Research on Underwater Target Localization Algorithm Considering the Uncertainty of Anchor Position
-
摘要: 考虑时钟异步和声波分层效应的影响，该文研究了当测量过程受到未知噪声干扰，且锚节点位置不确定时水下目标节点的定位问题。首先构造了水下节点间飞行时间模型，设计了一种交互式异步通信协议，建立了最小化定位误差的优化目标函数。然后提出了一种基于深度强化学习的水下目标定位算法，并采用层归一化来改进深度神经网络，进一步提高模型的泛化能力。最后，仿真和实验结果验证所提方法的有效性。Abstract: Considering the effects of an asynchronous clock and acoustic stratification, the localization problem of an underwater target node was studied when the measurement process was disrupted by unknown noise and the anchor position was uncertain. The time of flight model between underwater nodes is constructed, an interactive asynchronous communication protocol is designed, and an optimization objective function to minimize the localization error is established. An underwater target localization algorithm based on deep reinforcement learning is proposed, and layer normalization is used to improve the generalization ability of the model. Finally, simulation and experimental results validate the effectiveness of the proposed method.
-
表 1 超参数设置
参数 名称 数值 $\gamma $ 折扣因子 0.99 $\lambda $ 学习率 0.003 $\chi $ 软更新系数 0.01 ${N_{\text{e}}}$ 最大回合数 1000 $ {N_{\text{s}}} $ 最大步数 400 ${N_{ \mathcal{D}}}$ 经验池容量 100000 ${n_{\text{b}}}$ 批量数据的大小 128 
下载: 导出CSV
-
[1] KHAN H, HASSAN S A, and JUNG H. On underwater wireless sensor networks routing protocols: A review[J]. IEEE Sensors Journal, 2020, 20(18): 10371–10386. doi: 10.1109/JSEN.2020.2994199 [2] CARROLL P, MAHMOOD K, ZHOU Shengli, et al. On-demand asynchronous localization for underwater sensor networks[J]. IEEE Transactions on Signal Processing, 2014, 62(13): 3337–3348. doi: 10.1109/TSP.2014.2326996 [3] RAMEZANI H, JAMALI-RAD H, and LEUS G. Target localization and tracking for an isogradient sound speed profile[J]. IEEE Transactions on Signal Processing, 2013, 61(6): 1434–1446. doi: 10.1109/TSP.2012.2235432 [4] SHI Xiufang, MAO Guoqiang, ANDERSON B D O, et al. Robust localization using range measurements with unknown and bounded errors[J]. IEEE Transactions on Wireless Communications, 2017, 16(6): 4065–4078. doi: 10.1109/TWC.2017.2691699 [5] ANGJELICHINOSKI M, DENKOVSKI D, ATANASOVSKI V, et al. Cramér–Rao lower bounds of RSS-based localization with anchor position uncertainty[J]. IEEE Transactions on Information Theory, 2015, 61(5): 2807–2834. doi: 10.1109/TIT.2015.2409270 [6] MRIDULA K M and AMEER P M. Localization under anchor node uncertainty for underwater acoustic sensor networks[J]. International Journal of Communication Systems, 2018, 31(2): e3445. doi: 10.1002/dac.3445 [7] YAN Jing, GUO Dongbo, LUO Xiaoyuan, et al. AUV-aided localization for underwater acoustic sensor networks with current field estimation[J]. IEEE Transactions on Vehicular Technology, 2020, 69(8): 8855–8870. doi: 10.1109/tvt.2020.2996513 [8] CHANG Shengming, LI Youming, HE Yucheng, et al. RSS-based target localization in underwater acoustic sensor networks via convex relaxation[J]. Sensors, 2019, 19(10): 2323. doi: 10.3390/s19102323 [9] YAN Jing, MENG Yuan, YANG Xian, et al. Privacy-preserving localization for underwater sensor networks via deep reinforcement learning[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 1880–1895. doi: 10.1109/tifs.2020.3045320 [10] HAARNOJA T, TANG Haoran, ABBEEL P, et al. Reinforcement learning with deep energy-based policies[C]. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, 2017: 1352–1361. [11] HAARNOJA T, ZHOU A, ABBEEL P, et al. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor[C]. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, 2018: 1856–1865. [12] HUANG Baoqi, XIE Lihua, and YANG Zai. TDOA-based source localization with distance-dependent noises[J]. IEEE Transactions on Wireless Communications, 2015, 14(1): 468–480. doi: 10.1109/TWC.2014.2351798 [13] EROFEEVA V, GRANICHIN O, GRANICHINA O, et al. Sensor Selection under unknown but bounded disturbances in multi-target tracking problem[C]. Proceedings of the 27th Mediterranean Conference on Control and Automation, Akko, Israel, 2019: 215–220. [14] YAN Jing, YI Ming, YANG Xian, et al. Broad learning-based localization for underwater sensor networks with stratification compensation[J]. IEEE Internet of Things Journal, 2023. -
图(6) / 表(1)
计量
- 文章访问数: 456
- HTML全文浏览量: 219
- PDF下载量: 100
- 被引次数: 0
下载:
