Role-based Bayesian decision framework for autonomous unmanned systems

doi:10.23919/JSEE.2023.000114

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (6): 1397-1408.doi: 10.23919/JSEE.2023.000114

• AUTONOMOUS DECISION AND COOPERATIVE CONTROL OF UAV SWARMS • Previous Articles Next Articles

Role-based Bayesian decision framework for autonomous unmanned systems

Weijian PANG¹^,²(), Xinyi MA³^,*(), Xueming LIANG¹(), Xiaogang LIU¹(), Erwa DONG¹()

¹ Beijing Aeronautical Engineering Research Center, Beijing 100076, China
² Academy of Military Sciences, Beijing 100091, China
³ Air Forces Command College of PLA, Beijing 100097, China

Received:2022-09-30 Online:2023-12-18 Published:2023-12-29
Contact: Xinyi MA E-mail:pangweijian2013@163.com;cynthiacatmm@163.com;mailme_6688@126.com;lxg93215@163.com;d1140431964@163.com
About author:
PANG Weijian was born in 1986. He received his B.S. degree in radar engineering and M.S. degree in electronic science and technology from Air Force Engineering University, Xi’an, China, in 2009 and 2014 respectively. He received his doctorate in military operational research from Academy of Military Sciences in 2022. He is a researcher of Beijing Aeronautical Engineering Research Center. His research interests are military operational research and theory and technology of military application of intelligent unmanned systems. E-mail: pangweijian2013@163.com

MA Xinyi was born in 1984. She received her B.S. degree in computer science and technology and M.S. degree in software engineering from Beihang University, Beijing, China, in 2006 and 2010 respectively. She received her doctorate in military operational research from Academy of Military Sciences in 2022. She is a lecturer in Air Forces Command College of PLA. Her research interests are military operational research and causal inference in military applications. E-mail: cynthiacatmm@163.com

LIANG Xueming was born in 1972. He received his B.S. and M.S. degrees in aircraft guidance control and simulation from Air Force Engineering University, Xi’an, China, in 1993 and 1996 respectively. He received his Ph.D. degree in control science and engineering from Tsinghua University in 2010. He is a researcher in Beijing Aeronautical Engineering Research Center. His research interest is airborne weapon technology. E-mail: mailme_6688@126.com

LIU Xiaogang was born in 1974. He received his B.S. degree in weapon system and M.S. degree in system simulation from Air Force Engineering University, Xi ’an, China, in 1997 and 2002 respectively. He received his Ph.D. degree in navigation guidance and control from Northwestern Polytechnical University in 2006. He is a researcher of Beijing Aeronautical Engineering Research Center. His research interests are military operational research, theory, system simulation. E-mail: lxg93215@163.com

DONG Erwa was born in 1994. He received his doctorate in weapon science and technology from Beijing Institute of Technology in 2022. He is a researcher of Beijing Aviation Engineering Research Center. His main research direction is military application of intelligent system. E-mail: d1140431964@163.com
Supported by:
This work was supported by the Military Science Postgraduate Project of PLA (JY2020B006).

Abstract

Abstract:

In the process of performing a task, autonomous unmanned systems face the problem of scene changing, which requires the ability of real-time decision-making under dynamically changing scenes. Therefore, taking the unmanned system coordinative region control operation as an example, this paper combines knowledge representation with probabilistic decision-making and proposes a role-based Bayesian decision model for autonomous unmanned systems that integrates scene cognition and individual preferences. Firstly, according to utility value decision theory, the role-based utility value decision model is proposed to realize task coordination according to the preference of the role that individual is assigned. Then, multi-entity Bayesian network is introduced for situation assessment, by which scenes and their uncertainty related to the operation are semantically described, so that the unmanned systems can conduct situation awareness in a set of scenes with uncertainty. Finally, the effectiveness of the proposed method is verified in a virtual task scenario. This research has important reference value for realizing scene cognition, improving cooperative decision-making ability under dynamic scenes, and achieving swarm level autonomy of unmanned systems.

Key words: autonomous unmanned systems, multi-entity Bayesian network (MEBN), situation awareness, decision modeling

Weijian PANG, Xinyi MA, Xueming LIANG, Xiaogang LIU, Erwa DONG. Role-based Bayesian decision framework for autonomous unmanned systems[J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1397-1408.

Figures/Tables 18

Table 1

Fig 1

Fig 2

Table 2

Fig 3

Fig 4

Fig 5

Fig 6

Table 3

Table 4

Fig 7

Fig 8

Fig 9

Fig 10

Fig 11

Fig 12

Table 5

Table 6

References 22

1	OLIVARES-ALARCOS A, BESSLER D, KHAMIS A, et al A review and comparison of ontology-based approaches to robot autonomy. The Knowledge Engineering Review, 2019, 34, 29. doi: 10.1017/S0269888919000237
2	ARORA A, FIORINO H, PELLIER D, et al A review of learning planning action models. The Knowledge Engineering Review, 2018, 33, 24. doi: 10.1017/S0269888918000279
3	FINN S G, MEDARD M, BARRY R A. A novel approach to automatic protection switching using tree. Proc. of the International Conference on Communications, 1997: 272−276.
4	WANG Y X, LIU M, PU J S, et al. Semantical obstacle representation model for fast UAV path planning. Proc. of the 2nd Asia-Pacific Conference on Intelligent Robot Systems, 2017: 180−184.
5	PANG W J, LI H, HUANG Q, et al Review on ontology-based task planning for unmanned systems. Systems Engineering and Electronics, 2021, 44 (3): 908- 920.
6	WU C G, NA Y L. Knowledge graph modeling and intelligent reasoning techniques. Beijing: Chemical Industrial Press, 2021. (in Chinese)
7	YAO H F, WANG H J, WANG Y UUV autonomous decision-making method based on dynamic influence diagram. Complexity, 2020, 2020, 8565106.
8	ERNEST N, COHEN K, KIVELEVITCH E, et al Genetic fuzzy trees and their application towards autonomous training and control of a squadron of unmanned combat aerial vehicles. Unmanned Systems, 2015, 3 (3): 185- 204. doi: 10.1142/S2301385015500120
9	LASKEY K B MEBN: a language for first-order Bayesian knowledge bases. Artificial Intelligence, 2008, 172 (2/3): 140- 178. doi: 10.1016/j.artint.2007.09.006
10	LI X, SONIA B, TAMARA M W, et al SWARMs ontology: a common information model for the cooperation of underwater robots. Sensors, 2017, 17 (3): 569- 588. doi: 10.3390/s17030569
11	PANG W J, LI H, MA X Y, et al A semantic-centered cloud control framework for autonomous unmanned system. Journal of Systems Engineering and Electronics, 2022, 33 (4): 771- 784. doi: 10.23919/JSEE.2022.000077
12	PAULO C C. Bayesian semantics for the semantic web. Washington D.C.: George Mason University, 2005.
13	CARVALHO R N, COSTA P C G, LASKEY K B, et al. PROGNOS: predictive situational awareness with probabilistic ontologies. Proc. of the 13th International Conference on Information Fusion, 2010. DOI:10.1109/ICIF.2010.5711970.
14	PARK C Y, LASKEY K B, COSTA P C G, et al. Multi-entity Bayesian ntworks learning for hybrid variables in situation awareness. Proc. of the 16th International Conference on Information Fusion, 2013: 1894−1901.
15	PARK C Y, LASKEY K B MEBN-RM: a mapping between multi-entity Bayesian network and relational model. Applied Sciences, 2019, 9 (9): 1743. doi: 10.3390/app9091743
16	PARK C Y, LASKEY K B, COSTA P C G, et al. Predictive situation awareness reference model using multi-entity Bayesian networks. Proc. of the 17th International Conference on Information Fusion, 2014. https://ieeexplore.ieee.org/abstract/document/6916225.
17	PARK C Y, LASKEY K B. Reference model of multi-entity Bayesian networks for predictive situation awareness. https://arxiv.org/abs/1806.02457.
18	PARK C Y. Multi-entity Bayesian networks learning for predictive situation awareness. Commonwealth of Virginia: George Mason University, 2017.
19	SALOTTI J M Bayesian network for the prediction of situation awareness errors. International Journal of Human Factors Modelling and Simulation, 2018, 6 (2/3): 119- 126. doi: 10.1504/IJHFMS.2018.093174
20	LI T, ZHANG W, GAO S, et al. Situation assessment method based on Bayesian network and its application in space battlefield. Proc. of the 2nd International Conference on Computer Engineering, Information Science and Internet Technology, 2017: 547−554.
21	MATSUMOTO S, LASKEY K B, COSTA P C G PR-OWL decision: toward reusable ontology language for decision making under uncertainty. Semantic Technology for Intelligence, Defense, and Security, 2016, (9): 37- 45.
22	WANG S. Research on unmanned combat vehicle intelligent planning technology based on domain knowledge graph. Changsha: National University of Defense Technology, 2019. (in Chinese)

Feature	MEBN	SDG	DBN	GFT	DID
Fuzzy knowledge description capability	√	−	−	√	√
Probability knowledge description capability	√	−	√	√	√
Modeling convenience	√	−	√	−	√
Utility decision	√	−	−	√	−
Formalization	√	√	−	−	√
Modularization	√	−	−	√	√
Knowledge reuse	√	−	−	−	√
Dynamic decision	√	√	√	−	√
Preference description capability	√	−	−	−	−

Symbols	Definition
$R$	A set of prior rules for autonomous decision model
$ r $	The mapping relationship between input and output of decision nodes
$ L $	The serial number of a rule $ r $
$ t $	Time
$ {r}^{L} $	The Lth rule
$ {D}_{t} $	Decision node
$ Pa\left({D}_{t}\right) $	Parent node of the decision node $ {D}_{t} $
$ {\omega }_{Pa\left({D}_{t}\right)} $	Value range of the parent node of decision node $ {D}_{t} $
$ {P}_{r}\left({D}_{t}\|Pa\left({D}_{t}\right)\right) $	Local probability distribution function of decision node D at time t under input from its parent node
$ {p}_{j} $	The probability of the jth decision option
$ E\left(U\left({X}_{t},{D}_{t}\right)\right) $	At time t, the expected utility value of each decision option of decision node D under input X
$ {O}_{t} $	The observed value of the decision system to the environment at time t

Event labels	T0	T1	T2	T3	T4	T5	Description
HASJAM	−	−	−	−	−	TRUE	Find jamming
HASVISIBLE	−	−	−	−	GOOD	−	Visibility
HASENVSTATE	GOOD	−	−	−	−	−	Environment state
HASFIGHTERS	HIGH	LOW	LOW	LOW	LOW	LOW	Enemy’s UGV number
HASFORT	LOW	LOW	LOW	HIGH	HIGH	HIGH	Enemy’s fortifications number
HASUAVSERVICEABILITY	HIGH	−	−	−	−	−	Serviceability rate
HASPIERCINGARMOUR	HIGH	HIGH	LOW	LOW	LOW	LOW	Number of piercing ammunition
HASBLASTARMOUR	HIGH	HIGH	HIGH	HIGH	HIGH	LOW	Number of blasting ammunition
HASUAVENDURACE	HIGH	HIGH	HIGH	HIGH	LOW	LOW	Average sustainability of UAV
HASUGVENDURANCE	HIGH	HIGH	HIGH	HIGH	HIGH	LOW	Average sustainability of UGV
HASTOTALENDURANCE	HIGH	−	−	−	−	−	Sustainability

T0	T1	T2	T3	T4	T5	T6	T7	Description
UAVATTACKED	FALSE	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	UAV is attacked
UGVATTACKED	FALSE	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	UGV is attacked
ENTERCITY	FALSE	TRUE	FALSE	FALSE	FALSE	TRUE	FALSE	Entering city
OPENROAD	TRUE	FALSE	TRUE	TRUE	TRUE	FALSE	TRUE	Open road

Role	High			Low
Role	Search	March	Hide	Search	March	Hide
Guarder	9	−4	−7	3	8	−9
Follower	2	−9	7	−6	9	−3

Role-based Bayesian decision framework for autonomous unmanned systems

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 18

References 22

Related Articles 3

Recommended Articles

Metrics

Comments

[1]	Jun CHEN, Xudong GAO, Jia RONG, Xiaoguang GAO. A situation awareness assessment method based on fuzzy cognitive maps [J]. Journal of Systems Engineering and Electronics, 2022, 33(5): 1108-1122.
[2]	Yunpeng HU, Kebo LI, Yan’gang LIANG, Lei CHEN. Review on strategies of space-based optical space situational awareness [J]. Journal of Systems Engineering and Electronics, 2021, 32(5): 1152-1166.
[3]	Huiyun Zhao, Dongge Zhang, Hui Meng, and Jiuyang Tao. Analytical measurement method for situation elements’ dynamic characteristics#br# [J]. Journal of Systems Engineering and Electronics, 2017, 28(6): 1126-1132.

Time	Guarder			Follower
Time	Search	March	Hide	Search	March	Hide
T0	4.332	5.336	−8.556	−4.224	5.004	−0.78
T1	7.523	−1.048	−7.492	0.032	−4.572	4.54
T2	4.332	5.336	−8.556	4.224	5.004	−0.78
T3	5.592	2.816	−8.136	−2.544	1.224	1.32
T4	4.332	5.336	−8.556	−4.224	5.004	−0.78
T5	8.112	−2.224	−7.296	0.816	−6.336	5.52
T6	4.332	5.336	−8.556	−4.224	5.004	−0.78