【摘要】 针对结构化环境下移动机器人的路径规划问题 ,提出了一种基于神经网络的路径规划算法。该算法利用神经网络描述环境约束并计算碰撞能量函数。采用了一种离散化的方法逼近能量的负梯度方向 ,从而确定路径点集的运动趋向。最后利用计算机仿真分析了该算法的性能和效率。更多还原

【Abstract】 A kind of path planning algorithm based on neural network is represented aiming at mobile robots in structured environments. Neural network is used in the algorithm to describe the constrain of environments and calculate the collision energy function. A discrete method is adopted to approximate the minus gradient direction in order to determine the motion tendency of the point set. Finally, the performance and efficiency of the algorithm are estimated through computer simulation.更多还原