共查询到19条相似文献,搜索用时 78 毫秒
1.
2.
5.
6.
7.
未知环境中移动机器人并发建图与定位(CML)的研究进展 总被引:21,自引:0,他引:21
综述了近年较流行的CML方法,侧重比较各自估计与增量式建造地图的过程以及如何处理不确定信息、如何表示地图.还对CML问题的难点进行了分析,并探讨了未来的研究趋势. 相似文献
8.
为了验证提出的多传感器融合在工程应用中的有效性,针对视觉运动产生的失真情况,提出一种视觉-IMU传感器融合SALM的研究,并且设计了多传感器融合SLAM系统,将相机与IMU进行联合标定、采用图优化的融合方法在空间和时间上得到数据上的对齐。通过ROS系统自带的GAZEBO进行实时仿真,建立机器人小车模型在仿真的空间中运动,再通过APE绝对位姿误差计算并对比,得出了视觉-IMU融合的绝对位姿误差要比未融合情况下的误差小,优化之后的精度相比未融合的精度要高。因此利用该方法设计的融合系统较为合理。 相似文献
9.
针对动态物体在室内同步定位与地图构建(SLAM)系统中影响位姿估计的问题,提出一种动态场景下基于语义分割的SLAM系统。在相机捕获图像后,首先用PSPNet(Pyramid Scene Parsing Network)对图像进行语义分割;之后提取图像特征点,剔除分布在动态物体内的特征点,并用静态的特征点进行相机位姿估计;最后完成语义点云图和语义八叉树地图的构建。在公开数据集上的五个动态序列进行多次对比测试的结果表明,相对于使用SegNet网络的SLAM系统,所提系统的绝对轨迹误差的标准偏差有6.9%~89.8%的下降,平移和旋转漂移的标准偏差在高动态场景中的最佳效果也能分别提升73.61%和72.90%。结果表明,改进的系统能够显著减小动态场景下位姿估计的误差,准确地在动态场景中进行相机位姿估计。 相似文献
10.
提出一种基于改进粒子滤波器的移动机器人同时定位与建图方法.该方法将常规粒子滤波器与粒子群优化算法有机结合,引入最新的机器人观测信息以调整粒子的提议分布,从而在保证算法精度的同时,减少定位与建图所需的粒子数,并有效缓解粒子退化现象.此外,考虑到常规的重采样过程容易引起样本贫化现象,引入概率算子以增加粒子的多样性.实验结果表明该方法的可行性和有效性. 相似文献
11.
移动机器人同步定位与地图构建研究进展 总被引:3,自引:0,他引:3
同步定位与地图构建(Simultaneous localization and mapping, SLAM)作为能使移动机器人实现全自主导航的工具近来倍受关注.本文对该领域的最新进展进行综述,特别侧重于一些旨在降低计算复杂度的简化算法的分析上,同时对它们进行分类,并指出其优点和不足.本文首先建立了SLAM问题的一般模型,指出了解决SLAM问题的难点;然后详细分析了基于EKF的一些简化算法和基于其他估计思想的方法;最后,对于多机器人SLAM和主动SLAM等前沿课题进行了讨论,并指出了今后的研究方向. 相似文献
12.
移动机器人同步定位与地图构建过程中的轨迹规划研究 总被引:1,自引:1,他引:1
研究了移动机器人同步定位与地图构建(SLAM)过程中的轨迹规划问题.提出了一种新的目标函数,它同时考虑机器人运动对地图覆盖面积、地图不确定性、定位不确定性、导航代价等几个方面的影响.提出了一步最优和多步最优轨迹规划的概念,并分别设计了两种最优标准下的规划算法和近似计算方法.最后,通过对比仿真实验验证了所提出的方法的有效性,并指出了今后的研究方向. 相似文献
13.
基于分布式感知的移动机器人同时定位与地图创建 总被引:2,自引:0,他引:2
为了创建大规模环境的精确栅格地图,提出一种基于分布式感知的两层同时定位与地图创建(SLAM)算法.在局部层,机器人一旦进入了一个新的摄像头视野,便依据机器人本体上的激光和里程计信息,采用Rao-Blackwellized粒子滤波方法创建一个新的局部栅格地图.与此同时,带有检测标志的机器人在摄像头视野内以曲线方式运动,以解决该摄像头的标定问题.在全局层,一系列的局部地图组成一个连接图,局部地图间的约束对应于连接图的边.为了生成一个准确且全局一致的环境地图,采用随机梯度下降法对连接图进行优化.实验结果验证了所提算法的有效性. 相似文献
14.
15.
一种基于特征地图的移动机器人SLAM方案 总被引:1,自引:0,他引:1
设计了一种结构化环境中基于特征地图的地图创建方案;采用激光测距仪进行特征地图创建,利用"聚合-分害虫-聚合"的方法来提取线段表示环境信息实现局部地图创建;为了实现移动机器人的同时定位与地图创建,采用扩展卡尔曼滤波方法对机器人的位姿与地图信息进行预测及更新,结合状态估计和数据关联理论,实验显示x的校正量保持在±0.9cm之内;y的校正量保持在±2.5cm之内;θ的校正量在±1.2之内,实现了基于扩展卡尔曼滤波器的SLAM. 相似文献
16.
Xinzheng Zhang Ahmad B. Rad Yiu-Kwong Wong 《Journal of Intelligent and Robotic Systems》2008,53(2):183-202
Segment-based maps as sub-class of feature-based mapping have been widely applied in simultaneous localization and map building
(SLAM) in autonomous mobile robots. In this paper, a robust regression model is proposed for segment extraction in static
and dynamic environments. We adopt the MM-estimate to consider the noise of sensor data and the outliers that correspond to
dynamic objects such as the people in motion. MM-estimates are interesting as they combine high efficiency and high breakdown
point in a simple and intuitive way. Under the usual regularity conditions, including symmetric distribution of the errors,
these estimates are strongly consistent and asymptotically normal. This robust regression technique is integrated with the
extended Kalman filter (EKF) to build a consistent and globally accurate map. The EKF is used to estimate the pose of the
robot and state of the segment feature. The underpinning experimental results that have been carried out in static and dynamic
environments illustrate the performance of the proposed segment extraction method. 相似文献
17.
18.
《Advanced Robotics》2012,26(17):2021-2041
Abstract The calibration parameters of a mobile robot play a substantial role in navigation tasks. Often these parameters are subject to variations that depend either on changes in the environment or on the load of the robot. In this paper, we propose an approach to simultaneously estimate a map of the environment, the position of the on-board sensors of the robot, and its kinematic parameters. Our method requires no prior knowledge about the environment and relies only on a rough initial guess of the parameters of the platform. The proposed approach estimates the parameters online and it is able to adapt to non-stationary changes of the configuration. We tested our approach in simulated environments and on a wide range of real-world data using different types of robotic platforms. 相似文献
19.
A Discussion of Simultaneous Localization and Mapping 总被引:1,自引:0,他引:1
Udo Frese 《Autonomous Robots》2006,20(1):25-42
This paper aims at a discussion of the structure of the SLAM problem. The analysis is not strictly formal but based both on
informal studies and mathematical derivation. The first part highlights the structure of uncertainty of an estimated map with
the key result being “Certainty of Relations despite Uncertainty of Positions”. A formal proof for approximate sparsity of
so-called information matrices occurring in SLAM is sketched. It supports the above mentioned characterization and provides
a foundation for algorithms based on sparse information matrices.
Further, issues of nonlinearity and the duality between information and covariance matrices are discussed and related to common
methods for solving SLAM.
Finally, three requirements concerning map quality, storage space and computation time an ideal SLAM solution should have
are proposed. The current state of the art is discussed with respect to these requirements including a formal specification
of the term “map quality”.
This article is based on research conducted during the author's Ph.D. studies at the German Aerospace Center (DLR) in Oberpfaffenhofen.
Udo Frese was born in Minden, Germany in 1972. He received the Diploma degree in computer science from the University of Paderborn
in 1997. From 1998 to 2003 he was a Ph.D. student at the German Aerospace Center in Oberpfaffenhofen. In 2004 he joined University
of Bremen. His research interests are mobile robotic, simultaneous localization and mapping and computer vision. 相似文献