摘要
提出了基于免疫遗传算法的静态环境下移动机器人全局路径规划方法。该方法首先建立机器人工作空间中环境信息的神经网络模型,并利用该模型建立机器人免碰撞路径与神经网络输出的关系,将免碰撞要求和路径最优要求融合成免疫遗传算法的一个简单适应度函数。将抗体选择概率表示成一个基于抗体矢量距和抗体浓度的融合函数,同时保证了抗体的多样性和成熟收敛。通过仿真,并与遗传算法相比,性能有很大提高,证明了该全局路径规划方法的正确性和有效性。
A method of global path planning for mobile robot in static environment is proposed based on immune genetic algorithm.First the neural network model of environmental information is constructed in the working space for robot,also the relationship between the collision-free path and the neural network output is established based on this model,then the collision- free demand and the path optimization demand are fused to a simple fitness function for immune genetic algorithm.Antibody selective probability is expressed as a fusion function based on antibody vector distance and antibody density,the antibody diversity and maturation convergence are ensured synchronously.Finally the simulation results show that the performance is improved by contrast with genetic algorithm,also simulation results demonstrate that the algorithm for global path planning is feasible and valid.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第30期91-93,161,共4页
Computer Engineering and Applications
