Talk · IEEE International Conference on Smart Information Systems and Technologies · May 14, 2025
Decentralized Coordination of Intelligent Robot Swarms
Abzal E. Kyzyrkanov, Sabyrzhan K. Atanov, Shadi Aljawarneh, Назира Турсынова, Zhenis Otarbay, Algys Saltanat
Abstract
This paper presents a decentralized coordination algorithm for intelligent robot swarms that integrates behavior-based control, fuzzy logic for dynamic behavior weighting, and a virtual leader mechanism for scalable formation guidance. The algorithm enables each robot to independently combine three core behaviors—formation keeping, obstacle avoidance, and goal tracking—using weights derived from fuzzy inference based on real-time sensor data. A mathematical formulation of the behavior composition model and velocity control is provided. The system was validated in a Python-based simulation with 16 agents navigating around obstacles while preserving formation. Results demonstrate smooth, collision-free movement with less than 0.5 meters of average deviation from formation targets. Compared to existing methods, the proposed approach offers improved resilience, adaptability, and real-time performance without centralized control.
More by Zhenis Otarbay
- Ocular-correlated signals and decision rules in DTW decoding of motor-imagery EEG: code and resultsZenodo · 2026
- When Deployment Changes a Learned Action: Post-Inference Projection in Offline Multi-Agent Reinforcement LearningAI · 2026
- Robust Offline Multi-Agent Reinforcement Learning for Latency-Aware SDN Path Control in 6G-Oriented Network SoftwarizationTechnologies · 2026 · Citations: 1
- An Exploratory Study of Gender Effects on Pupillary Cognitive Load in Human–Robot InteractionIEEE International Conference on Smart Information Systems and Technologies · 2026