基于BISOM的多AUV任务分配和路径规划算法

The Task Allocation and Path Planning Based onBISOM

针对三维水下障碍物环境的多AUV（Autonomous Underwater Vehicle）任务分配与路径规划问题,提出了一种生物启发自组织任务分配和路径规划算法.首先,利用自组织神经网络SOM（Self一Organizing Map）将水下目标分配给一组AUV,这个过程包括自组织神经网络的初始权值的定义、获胜神经元的选取、邻域函数的计算;其次,针对传统SOM 路径规划更新的速度跳变与安全避障问题,将生物启发神经动力学模型（BINM： Biological Inspired Neural Dynamics Model）嵌入自组织神经网络之中,利用生物启发神经动力学模型进行自组织神经网络权值的更新,从而可以规划出一条无速度跳变、无碰撞的有效路径,实现多AUV 自适应任务分配与有效路径规划.最后,为了验证所提出方法的有效性,给出了仿真实验结果.

For the task allocation and path planning of multi-AUV （Autonomous Underwater Vehicle） system in three dimensionalunderwater environments with obstacles, a novel biological inspired self-organizing task allocation and path planning algorithm isproposed. Firstly, the SOM neural network （the self-organizing map） is developed to assign targets in underwater environment to ateam of AUVs. The working process involves the definition of the initial neural weights of the SOM network, the rule of selectingthe winner, the computation of the neighborhood function. Then, in order to solve the problem of obstacle avoidance and sharpspeed jump, the biological inspired neural dynamics model （BINM） is embedded into the SOM neural network, the biologicalinspired neural dynamic model is used to update weights of the SOM neural network, and plan a path without sharp speed jumpand obstacles. As a result, adaptive task allocation and effective path planning are achieved. Finally, to demonstrate theeffectiveness of the proposed approach, simulation results are given in this paper.