未知环境下移动机器人同步地图创建与定位研究进展

移动机器人同步地图创建与定位(SLAM)是移动机器人的核心研究课题.本文对SLAM的最新研究进展和关键技术进行了综述:并从地图创建模型、计算复杂度和算法鲁棒性等方面对现有方法进行了对比分析.最后总结分析了SLAM研究存在的难题,探讨了今后的发展方向.     

基于场景识别的移动机器人定位方法研究

提出了一种基于场景识别的移动机器人定位方法．对CCD采集的工作环境的系列场景图像,用多通道Gabor 滤波器提取场景图像的全局纹理特征,然后通过SVM分类器来识别场景图像,实现机器人的逻辑定位．在移动机器人CASIA-I 上对该算法进行了实验．实验结果表明,该定位方法可达到91.11%的定位准确率,对光照、对比度等因素有较强的鲁棒性,并且满足机器人实时定位的要求．     

未知环境下的移动机器人定位及实时避障

针对未知环境下移动机器人实时动态避障及定位问题，考虑里程计定位的无界累加误差和动态障碍物环境下实时障碍躲避需要，提出了一种可行的避障定位的策略。该策略融合了机器人内部传感器、里程计、电子罗盘和激光测距仪的同步和异步信息，合理地解决了常规定位过程中的方向迷失问题，对于静态和动态障碍物都能很好地实时躲避，具有很强的抗干扰性和较高的定位精度。实验证明了该方法的有效性和实用性.     

基于粒子滤波器的移动机器人自定位方法研究

首先,对粒子滤波器的原理进行了简要阐述。然后详细描述了基于粒子滤波器的移动机器人自定位算法——蒙特卡洛定位算法。在ROS(Robot Operating System)平台上对该算法进行了仿真实验并分析了其性能。最后,对蒙特卡洛粒子滤波定位方法用于移动机器人定位进行了总结。结果表明,MCL(蒙特卡洛)算法是一种精确鲁棒的移动机器人概率定位方法,可对解决移动机器人的定位问题提供有意义的参考。提出的机器人自定位方法为机器人在Robocup竞赛中自主执行各种作业提供定位支持,已在2013年中国机器人大赛获奖。     

自适应扩展卡尔曼滤波器在移动机器人定位中的应用

针对移动机器人定位过程中存在的误差积累问题,提出了采用自适应扩展卡尔曼滤波算法(AEKF).分析了扩展卡尔曼滤波(EKF)和AEKF两种算法, AEKF取采样时刻的各项泰勒级数,并利用Sage-Husa时变噪声估计器实时估计观测噪声,克服了线性化误差,增强了环境适应性;同时,对AEKF的收敛性及运算复杂度进行分析,并结合算法实验表明AEKF具有良好的速度精度综合性价比;最后对比分析两种算法实现机器人定位的效果并实验完成误差对比.结果表明AEKF具有更优的定位性能.     

模糊PID控制下移动机器人定位方法研究

机器人定位研究一直是机器人学研究的重点,但目前机器人定位方法都存在缺点,抗干扰能力差,不能做到准确定位,主要是由于环境等多方面因素的干扰,定位误差会逐渐加大;由于上述原因,提出了一种基于设定值加权模糊PID控制的移动机器人自定位方法;给出了定位过程的参数,为机器人移动建立模型,设计一种模糊 PID 控制器,根据误差及变化率大小,选择模糊定位或PID定位,实现移动机器人的智能定位,提高机器人定位准确的准确性;通过仿真实验结果证明:模糊PID控制的机器人自定位方法对移动机器人的定位过程有较好的改善作用,实用效果较好。     

基于粒子滤波器的移动机器人定位和地图创建研究进展

首先,对粒子滤波器的原理和研究进展进行了综述．然后,介绍了基于粒子滤波器的移动机器人定位研究进展．其次,给出了粒子滤波器在移动机器人地图创建领域的最新成果．最后,对粒子滤波器在移动机器人研究领域的未来发展方向进行了展望．     

采用双重采样的移动机器人Monte Carlo定位方法

移动机器人Monte Carlo定位效率受限于大量粒子的权值更新运算. 本文提出一种实现粒子集规模自适应调整的双重采样方法: 第一层基于粒子权重的固定粒子数重采样, 有效减轻粒子权值退化并保证预测阶段粒子多样性; 第二层粒子稀疏化聚合重采样, 基于粒子空间分布合理性将粒子加权聚合, 从而减少参与权值更新粒子数. 该方法通过提高粒子预测能力保证滤波精度, 通过减少权值更新运算提高了粒子滤波效率. 仿真实验表明, 双重采样方法能够有效实现粒子集规模自适应调整,采用双重采样的移动机器人Monte Carlo定位方法是高效、鲁棒的.     

基于光电鼠标的移动机器人室内定位方法

介绍通常的定位方法和背景知识后，提出了使用光电鼠标来提高航迹推算法法精度的方法。仿真显示该方法比传统的航迹推算法法要好。     

NLOS环境下基于EKF的移动机器人定位研究

针对室内移动机器人基于接收信号强度(RSSI,Received Signal Strength Indication)测距定位存在非视距(NLOS,Not-line-of-sight)传播问题,提出一种利用运动模型预测RSSI并修正NLOS测量的定位算法。首先结合移动机器人运动模型预测位置和信号强度RSSI,进而实现NLOS误差判定和测量修正;然后结合步长将移动机器人限制到圆域内,采用改进三边定位算法定位;最后使用扩展卡尔曼滤波(EKF,extended Kalman Filter)进行定位结果优化,得到位置的优化估计。仿真实验表明,该方法能有效地提高定位精度,能有效抑制具有较大量值的NLOS误差,是NLOS环境下一种有效的定位方法。     

Mobile robot localization using sonar

This correspondence describes a method by which range data from a sonar rangefinder can be used to determine the two-dimensional position and orientation of a mobile robot inside a room. The plan of the room is modeled as a list of segments indicating the positions of walls. The algorithm works by correlating straight segments in the range data against the room model, then eliminating implausible configurations using the sonar barrier test, which exploits physical constraints on sonar data. The approach is extremely tolerant of noise and clutter. Transient objects such as furniture and people need not be included in the room model, and very noisy, low-resolution sensors can be used. The algorithm's performance is demonstrated using a Polaroid Ultrasonic Rangefinder.     

不完整地图中移动机器人蒙特卡罗定位研究*

针对移动机器人在不完整地图中定位的问题,提出了一种改进的粒子聚类蒙特卡罗定位(Monte Carlo localization, MCL)算法。在定位过程中,将机器人的位姿分为六种状态,每一种状态对应一个粒子簇。在机器人运动的过程中,这六种状态之间可以相互转移,在计算状态转移概率的基础上,实现了不完整地图中移动机器人蒙特卡罗定位算法。实验验证了该算法在解决移动机器人在不完整地图中定位问题的有效性。     

Mobile robot localization based on PSO estimator

Localization is fundamental to autonomous operation of the mobile robot. A particle filter (PF) is widely used in mobile robot localization. However, the robot localization based PF has several limitations, such as sample impoverishment and a degeneracy problem, which reduce significantly its performance. Evolutionary algorithms, and more specifically their optimization capabilities, can be used in order to overcome PF based on localization weaknesses. In this paper, mobile robot localization based on a particle swarm optimization (PSO) estimator is proposed. In the proposed method, the robot localization converts dynamic optimization to find the best robot pose estimate, recursively. Unlike the localization based on PF, the resampling step is not required in the proposed method. Moreover, it does not require noise distribution. It searches stochastically along the state space for the best robot pose estimate. The results show that the proposed method is effective in terms of accuracy, consistency, and computational cost compared with localization based on PF and EKF.     

基于全景视觉的移动机器人地图创建与定位

提出一种高效的基于全景视觉的室内移动机器人地图构建和定位方法. 该方法充分利用全景视觉系统视野广阔、获取环境信息完整的特点, 根据全景图像生成环境描述子; 利用上述环境描述子描述环境, 创建拓扑地图, 将地图表示为环境描述子的集合. 在此基础上, 提出一种基于贝叶斯理论的定位方法, 根据当前全景摄像头的观测值, 利用已生成的地图完成状态跟踪, 全局定位和“绑架”定位. 最后通过实验验证了该方法的有效性, 并给出了计算成本分析.     

Mobile robot localization with gyroscope and constrained Kalman filter

The odometry information used in mobile robot localization can contain a significant number of errors when robot experiences slippage. To offset the presence of these errors, the use of a low-cost gyroscope in conjunction with Kalman filtering methods has been considered by many researchers. However, results from conventional Kalman filtering methods that use a gyroscope with odometry can unfeasible because the parameters are estimated regardless of the physical constraints of the robot. In this paper, a novel constrained Kalman filtering method is proposed that estimates the parameters under the physical constraints using a general constrained optimization technique. The state observability is improved by additional state variables and the accuracy is also improved through the use of a nonapproximated Kalman filter design. Experimental results show that the proposed method effectively offsets the localization error while yielding feasible parameter estimation.     

Mobile robot localization using a self-organized visual environment representation

Owing to the upcoming applications in the field of service robotics mobile robots are currently receiving increasing attention in industry and the scientific community. Applications in the area of service robotics demand a high degree of system autonomy, which robots without learning capabilities will not be able to meet. Learning is required in the context of action models and appropriate perception procedures. In both areas flexible adaptivity is difficult to achieve especially when high bandwidth sensors (e.g. video cameras) - which are needed in the envisioned unstructured worlds - are used. This paper proposes a new methodology for image-based navigation using a self-organized visual representation of the environment. Self-organization leads to internal representations, which can be used by the robot, but are not transparent to the user. It is shown how this conceptual gap can be bridged.     

Mobile robot localization by fuzzy logic fusion of multisensor data

Interest has been growing in the use of different sensors to increase the capabilities of navigation systems of autonomous vehicles. This area has been studied by several researchers. Nevertheless, this problem has not been solved in a fully satisfying manner. We proposed the method of global, long-term position estimation in a known environment. The method does not require any a priori position prediction or estimation. It is especially suitable in the case of using very simple sensors. The algorithm is based on fuzzy logic fusion of data received from several sensors for some time period. We discuss the methodology of solution evaluation and present some examples of typical criteria. Results of first computer simulation are presented.     

移动机器人对气体泄漏源的定位—–矩阵半张量积方法

对于使用移动机器人在风速/风向变化较大的气流环境中定位气体泄漏源的问题,我们建立了一个定位模型.模型的输入为机器人在定位过程中实时获取的多传感器信息(激光信息、视觉信息、气体浓度信息、风信息等),输出为相应的搜寻行为或策略,主要包括避障行为、随机搜寻、视觉搜寻、化学趋向性搜寻、风趋向性搜寻、路径规划和气体泄漏源定位等.利用矩阵的半张量积理论,我们确定了这个模型输入和输出之间的结构矩阵.根据多传感器的测量信息,结构矩阵产生相应的搜寻行为或策略,由动态机器人有效地完成,以确定气体源的位置.本方法的可靠性经过机器人实地实验得到验证.