This article addresses the problem of managing multi-agent robotic systems using artificial intelligence technologies. A hybrid model combining the Vision-Language-Action (VLA) architecture with the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm is proposed for the synergetic control of a group of robots. The model is built on the Centralized Training with Decentralized Execution (CTDE) principle, with a Social-Force component incorporated into the reward function to automatically maintain a safe distance between agents. Experiments were conducted in the NVIDIA Isaac Sim environment using a dataset of over 10,000 trajectories and scenarios involving 4 to 16 agents. The results show a 90% task success rate, a 0.5% collision probability, and 89% energy efficiency, along with a significant reduction in communication load compared to a rule-based method and standard MADDPG. These findings confirm that integrating VLA models with multi-agent reinforcement learning improves the adaptability, fault tolerance, and collective decision-making capability of robotic swarms, opening prospects for application in agriculture, logistics, and smart-city infrastructure.
| Mualliflar | A.T. Hamiyev |
|---|---|
| Jurnal | Кимёвий технология. Назорат ва бошқарув |
| Nashr sanasi | 2026-06-29 |
| Jild | 2026 |
| Son | 3 |
| Betlar | 51-57 |
| Til | en |
| DOI | 10.59048/2181-1105.1809 |
DOI: 10.59048/2181-1105.1809 · Maqolaning asl sahifasi
This research addresses the critical problem of controlling complex robotic systems characterized by parametric uncertainty and external disturbances. Within the scope of this work, a novel adaptive control model was…
The widespread use of AI systems in important infrastructure, it's very important that algorithmic decision-making processes are clear and easy to understand. Explainable Artificial Intelligence (XAI) has emerged as a…
This article is devoted to the issues of planning the actions of robots based on intelligent technologies. One of the main issues in the intelligent planning of robot manipulators' movements is to determine the…
This paper addresses the growing need for sustainable energy solutions by analyzing global solar energy trends and the barriers limiting renewable energy deployment in Uzbekistan, despite national goals such as the…
This article examines the architecture of an information system that supports information processing and clinical decision-making in the field of medicine. The system is described using a multilayer functional model…
This article is devoted to the modeling of a mechatronic module based on linear motion actuator, including the processes of modeling the dynamic, kinematic, and control parameters of the mechatronic module, as well as…
A method for synthesizing a fuzzy compensating element from the static characteristic of a nonlinear plant is presented. The method transforms the characteristic into a rotated coordinate system, identifies zero…
This paper presents a comprehensive study on the development of a mathematical model and image processing algorithms for artificial intelligence-based technical vision systems. The research focuses on analyzing the…
Vision-based sensors constitute a cornerstone of contemporary automation, robotics, and intelligent transportation systems, where their reliability directly determines operational safety and efficiency. Conventional…
This article analyzes the problems of intelligent control of the process of low-temperature separation (LTS) of natural gas and modern approaches to solving them. Since the process complexity of gas separation at low…