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  

Algorithm for AUV's 3-D path planning and safe obstacle avoidance based on biological inspired model

作　　者：朱大奇[1] 孙兵[1] 李利[1] 

机构地区：[1]上海海事大学水下机器人与智能系统实验室,上海201306

出　　处：《控制与决策》2015年第5期798-806,共9页Control and Decision

基　　金：国家自然科学基金项目(51279098);上海市科委创新行动计划项目(14JC1402800;13510721400)

摘　　要：针对自治水下机器人(AUV)的路径规划问题,在三维栅格地图的基础上,给出一种基于生物启发模型的三维路径规划和安全避障算法.首先建立三维生物启发神经网络模型,利用此模型表示AUV的三维工作环境,神经网络中的每一个神经元与栅格地图中的位置单元一一对应;然后,根据神经网络中神经元的活性输出值分布情况自主规划AUV的运动路径.静态环境与动态环境下仿真实验结果表明了生物启发模型在AUV三维水下环境中路径规划和安全避障上的有效性.For the problem of path planning for the autonomous underwater vehicle（AUV）, in a 3-D grid map, an algorithm based on the biological inspired model for 3-D path planning and safe obstacle avoidance is proposed. Firstly, based on the establishment of 3-D biological inspired neural network model, the AUV 3-D working environment is represented. There is one-to-one correspondence between each neuron in the neural network and the position of the grid map. Then, the motion path of the AUV is planned on the basis of the distribution of neurons＇ active output value in neural network. Finally, the simulation results of path planning in the static and dynamic environment show that biological inspired model can solve effectively the path planning and safe obstacle avoidance for the AUV in the 3-D underwater environment.

关 键 词：三维栅格地图 生物启发模型 路径规划 安全避障 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]