Journal of Textile Research ›› 2020, Vol. 41 ›› Issue (07): 78-87.doi: 10.13475/j.fzxb.20190800210

• Textile Engineering • Previous Articles     Next Articles

Task allocation of handling robot in textile workshop based on multi-agent game theory

LI Xun1(), NAN Kaikai1, ZHAO Zhengfan2, WANG Xiaohua1, JING Junfeng1   

  1. 1. School of Electronics and Information, Xi'an Polytechnic University, Xi'an, Shaanxi 710048, China
    2. The Fifth Electronics Research Institute, Ministry of Industry and Information Technology, Guangzhou, Guangdong 510610, China
  • Received:2019-08-02 Revised:2020-01-21 Online:2020-07-15 Published:2020-07-23

Abstract:

A distributed autonomous decision-making framework was proposed based on multi-agent game theory. The framework is used to solve the problems of handling robot in the process of intelligent textile production and processing, which are large-scale and complex dynamic task allocation problems. To start with, the task model was established according to the actual task environment of textile production. Taking into account of the task distance and time priority, the target utility function of the agent was then used as the policy selection basis, and the equilibrium theory of the game was introduced to solve the problem. Eventually, the decision framework was verified by experiments. The experimental results show that the global optimal solution of the task allocation in this decision framework can be better achieved in comparison to the similar distributed task allocation algorithms. In summary, the proposed algorithm has high scalability, good robustness, and convergence performance. Furthermore, the proposed algorithm has excellent performance for dynamic task allocation.

Key words: multi-agent, handling robot, task allocation, textile workshop, game theory

CLC Number: 

  • TP24

Fig.1

Process flow chart of combing workshop"

Fig.2

Abstract description and simplified schematic of textile workshop production task. (a)Combing workshop; (b) Machine distribution in combing workshop; (c) Simplified task abstraction diagram of workshop"

Fig.3

Algorithm flow chart"

Fig.4

Iterative completion process of task allocation. (a) Iteration 79th; (b) Iteration 139th;(c) Iteration 189th; (d) Iteration 331th;(e) Iteration 597th; (f) Iteration 682th;(g) Iteration 771th; (h) Iteration 804th"

Fig.5

Results of the same quantity of agents in different task quantities"

Tab.1

Iterative performance results of algorithms under different order of magnitude m and n"

m 迭代次数
n=4 n=5 n=6 n=7 n=8
10 14 13 14 12 14
15 23 26 25 23 24
20 38 41 38 38 43
25 55 57 53 49 46
30 68 70 63 72 67
35 73 88 67 85 79
40 89 97 99 94 83
45 107 104 103 98 109
50 112 122 111 122 117
55 124 125 141 134 129
60 158 146 147 150 135
65 166 149 167 164 148
70 166 175 174 165 158
75 168 163 175 180 180
80 178 183 206 189 173
85 185 203 216 207 197
90 216 224 224 214 221
95 223 245 232 221 232
100 223 231 232 243 245
105 233 276 251 258 273
110 251 261 277 263 280
115 236 292 301 284 303
120 247 285 307 302 319
125 · 295 309 306 342
130 · 331 311 314 305
135 · · 329 334 328

Fig.6

Task allocation income of three different methods"

Fig.7

System benefits in dynamic task change"

Fig.8

Task allocation results under different communication network strength. (a) Strong communication;(b) Weak communication"

Tab.2

Experimental results of strong communication network connection"

智能体数 100次完成任务平均时间/s
PSO 市场法 博弈论
20
25
30
35
40
2.35
2.43
2.68
2.76
3.05
1.53
1.59
1.67
1.73
1.85
0.72
0.85
0.91
0.94
0.96

Tab.3

Test results of weak communication network connection with 30% communication failure"

智能体数 100次完成任务平均时间/s
PSO 市场法 博弈论
20
25
30
35
40
2.73
2.86
2.98
3.18
3.27
2.63
3.07
3.15
3.34
3.58
0.98
1.04
1.16
1.24
1.26

Fig.9

Task allocation experiments under different conditions. (a) Allocation of efficiency in different situations;(b) Isometric map for allocation efficiency"

[1] 曹鹏飞, 郝矿荣, 丁永生. 面向多机器人动态任务分配的事件驱动免疫网络算法[J]. 智能系统学报, 2018,13(6):952-958.
CAO Pengfei, HAO Kuangrong, DING Yongsheng. Event-driven immune network algorithm for multi-robot dynamic task allocation[J]. CAAI Transactions on Intelligent Systems, 2018,13(6):952-958.
[2] 李珣, 李林鹏, 南恺恺, 等. 智能家居移动机器人的人脸识别方法[J]. 西安工程大学学报, 2020,34(1):61-66.
LI Xun, LI Linpeng, NAN Kaikai, et al. Face recognition method of smart home mobile robot[J]. Journal of Xi'an Polytechnic University, 2020,34(1):61-66.
[3] 梁星星, 马扬, 冯旸赫, 等. 面向多旅行商问题的多目标模拟退火算法研究[J]. 南京师大学报(自然科学版), 2017,40(3):80-86.
LIANG Xingxing, MA Yang, FENG Yanghe, et al. Research on multi-objective simulated annealing algorithm for multi-traveling salesman problem[J]. Journal of Nanjing Normal University (Natural Science Edition), 2017,40(3):80-86.
[4] 万路军, 姚佩阳, 税冬东, 等. 多编组任务分配动态优化模型及IVFSA算法求解[J]. 电光与控制, 2014,21(5):43-49,57.
WAN Lujun, YAO Peiyang, SHUI Dongdong, et al. Dynamic task allocation methods in multiple groups using IVFSA[J]. Electronics Optics & Control, 2014,21(5):43-49,57.
[5] TANG F, PARKER L E. A complete methodology for generating multi-robot task solutions using asymtred and market-based task allocation[C] // International Conference on Robotics & Automation. Roma: IEEE, 2007: 108-113.
[6] LEE D H, ZAHEER S A, HAN J H, et al. Competency adjustment and workload balancing framework in multi-robot task allocation[J]. International Journal of Advanced Robotic Systems, 2018,15(6):17-23.
[7] LUO L, CHAKRABORTY N, SYCARA K. Provably-good distributed algorithm for constrained multi-robot task assignment for grouped tasks[J]. IEEE Transactions on Robotics, 2015,31(1):19-30.
[8] 段俊花, 朱怡安, 黄姝娟, 等. 多模态融合的多机器人任务分配算法研究[J]. 西北工业大学学报, 2013,31(6):974-978.
DUAN Junhua, ZHU Yian, HUANG Shujuan, et al. Multi-robot task allocation algorithm based on multi-modality synjournal[J]. Journal of Northwestern Polytechnical University, 2013,31(6):974-978.
[9] 齐心跃, 田彦涛, 杨茂, 等. 基于市场机制的多机器人救火任务分配策略[J]. 吉林大学学报(信息科学版), 2009,27(5):506-513.
QI Xinyue, TIAN Yantao, YANG Mao, et al. Market based multi-robot task allocation for fire disaster response[J]. Journal of Jilin University (Information Science Edition), 2009,27(5):506-513.
[10] 王皓, 曹健. 分布式环境下面向复杂任务的Agent联盟构建[J]. 计算机工程, 2013,39(12):216-222.
WANG Hao, CAO Jian. Agent coalition formation for complex task under distributed environment[J]. Computer Engineering, 2013,39(12):216-222.
[11] 秦新立, 宗群, 李晓瑜, 等. 基于改进蚁群算法的多机器人任务分配[J]. 空间控制技术与应用, 2018,44(5):55-59.
QIN Xinli, ZONG Qun, LI Xiaoyu, et al. Task allocation of multi-robot based on improved ant colony algorithm[J]. Aerospace Control and Application, 2018,44(5):55-59.
[12] 刘淑华, 张嵛, 吴洪岩, 等. 基于群体智能的多机器人任务分配[J]. 吉林大学学报(工学版), 2010,40(1):123-129.
LIU Shuhua, ZHANG Yu, WU Hongyan, et al. Multi-robot task allocation based on swarm intelligence[J]. Journal of Jilin University (Engineering and Technology Edition), 2010,40(1):123-129.
[13] FANG B F, GUO X P, WANG Z J, et al. Collaborative task assignment of interconnected, affective robots towards autonomous healthcare assistant[J]. Future Generation Computer Systems, 2019,92:241-251.
doi: 10.1016/j.future.2018.09.069
[14] 刘小梅, 田彦涛, 杨茂. 基于博弈论的多机器人任务分配算法[J]. 吉林大学学报(信息科学版), 2010,28(3):256-263.
LIU Xiaomei, TIAN Yantao, YANG Mao. Game theory based multi-robot task allocation algorithm[J]. Journal of Jilin University (Information Science Edition), 2010,28(3):256-263.
[15] GERKEY B P. On multi-robot task allocation[J]. British Journal of Health Psychology, 2003,13(4):659-681.
[16] 罗云峰. 博弈论教程[M]. 北京: 清华大学出版社,北京交通大学出版社, 2007: 43-56.
LUO Yunfeng. Course of game theory [M]. Beijing: Tsinghua University Press, Beijing Jiaotong University Press, 2007: 43-56.
[17] 黎萍, 杨宜民. 基于博弈论的多机器人系统任务分配算法[J]. 计算机应用研究, 2013,30(2):392-395.
LI Ping, YANG Yimin. Game theory based task allocation algorithm for multi-robot systems[J]. Application Research of Computers, 2013,30(2):392-395.
[1] ZHANG Gefu;XU Qi;SONG Xinping. Apparel supply chain generalized quick response system based on business intelligence [J]. JOURNAL OF TEXTILE RESEARCH, 2008, 29(12): 126-130.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!