Chenxi Lyu¹, Chen Dong¹, Qiancheng Xiong¹, Yuzhong Chen¹, Qian Weng^1,*, Zhenyi Chen²

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 3371-3391, 2025, DOI:10.32604/cmc.2025.065153 - 03 July 2025

Abstract The rapid advancement of Industry 4.0 has revolutionized manufacturing, shifting production from centralized control to decentralized, intelligent systems. Smart factories are now expected to achieve high adaptability and resource efficiency, particularly in mass customization scenarios where production schedules must accommodate dynamic and personalized demands. To address the challenges of dynamic task allocation, uncertainty, and real-time decision-making, this paper proposes Pathfinder, a deep reinforcement learning-based scheduling framework. Pathfinder models scheduling data through three key matrices: execution time (the time required for a job to complete), completion time (the actual time at which a job is finished),… More >

Guodong Yuan^1,*, Jin Xie²

Journal on Artificial Intelligence, Vol.7, pp. 1-16, 2025, DOI:10.32604/jai.2025.061437 - 14 March 2025

Abstract This paper addresses the problem of access efficiency in multi-robot systems to the monitoring area. A distributed algorithm for multi-robot continuous monitoring, based on the uncertainty of target points, is used to minimize the uncertainty and instantaneous idle time of all target points in the task domain, while maintaining a certain access frequency to the entire task domain at regular time intervals. During monitoring, the robot uses shared information to evaluate the cumulative uncertainty and idle time of the target points, and combines the update list collected from adjacent target points with a utility function More >

Virginijus Baranauskas^1,*, Žydrūnas Jakas¹, Kastytis Kiprijonas Šarkauskas¹, Stanislovas Bartkevičius², Gintaras Dervinis¹, Alma Dervinienė³, Leonas Balaševičius¹, Vidas Raudonis¹, Renaldas Urniežius¹, Jolanta Repšytė¹

Intelligent Automation & Soft Computing, Vol.32, No.3, pp. 1343-1356, 2022, DOI:10.32604/iasc.2022.022288 - 09 December 2021

Abstract The research work presents a collision prediction method of mobile robots. The authors of the work use so-called, virtual cocoons to evaluate the collision criteria of two robots. The idea, mathematical representation of the calculations and experimental simulations are presented in the paper work. A virtual model of the industrial process with moving mobile robots was created. Obstacle avoidance was not solved here. The authors of the article were working on collision avoidance problem solving between moving robots. Theoretical approach presents mathematical calculations and dependences of path angles of mobile robots. Experimental simulations, using the… More >