100] • Stamatios Papadakis, University of Crete, Greece [79] • Michael M. Resch, HLRS, University of Stuttgart, Germany [76] • Nina Rizun, Gdańsk University of Technology, Poland [149] • Abdel-Badeeh M. Salem, Ain Shams University, Egypt [15] • Demetrios Sampson, University of Piraeus, Greece [111] • Antonio Sarasa Cabezuelo, Universidad Complutense de Madrid, Spain [29] • Prem Kumar Singh, Gandhi Institute of Technology and Management, India [132] • Daniel Thalmann, Swiss Federal Institute of Technology in Lausanne, Switzerland…”