Design of Robust Behavior Tree Control Architecture for Agents in Dynamic Task Environment

doi:10.16182/j.issn1004731x.joss.24-0584

Abstract

Abstract:

In recent years, the environment in which agents perform tasks has become more open and dynamic, which puts forward higher requirements for the robustness of task planning and behavior scheduling of agents. As a classic behavior control architecture, behavior tree has the characteristics of modularity, behavior parameterization, and structure of both plan representation and reaction, which can effectively support the behavior representation, decision making and scheduling of agents. Based on the hybrid behavior strategy, this paper proposes a robust behavior tree control architecture for dynamic task environment to realize the prudent decision-making and reactive control of agents. The robust behavior tree control architecture combines the prudent planning algorithm and reactive rules of the agent. A behavior tree code framework of the architecture is accordingly designed, and the planning subtree and the Loopnode are customized to support the fast implementation of the behavior tree to complete the switch between planning and reaction within the tree, which supports users to implement behavior tree quickly and standardly based on the customized structure. By the modeling and simulating of the agent object in a typical attack and defense game case, the paper verifies the rationality of the proposed behavior tree control architecture. Compared with the classical reactive behavior tree strategy, the robust behavior tree can flexibly switch between execution of the plan and reactive strategies, improve the blue agent's penetration win rate to 90% in typical scenarios, shorten task execution time by 24.88%, and improve the effectiveness of agent behavior strategy and modeling efficiency.

Key words: dynamic environment, behavior tree control architecture, hybrid behavior decision, node customization, path planning

CLC Number:

TP391.9

Wang Qiwei, Zhang Qi, Yang Shuo, Peng Yong. Design of Robust Behavior Tree Control Architecture for Agents in Dynamic Task Environment[J]. Journal of System Simulation, 2025, 37(1): 54-65.

Figures/Tables 21

Fig. 1

Fig. 2

Fig. 3

Table 1

Fig. 4

Fig. 5

Fig. 6

Table 2

Fig. 7

Fig. 8

Table 3

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Fig. 13

Fig. 14

Table 4

Fig. 15

Fig. 16

Table 5

References 18

1	Luo Fanming, Jiang Shengyi, Yu Yang, et al. Adapt to Environment Sudden Changes by Learning a Context Sensitive Policy[C]//Thirty-Sixth AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI Press, 2022: 7637-7646.
2	Fozilov Khusniddin, Colan Jacinto, Sekiyama Kosuke, et al. Toward Autonomous Robotic Minimally Invasive Surgery: A Hybrid Framework Combining Task-motion Planning and Dynamic Behavior Trees[J]. IEEE Access, 2023, 11: 91206-91224.
3	伍文迪. 基于行为树的群体机器人协同技术研究[D]. 长沙: 国防科技大学, 2020.
	Wu Wendi. Research on Collaborative Technology of Swarm Robots Based on Behavior Tree[D]. Changsha: National University of Defense Technology, 2020.
4	Li Ning, Jiang Hao, Li Chunpeng, et al. Towards Adaptive Behavior Trees for Robot Task Planning[C]//2022 China Automation Congress (CAC). Piscataway: IEEE, 2022: 6720-6725.
5	Ahmad Faseeh, Mayr Matthias, Krueger Volker. Learning to Adapt the Parameters of Behavior Trees and Motion Generators (BTMGs) to Task Variations[C]//2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2023: 10133-10140.
6	David Cáceres Domínguez, Iannotta Marco, Stork Johannes A, et al. A Stack-of-tasks Approach Combined with Behavior Trees: A New Framework for Robot Control[J]. IEEE Robotics and Automation Letters, 2022, 7(4): 12110-12117.
7	Colledanchise Michele, Almeida Diogo, Ögren Petter. Towards Blended Reactive Planning and Acting Using Behavior Trees[C]//2019 International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2019: 8839-8845.
8	钟灿灿, 陈万米. 移动机器人的混合式路径规划算法研究[J]. 自动化仪表, 2021, 42(9): 61-66.
	Zhong Cancan, Chen Wanmi. Research on Hybrid Path Planning Algorithm for Mobile Robots[J]. Process Automation Instrumentation, 2021, 42(9): 61-66.
9	华洪. 基于改进A*算法的自主移动机器人路径规划方法研究[D]. 南京: 南京理工大学, 2021.
10	史殿习, 苏雅倩文, 李宁, 等. 基于行为树调度的多无人机未知室内空间探索方法[J]. 计算机科学, 2022, 49(增2): 71-81.
	Shi Dianxi, Su Yaqianwen, Li Ning, et al. Multi-UAV Cooperative Exploring for Large Unknown Indoor Environment Based on Behavior Tree[J]. Computer Science, 2022, 49(S2): 71-81.
11	张琪. 学习驱动的CGF决策行为建模方法研究[D]. 长沙: 国防科技大学, 2018.
	Zhang Qi. Research on Learning Driven Behavior Modeling Methods for Decision Making of Computer Generated Forces(CGFs)[D]. Changsha: National University of Defense Technology, 2018.
12	冷静. 面向实时避碰的无人水面机器人在线路径规划方法[D]. 北京: 中国科学院大学, 2014.
	Leng Jing. Online Path Planning for Unmanned Surface Vehicles for Real-time Obstacle Avoidance[D]. Beijing: University of Chinese Academy of Sciences, 2014.
13	Gustavsson Oscar, Iovino Matteo, Styrud Jonathan, et al. Combining Context Awareness and Planning to Learn Behavior Trees from Demonstration[C]//2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). Piscataway: IEEE, 2022: 1153-1160.
14	Leonardo Henrique Moreira, Célia Ghedini Ralha. Method for Evaluating Plan Recovery Strategies in Dynamic Multi-agent Environments[J]. Journal of Experimental & Theoretical Artificial Intelligence, 2023, 35(8): 1225-1249.
15	Pezzato Corrado, Carlos Hernández Corbato, Bonhof Stefan, et al. Active Inference and Behavior Trees for Reactive Action Planning and Execution in Robotics[J]. IEEE Transactions on Robotics, 2023, 39(2): 1050-1069.
16	Ruiz-Celada Oriol, Verma Parikshit, Diab M, et al. Automating Adaptive Execution Behaviors for Robot Manipulation[J]. IEEE Access, 2022, 10: 123489-123497.
17	唐昀超, 祁少军, 朱立学, 等. 移动机器人避障运动研究[J]. 系统仿真学报, 2024, 36(1): 1-26.
	Tang Yunchao, Qi Shaojun, Zhu Lixue, et al. Obstacle Avoidance Motion in Mobile Robotics[J]. Journal of System Simulation, 2024, 36(1): 1-26.
18	柳佳. 移动机器人路径规划和避障算法研究[D]. 武汉: 武汉理工大学, 2022.
	Liu Jia. Research on Path Planning and Obstacle Avoidance Algorithm of Mobile Robot[D]. Wuhan: Wuhan University of Technology, 2022.

参数名称	参数大小	参数类型	含义
红蓝方运动速度/ (m/s)	25	智能体状态参数	双方智能体移动速度
智能体最大感知范围/ m	30	智能体状态参数	该范围内对红方进行反应
地图面积/m²	490×490	环境参数	智能体运动的范围参考
静态障碍物面积/ m²	20×20	环境参数	每个障碍物块的大小
目标位置	(20，20)	目标参数	目标的中心坐标
仿真总时长/s	300	时间参数	限制单次实验的最大时长

数据名称	反应树数值	健壮树数值
单回合平均运行时长/s	22.89	18.33
运行至最大时间回合数	5	0
蓝方胜利回合数	40	45

[1]	Yu Yiran, Lai Huicheng, Gao Guxue, Zhang Guo, Peng Wangyinan, Yang Longfei, Huang Junhao. Optimization Method for Multi Agricultural Machinery Collaborative Operation Based on Genetic Algorithm and A * Algorithm [J]. Journal of System Simulation, 2025, 37(9): 2397-2408.
[2]	Ni Peilong, Mao Pengjun, Wang Ning, Yang Mengjie. Robot Path Planning Based on Improved A-DDQN Algorithm [J]. Journal of System Simulation, 2025, 37(9): 2420-2430.
[3]	Zhang Kaixiang, Mao Jianlin, Wang Niya, Xu Zhihao. Multi-robot Hierarchical Collaborative k-robust Path Planning for Path Interference [J]. Journal of System Simulation, 2025, 37(8): 2074-2088.
[4]	Wan Yuhang, Zhu Zilu, Zhong Chunfu, Liu Yongkui, Lin Tingyu, Zhang Lin. Dynamic Path Planning for Robotic Arms Based on an Improved PPO Algorithm [J]. Journal of System Simulation, 2025, 37(6): 1462-1473.
[5]	Ye Chen, Shao Peng, Zhang Shaoping, Li Wenting, Zhou Tengming. Enhanced Artificial Gorilla Algorithm for Mobile Robot Path Planning [J]. Journal of System Simulation, 2025, 37(6): 1474-1485.
[6]	Yuan Jianchao, Yang Shuo, Zhang Qi, Li Ge. Research on Behavior Control Techniques for Autonomous Vehicles Based on Parallel Behavior Tree Architecture [J]. Journal of System Simulation, 2025, 37(6): 1542-1554.
[7]	Zhang Yan, Li Binghua, Huo Tao, Liu Rong. Research on Robot Dynamic Obstacle Avoidance Method Based on Improved A* and Dynamic Window Algorithm [J]. Journal of System Simulation, 2025, 37(6): 1555-1564.
[8]	Zhou Xiaohui, Li Yanqiang, Wang Yong, Zhao Decai, Yang Xiaoyao. Robot Path Planning Based on Ant Colony Algorithm with Dual Heuristic Information [J]. Journal of System Simulation, 2025, 37(5): 1280-1289.
[9]	Yu Die, Bao Baizhong, Si Yan, Duan Jian, Zhan Xiaobin, Shi Tielin. Mobile Robot Path Planning Based on Search-step Optimized A* Algorithm [J]. Journal of System Simulation, 2025, 37(4): 1041-1050.
[10]	Zhang Sen, Dai Qiangqiang. UAV Path Planning Based on Improved Deep Deterministic Policy Gradients [J]. Journal of System Simulation, 2025, 37(4): 875-881.
[11]	He Zhigang, Li Dayan, Wang Niya, Mao Jianlin, Wang Ning. A Multi-robot Collaborative Path Planning Algorithm with Chain Working Mode [J]. Journal of System Simulation, 2025, 37(4): 953-967.
[12]	Lin Guijuan, Li Zihan, Wang Yu. Research on Improved A* Algorithm Path Planning Based on Global Key Point Extraction [J]. Journal of System Simulation, 2025, 37(3): 667-678.
[13]	Bai Yuxin, Chen Zhenya, Shi Ruitao, Su Weitao, Ma Zhuoqiang, Yang Shangjin. Research on Robot Path Planning Based on Improved Harris Hawks Algorithm [J]. Journal of System Simulation, 2025, 37(3): 742-752.
[14]	Jiang Limei, Chen Xinwei. Visual SLAM Algorithm Based on Feature Point Selection in Dynamic Scenes [J]. Journal of System Simulation, 2025, 37(3): 753-762.
[15]	Jin Xu, Mo Yuanbin. Multi-strategy Hybrid Mountain Gazelle Optimizer for Robot Path Planning [J]. Journal of System Simulation, 2025, 37(3): 803-821.