A Cooperative Hunting Method for Multi-USVs Based on Trajectory Prediction by OR-LSTM

被引：0
作者：
Yu, Jiabin [1 ,2 ]
Chen, Zhihao [1 ,2 ]
Zhao, Zhiyao [1 ,2 ]
Deng, Heng [3 ]
Wu, Jiguang [1 ,2 ]
Xu, Jiping [1 ,2 ]
机构：
[1] Beijing Technol & Business Univ, Sch Comp & Artificial Intelligence, Beijing 100048, Peoples R China
[2] Beijing Technol & Business Univ, Beijing Lab Intelligent Environm Protect, Beijing 100048, Peoples R China
[3] Beijing Univ Technol, Sch Informat Sci & Technol, Beijing 100124, Peoples R China
来源：
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY | 2024年 / 73卷 / 12期
基金：
中国国家自然科学基金;
关键词：
Trajectory; Underactuated surface vessels; Prediction algorithms; Three-dimensional displays; Solid modeling; Long short term memory; Earth; Unmanned surface vessels; trajectory prediction; OR-LSTM network; cooperative hunting; virtual structure method;
D O I：
10.1109/TVT.2024.3432739
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Multi-unmanned surface vessel (USV) cooperative hunting is widely used in dynamic target hunting in the presence of obstacles, due to its high efficiency. This paper proposes a cooperative hunting method for multi-USVs based on trajectory prediction by obstacle relation long short-term memory (OR-LSTM). First, the historical target trajectory is preprocessed by univariate nonlinear regression, and the obstacle information is input to OR-LSTM to predict the trajectory of the target, with improved accuracy and convergence. A bionic-based cooperative hunting strategy is proposed, by which multi-USVs ambush the predicted trajectory of the target by simulating the hunting strategy of lions. When the target is close to the ambush position, the multi-USVs start to hunt it. Two groups of simulation experiments were implemented on the Unity 3D platform to validate the proposed algorithm, which had higher accuracy and faster convergence in target trajectory prediction than the traditional algorithm, and higher efficiency in target hunting.
引用
收藏
页码：18087 / 18101
页数：15
相关论文
共 35 条
  • [1] Yu J.B., Chen Z.H., Zhao Z.Y., Yao P., Xu J.P., A traversal multitarget path planning method for multi-unmanned surface vessels in spacevarying ocean current, Ocean Eng., 278, 1, (2022)
  • [2] Chen Z.H., Zhao Z.Y., Xu J.P., Wang X.Y., Lu Y., Yu J.B., A cooperative huntingmethod formulti-USV based on theA∗algorithm in an environment with obstacles, Sensors, 23, 16, (2023)
  • [3] Xu W.H., Sun M.Y., A self-organized chain for formation method for swarm robots to enclose multiple intruders, Control Theory Appl., 40, 1, pp. 94-102, (2022)
  • [4] Zhang S.Y., Dai S.L., Real-time trajectory generation for haptic feedback manipulators in virtual cockpit systems, J. Comput. Inf. Sci. Eng., 18, 4, pp. 1-11, (2018)
  • [5] Chen J., Xiao R., Lei W., Zhu L., Shi D., Unveiling interpretable key performance indicators in hypoxic response: A system identification approach, IEEE Trans. Ind. Electron., 69, 12, pp. 13676-13685, (2022)
  • [6] Liu J., Shi G., Zhu K., Vessel trajectory prediction model based on AIS sensor data and adaptive chaos differential evolution support vector regression (ACED-SVR), Appl. Sci., 9, (2019)
  • [7] Kavitha M., Rajivkannan A., Hybrid convolutional neural network and long short-term memory approach for facial expression recognition, Intell. Automat. Soft Comput., 35, 1, pp. 1-16, (2022)
  • [8] Shan W.J., Digital streamingmedia distribution and transmission process optimisation based on adaptive recurrent neural network, Connection Sci., 34, 1, pp. 1169-1180, (2022)
  • [9] Xiao H., Et al., UB-LSTM: A trajectory prediction method combined with vehicle behavior recognition, J. Adv. Transp., 1, 1, pp. 1-12, (2020)
  • [10] Wan H., Pan J., Zhen R., Shi Z., Prediction of ship trajectory based on CNN-GRU, J. Guangzhou Maritime Univ., 30, 2, pp. 1-7, (2022)
1234