Uncovering Resilient Actions of Robotic Technology with Data Interpretation Trajectories Using Knowledge Representation Procedures

• Published in: Security and communication networks Vol. 2023; pp. 1 - 8
• Main Authors: Teekaraman, Yuvaraja, Kirpichnikova, Irina, Manoharan, Hariprasath, Kuppusamy, Ramya, Radhakrishnan, Arun
• Format: Journal Article
• Language: English
• Published: London Hindawi 2023; John Wiley & Sons, Inc
• Subjects: Classification; Collaboration; Design; Failure times; Knowledge representation; Learning; Mathematical functions; Methods; Multiple robots; Path planning; Robot dynamics; Robotics; Robots; Training; Trajectories
• ISSN: 1939-0114; 1939-0122
• DOI: 10.1155/2023/7419259

This article highlights the importance of learning models which prevent the resilient attack of robotic technology with a subset of trajectories. Many complement models are introduced in the field of path planning robots without any knowledge of representation procedures, so robotic data are subject to different attacks from several users. During such attacks, the data will be misplaced and commands specified to robots will be disorganized so a new training data set has to be incorporated which is a difficult task. Therefore, to prevent probability of data failure time-dependent binary probability prototypes are introduced with low training data. Furthermore, a regularized boosting procedure (RBP) has been applied with different weights to switch multiple robots with discrete knowledge representation. Then a high space block is incorporated for maximizing coverage areas during loss functions and this is implicit as an innovative technique as compared with existing procedures. To validate the effectiveness of proposed learning techniques in robots, four scenarios are considered which include accuracy and success rate of detection. Subsequently, the outcomes prove that the robotic path with learning models are highly effective for an average percentile of 86% as compared to conventional techniques.