Multi-Objective Rule System Based Control Model with Tunable Parameters for Swarm Robotic Control in Confined Environment  

作　　者：Yuan Wang Lining Xing Junde Wang Tao Xie Lidong Chen 

机构地区：[1]Beijing Institute of Advanced Studies,College of Advanced Interdisciplinary Studies,National University of Defense Technology,Beijing 100084,China [2]Key Laboratory of Collaborative Intelligence Systems,Ministry of Education,Xidian University,Xi’an 710071,China

出　　处：《Complex System Modeling and Simulation》2024年第1期33-49,共17页复杂系统建模与仿真（英文）

基　　金：supported by the Hunan Provincial Natural Science Foundation of China(No.2023JJ40686).

摘　　要：Enhancing the adaptability of Unmanned Aerial Vehicle(UAV)swarm control models to cope with different complex working scenarios is an important issue in this research field.To achieve this goal,control model with tunable parameters is a widely adopted approach.In this article,an improved UAV swarm control model with tunable parameters namely Multi-Objective O-Flocking(MO O-Flocking)is proposed.The MO O-Flocking model is a combination of a multi rule control system and a virtual-physical-law based control model with tunable parameters.To achieve multi-objective parameter tuning,a multi-objective parameter tuning method namely Improved Strength Pareto Evolutionary Algorithm 2(ISPEA2)is designed.Simulation experiment scenarios include six target orientation scenarios with different kinds of objectives.Experimental results show that both the ISPEA2 algorithm and MO O-Flocking control model have good performance in their experiment scenarios.

关 键 词：swarm robotics flocking model parameter tuning multi-objective optimization HEURISTICS 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]