基于三维基因调控网络的智能机器人群体聚合与控制方法  

Method of Swarm Aggregation and Control for Intelligent Robot Based on Three-dimensional Gene Regulatory Network

作　　者：范衠 马培立 朱贵杰 谢敏冲[1] 陈添善 谢飞 石泽 包卫东 朱晓敏[3] Fan Zhun;Ma Peili;Zhu Guijie;Xie Minchong;Chen Tianshan;Xie Fei;Shi Ze;Bao Weidong;Zhu Xiaomin(College of Engineering,Shantou University,Shantou 515063,China;Key Lab of Digital Signal and Image Processing of Guangdong Province,Shantou University,Shantou 515063,China;College of Systems Engineering,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]汕头大学工学院,广东汕头515063 [2]汕头大学广东省数字信号与图像处理技术重点实验室,广东汕头515063 [3]国防科技大学系统工程学院,湖南长沙410073

出　　处：《南京师范大学学报（工程技术版）》2022年第1期9-15,共7页Journal of Nanjing Normal University(Engineering and Technology Edition)

基　　金：中央军委科技委基础研究项目(18-163-11-ZT-003-008-02);中央军委科技委基础研究项目(193-A14-226-01-01)。

摘　　要：针对传统的基因调控网络模型会导致机器人群体聚合形态在三维空间中不具备泛化性的问题,提出一种基于三维基因调控网络的智能机器人群体聚合与控制方法,并针对集群围捕任务测试了该方法在三维空间复杂场景下的表现.在此基础上使用V-rep平台来模拟真实场景,验证了在加入物理特性后该模型的效能.仿真结果表明,该方法在复杂场景下具有良好的表现.To address the problem that the traditional gene regulatory network(GRN)model could not generate suitable swarm aggregation morphology patterns in three-dimensional space, an aggregation and control method of swarm intelligent robot based on 3 D GRN is proposed. Then, the performance of the method is tested in three-dimensional complex scenes in entrapping task. Furthermore, the V-rep platform is used to simulate real scenarios and verify the efficacy of the model when the environment is added to the physics engine. Simulation results show that the proposed method has good performance and is robust under complex scenarios.

关 键 词：群体智能机器人 基因调控网络 三维空间 群体聚合形态 分布式围捕 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]