基于改进生物启发模型的UUV在线避障方法

李 磊; 杜 度; 陈 科

doi:10.11993/j.issn.2096-3920.2019.03.005

基于改进生物启发模型的UUV在线避障方法

doi: 10.11993/j.issn.2096-3920.2019.03.005

海军研究院, 北京, 100161

详细信息

作者简介:
李磊(1987-), 男, 博士, 工程师, 主要研究方向为UUV总体设计、协同组网与智能控制.

中图分类号: TJ630.33; U674.941; U664.82
计量
- 文章访问数: 654
- HTML全文浏览量: 17
- PDF下载量: 286
- 被引次数: 0
出版历程
- 收稿日期: 2018-12-23
- 修回日期: 2019-02-23
- 刊出日期: 2019-06-30

Online Obstacle Avoidance of UUV Based on the Improved Biological Inspired Model

Naval Research Academy, Beijing 100161, China

摘要

摘要: 针对无人水下航行器(UUV)在复杂海洋环境中面临的安全快速避障问题, 文中提出一种基于改进生物启发模型的在线避障方法, 以确保UUV具有快速实时的避障能力。首先, 根据预测控制滚动优化原理, 以前视声呐所获得的实时障碍物信息为基准, 对栅格地图进行滚动优化, 实时更新环境信息。其次, 将滚动栅格地图的变化一一对应成生物启发式神经网络拓扑结构图, 并针对生物启发模型的位置不确定性设计了新型判定函数, 通过判定函数值获取UUV下一时刻的航行位置, UUV通过对规划路径的跟踪, 实现在线实时避障。最后, 设计了滚动栅格动态试验以验证环境建模的正确性。通过障碍物避障的在线路径规划仿真试验验证了文中所提方法的有效性。
- 无人水下航行器 /
- 路径规划 /
- 生物启发模型 /
- 在线避障
Abstract: Aiming at the problem of safe and rapid obstacle avoidance faced by unmanned undersea vehicle(UUV) in complex marine environment, this paper proposes an online obstacle avoidance method based on improved biological inspired model to ensure the real-time obstacle avoidance capability. Firstly, according to the principle of predictive control rolling optimization, the real-time obstacle information obtained from the forward-looking sonar is used as a reference, and the grid map is optimized for rolling and real-time updating of environmental information. Secondly, the changes of the rolling grid map one-to-one correspond to the biological inspired neural network topology map, then a new decision function is designed for the position uncertainty of the biological inspired model. By determining the function value to obtain the navigation position of UUV at the next moment, UUV can track the planned path to realize online real-time obstacle avoidance. Finally, a dynamic test of rolling grid is designed to verify the correctness of the environmental modeling, and a simulation test of online path planning for obstacle avoidance is also designed. Simulation results verify the effectiveness of the proposed method.
- unmanned undersea vehicle(UUV) /
- path planning /
- biological inspired model /
- online obstacle avoidance

HTML全文

参考文献(14)

[1]	蔡自兴, 贺汉根, 陈虹, 等. 未知环境下移动机器人导航控制理论与方法[M]. 北京: 科学出版社, 2009.
[2]	郭利进. 大尺度环境下移动机器人同时定位与地图创建研究[D]. 天津: 天津大学, 2007.
[3]	马兆青, 袁曾任. 基于栅格方法的移动机器人实时导航和避障[J]. 机器人, 1996, 18(6): 344-348. Ma Zhao-qing, Yuan Zeng-ren. Real-time Navigation and Obstacle Avoidance Based on Grids Method for Fast Mobile Robot[J]. Robot, 1996, 18(6): 344-348.
[4]	王栋耀, 马旭东, 戴先中. 基于声呐的移动机器人沿墙导航控制. 机器人, 2004, 26(4): 346-350. Wang Dong-yao, Ma Xu-dong, Dai Xian-zhong. Wall-Following Navigation Control for a Sonar-based Mobile Robot[J]. Robot, 2004, 26(4): 346-350.
[5]	朱云龙, 申海, 陈瀚宁, 等. 生物启发计算研究现状与发展趋势[J]. 信息与控制, 2016, 45(5): 600-614. Zhu Yun-long, Shen Hai, Chen Han-ning, et al. Research Status and Development Trends of the Bio-inspired Compution[J]. Information and Control, 2016, 45(5): 600-614.
[6]	秦政, 边信黔, 严浙平. 多波束前视声呐在潜器避障中的应用研究[J]. 电子器件, 2007, 30(5): 1909-1913. Qin Zheng, Bian Xin-qian, Yan Zhe-ping. Research on Application of Multibeam Forward Looking Sonar in Obstacle Avoidance for Underwater Vehicle[J]. Chinese Journal of Electron Devices. 2007, 30(5): 1909-1913.
[7]	孙兵, 朱大奇, 邓志刚. 开架水下机器人生物启发离散轨迹跟踪控制[J]. 控制理论与应用, 2013, 30(4): 454- 462. Sun Bing, Zhu Da-qi, Deng Zhi-gang. Bio-inspired Discrete Trajectory-tracking Control for Open-frame Underwater Vehicles[J]. Control Theory & Applications. 2007, 30(5): 1909-1913.
[8]	朱大奇, 张光磊, 李蓉. 生物启发 AUV 三维轨迹跟踪控制算法[J]. 智能系统学报, 2014, 9(2): 180-185. Zhu Da-qi, Zhang Guang-lei, Li Rong. Biological Inspired Three-dimensional Tracking Control Algorithm for Autonomous Underwater Vehicles[J]. CAAI Transactions on Intelligent Systems, 2014, 9(2): 180-185.
[9]	Yang S X, Meng M H. Real-time Collision-free Motion Planning of Mobile Robots Using Neural Dynamics Based Approaches[J]. IEEE Trans on Neural Network, 2003, 14(6): 1541-1552.
[10]	Grossberg S. Nonlinear Neural Networks: Principles, Mechanisms and Architectures[J]. Neural Networks, 1988, 1(1): 17-61.
[11]	Yang S X, Luo C. A Neural Network Approach to Complete Coverage Path Planning[J]. IEEE Trans on Systems, Man and Cybernetics, Part B: Cybernetics, 2004, 34(1): 718-725.
[12]	Luo C, Yang S X. A Bio-inspired Neural Network for Re-al-time Concurrent Map Building and Complete Coverage Robot Navigation in Unknown Environment[J]. IEEE Trans on Neural Network, 2008, 19(7): 1279-1298.
[13]	Li H, Yang S X, Seto M L. Neural-network Based Path Planning for Multi-robot System with Moving Obstacles [J]. IEEE Trans on Systems, Man and Cybernetics, Part C:Applications and Reviews, 2009, 39(4): 410-419.
[14]	朱大奇, 孙兵, 李利. 基于生物启发模型的AUV三维自主路径规划与安全避障算法[J]. 控制与决策, 2015, 30(5): 798-806. Zhu Da-qi, Sun Bing, Li Li. Algorithm for AUV’s 3-D Path Panning and Safe Obstacle Avoidance Based on Biological Inspired Model[J]. Control and Decision, 2015, 30(5): 798-806.