中文摘要：

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．

英文摘要：

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.