研究AUV在三维海底地形环境中的路径规划问题。针对三维地形中路径的不同特点，将路径分为3种类型。设计了优化路径的遗传算法实现方案，所提出的惩罚函数及启发性知识的使用，使算法能灵活的得到具有不同特点的最优路径。仿真实验表明了该算法的可行性与可靠性，对AUV的安全航行具有重要的理论意义及应用参考价值。

The path-planning algorithm of AUV in 3D seabed environment is studied. For 3D environment, the optimal paths are classified into three different types. The optimal paths of each type are obtained flexibly by using genetic algorithm, especially the incorporating of problem-specific knowledge and penalty function. Simulation results show the feasibility and reliability of the path-planning algorithm, which has considerable value on the safe navigation of AUV in seabed environment.