无人车的室内自主驾驶中常用到EKF-SLAM(Simultaneous Localization and Mapping)技术。单纯的编码器SLAM技术,由于其长时间的运行会导致累计误差过大,使得定位非常不准确,所以需要一种技术,对位置信息的定位方式加以辅助,考虑...无人车的室内自主驾驶中常用到EKF-SLAM(Simultaneous Localization and Mapping)技术。单纯的编码器SLAM技术,由于其长时间的运行会导致累计误差过大,使得定位非常不准确,所以需要一种技术,对位置信息的定位方式加以辅助,考虑到二维码识别技术的方便性以及易用性,本文采用二维码人工路标作为绝对定位方式的标签,提升EKF—SLAM的定位准度,并利用扩展卡尔曼滤波进行多数据融合,通过实验验证了实验该方案的可行性与实用性。展开更多
In view of the technical difficulties of autonomous navigation in local areas,this paper proposes a high-precision autonomous navigation shared bal-ancing bike system based on EKF-SLAM.This system uses the EKF-SLAM alg...In view of the technical difficulties of autonomous navigation in local areas,this paper proposes a high-precision autonomous navigation shared bal-ancing bike system based on EKF-SLAM.This system uses the EKF-SLAM algorithm in robot localization to achieve simultaneous localization and map con-struction using the extended Kalmanfilter.At the same time,GPS and IMU are also employed for absolute positioning,and point cloud matching is used for rel-ative positioning to achieve multisensor fusion positioning.For the convenience of users,this system uses the RNN-T model for speech recognition destinations.Through experimental verification,the EKF-SLAM-based autonomous naviga-tion technology proposed in this paper can meet the accurate localization service and can realize the function of high precision autonomous navigation and voice recognition of destinations for shared balancing vehicles in a local area.展开更多
为解决移动机器人扩展卡尔曼滤波(EKF-SLAM)算法计算复杂、精确度不高及易受干扰的缺点,提出一种基于最优平滑滤波理论的改进同步定位与地图构建(simultaneous localization and mapping,SLAM)算法。详细介绍算法的改进过程,通过Matlab...为解决移动机器人扩展卡尔曼滤波(EKF-SLAM)算法计算复杂、精确度不高及易受干扰的缺点,提出一种基于最优平滑滤波理论的改进同步定位与地图构建(simultaneous localization and mapping,SLAM)算法。详细介绍算法的改进过程,通过Matlab软件对其位置轨迹跟踪误差及标准差进行仿真分析,基于机器人操作系统(robot operating system,ROS)系统的实验平台,在室内走廊进行SLAM实验以测试改进算法的效果。结果表明,改进的SLAM算法精度高、抗干扰能力强,能实现移动机器人的即时定位与地图构建。基于ROS系统的软件平台能简化开发难度,提升移动机器人的智能化。展开更多
在SLAM领域中,为了克服稀疏特征地图不能提供详尽环境信息的缺点,从观测信息的物理意义出发,提出了全局观测地图模型.其基本思想是在稀疏特征地图中嵌入全局密集地图信息,采用位移准则、特征准则和传感器量程准则提取必要的观测信息,然...在SLAM领域中,为了克服稀疏特征地图不能提供详尽环境信息的缺点,从观测信息的物理意义出发,提出了全局观测地图模型.其基本思想是在稀疏特征地图中嵌入全局密集地图信息,采用位移准则、特征准则和传感器量程准则提取必要的观测信息,然后对观测信息进行去噪、转换,接着根据观测信息的物理意义和机器人位姿估计的不确定性获取环境的全局密集地图,可视化后得到环境的二值地图、灰度地图或颜色地图.将全局观测地图模型与EKF-SLAM算法相结合,提出了GOE-SLAM算法,采用Car Park Dataset对GOE-SLAM进行了实验验证,结果表明GOE-SLAM生成了可信的密集地图,并且GOE-SLAM的计算复杂度与EKF-SLAM相当.展开更多
文摘无人车的室内自主驾驶中常用到EKF-SLAM(Simultaneous Localization and Mapping)技术。单纯的编码器SLAM技术,由于其长时间的运行会导致累计误差过大,使得定位非常不准确,所以需要一种技术,对位置信息的定位方式加以辅助,考虑到二维码识别技术的方便性以及易用性,本文采用二维码人工路标作为绝对定位方式的标签,提升EKF—SLAM的定位准度,并利用扩展卡尔曼滤波进行多数据融合,通过实验验证了实验该方案的可行性与实用性。
文摘In view of the technical difficulties of autonomous navigation in local areas,this paper proposes a high-precision autonomous navigation shared bal-ancing bike system based on EKF-SLAM.This system uses the EKF-SLAM algorithm in robot localization to achieve simultaneous localization and map con-struction using the extended Kalmanfilter.At the same time,GPS and IMU are also employed for absolute positioning,and point cloud matching is used for rel-ative positioning to achieve multisensor fusion positioning.For the convenience of users,this system uses the RNN-T model for speech recognition destinations.Through experimental verification,the EKF-SLAM-based autonomous naviga-tion technology proposed in this paper can meet the accurate localization service and can realize the function of high precision autonomous navigation and voice recognition of destinations for shared balancing vehicles in a local area.
文摘在SLAM领域中,为了克服稀疏特征地图不能提供详尽环境信息的缺点,从观测信息的物理意义出发,提出了全局观测地图模型.其基本思想是在稀疏特征地图中嵌入全局密集地图信息,采用位移准则、特征准则和传感器量程准则提取必要的观测信息,然后对观测信息进行去噪、转换,接着根据观测信息的物理意义和机器人位姿估计的不确定性获取环境的全局密集地图,可视化后得到环境的二值地图、灰度地图或颜色地图.将全局观测地图模型与EKF-SLAM算法相结合,提出了GOE-SLAM算法,采用Car Park Dataset对GOE-SLAM进行了实验验证,结果表明GOE-SLAM生成了可信的密集地图,并且GOE-SLAM的计算复杂度与EKF-SLAM相当.