智能汽车主动避障的改进蚁群路径规划方法

Improved Ant Colony Path Planning Method for Intelligent Vehicle Active Obstacle Avoidance

针对智能汽车主动避障路径规划问题,为有效提高路径规划质量、加快算法的收敛速度,提出了一种改进的自适应蚁群智能规划方法。首先,阐释了传统蚁群算法的原理和具体流程,并分析了传统算法存在的缺陷;其次,提出了信息素因子和启发因子的自适应更新算法以扩大算法的搜索范围、提高全局搜索能力,从而避免算法陷于局部最优;再者,设计了信息素挥发率和信息素浓度函数的自适应调节算法以加快算法的粒子进化速度,从而保证了算法的快速收敛。智能汽车避障实验结果表明,与传统蚁群算法相比,这里改进蚁群算法能够有效加快路径规划速度、提升算法的收敛速度并显著缩短规划的路径长度。

Aiming at the problem of active obstacle avoidance and path planning for smart car,in order to effectively improve the quality of path planning and accelerate the convergence speed of the algorithm,an improved adaptive ant colony intelligent planning algorithm is proposed.First,the principle and specific process of traditional ant colony algorithm are explained,and the defects existing in traditional algorithm are analyzed.Secondly,the adaptive update algorithm of pheromone factors and heuristic factors are proposed to expand the search range of the algorithm and improve the global search ability,so as to avoid the algorithm being trapped in the local optimum.Furthermore,the pheromone volatility rate and pheromone concentration function are designed to adaptively adjust the algorithm to accelerate the particle evolution speed of the algorithm,thereby ensuring the rapid convergence of the algorithm.The obstacle avoidance experiment results of smart cars show that,compared with the traditional ant colony algorithm,the improved ant colony algorithm in this paper can effectively accelerate the path planning speed,improve the algorithm′s convergence speed,and significantly shorten the planned path length.