摘要
为提高移动智能小车SLAM自主导航避障性能和运动稳定性,提出一种基于ROS框架的语音导航智能小车设计方法。建立智能小车的运动学模型,完成硬件电路和软件平台的搭建,基于粒子滤波器的FastSLAM算法,结合A^(*)和动态窗口法DWA,编写ROS框架下的Cmapping功能包,实现智能小车的运动实验仿真、路径规划和动态避障。采用语音识别控制策略,利用Gazebo仿真和Rviz可视化,开展智能小车的语音导航试验。对比分析A^(*)结合TEB算法的小车避障耗时及运动平顺性,仿真与实车验证结果均表明,本文方法设计的智能小车避障时间短,移动路径具有连续性,语音导航对环境的适应性强。
In order to improve the performance of obstacle avoidance and motion stability of SLAM autonomous navigation,a design method of voice navigation intelligent cart based on ROS framework is proposed.The kinematic model of the itelligent ceart is established,and the hardware cireuit and software platform are completed.Based on the FastSLAM algorithm of particle filter,combined with A^(*)and the dynamic window approach,the Gmapping function package under the ROS framework is writen to realize the motion experiment simulation,path planning and dynamic obstacle avoidance of the itelligent cart.Using the speech recognition control strategy,Gazebo simulation and Rviz visualization,the experiment of itelligent car voice navigation is carried oult.Comparing and analyzing the cart avoidance time consumption and smoothness of motion of A^(*)combined with TEB algorithm,both simulation and real vehicle verification results show that the itelligent cart designed by the method of this paper has shorter obstacle avoidance time,continuity of moving path,and strong adaptability of voice navigation to the env ironment.
作者
李飞
胡坤
张勇
LI Fei;HU Kun;ZHANG Yong(School of Mechanical Engineering,Anhui University of Science and Technology,Huainan Anbui 232001,China;State Key laboratory of Coal Mining Response and Disaster Prevention and Control in Deep Coal Mines,Huainan Anhui 232001,China)
出处
《机械设计与研究》
CSCD
北大核心
2021年第6期46-52,65,共8页
Machine Design And Research
基金
国家自然科学基金项目(51874004.51904007)
安徽省重点研发计划(202004a07020043)
安徽省科技重大专项资助项目(18030901049)。
