路网约束下基于灰狼算法的机器人路径规划  

Robot Path Planning Based on Gray Wolf Algorithm under Road Network Constraints

在线阅读下载全文

作  者:王涛 李志斌 WANG Tao;LI Zhi-bin(School of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区:[1]上海电力大学自动化工程学院,上海200090

出  处:《计算机仿真》2024年第5期441-445,共5页Computer Simulation

摘  要:机器人在规划路径时,由于初始路径群体数量多,且存在大量冗余个体,导致路径规划普遍存在效率低、可靠性不高等问题,为此设计一种路网约束下基于灰狼算法的机器人路径规划方法。利用多传感器采集车辆、环境等道路数据,推算车辆行驶速度、交通量及密度,使用信息守恒理论平滑计算交通数据,运用负指数函数构建证据理论信度,引入卡尔曼滤波器实现道路交通数据融合,构成完整路网架构;使用灰狼算法规划机器人路径,将狼群中适应度最高的3匹狼拟作头狼,通过搜寻猎物、包围猎物与进攻猎物来创建数学模型,更新灰狼方位了解其移动情况,完成机器人路径自适应规划。实验结果表明,所提方法时效性强,在静态、动态环境下均能实现机器人最优路径规划,且在动态环境下仅迭代4次就可找到最优路径,为机器人的高效率应用提供技术帮助。Due to the large number of initial path groups and many redundant individuals,generally,the problems of low efficiency and low reliability exist in path planning process.Therefore,based on gray wolf algorithm,this paper presented a method for robot path planning under road network constraints.Firstly,multiple sensors were used to collect road data,including vehicle and environment.And then,the speed,traffic volume and density were calculated.Secondly,information conservation theory was adopted to calculate the traffic data smoothly.Meanwhile,negative exponential function was used to design the evidence theory reliability.Moreover,Kalman filter was introduced to achieve the fusion of traffic data,thus forming a complete architecture of road network.Furthermore,gray wolf algorithm was used to plan the path of robot.The three wolves with the highest fitness in wolfpack were regarded as the head wolves.Finally,a mathematical model was built by searching for,encircling prey and attacking prey.After the orientation of gray wolf was updated,the robot path adaptive planning was completed.The experimental results show that the proposed method has strong timeliness,and can achieve optimal path planning in static and dynamic environments.In addition,the method can find the optimal path only after 4 iterations in dynamic environment,while providing technical help for efficient application of robots.

关 键 词:路网约束 灰狼算法 机器人运动 路径规划 数据感知 

分 类 号:TP242[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象