基于多传感器融合的移动机器人定位

Mobile Robot Localization Based on Multi-sensor Fusion

移动机器人定位是进行导航和路径规划的前提和基础。论文提出了一种基于多传感器数据融合的室内移动机器人定位方法。使用基于粒子滤波的蒙特卡洛算法,融合激光雷达、加速度计和里程计等多传感器的信息进行定位,有效改善了传统定位方法因为无法关联底层数据信息或者路面打滑导致定位失败等问题。进而,通过采取基于权值的融合,消除了连续迭代步骤中"跳跃"行为的影响;通过粒子剔除机制,优化了粒子种群,提高算法的执行效率。最后,基于设计的两轮机器人平台,通过仿真和真实环境联合论证,验证了所开发机器人定位方法的有效性。

Mobile robot localization is the premise and basis for navigation and path planning. This paper proposes an indoormobile robot localization method based on multi-sensor data fusion. The Monte Carlo algorithm based on particle filter is used to in-tegrate the information of multi-sensors such as laser radar,accelerometer and odometer to effectively improve the traditional local-ization method because it cannot correlate the underlying data information or the road surface slip causes the localization failure. Fur-thermore,by adopting the weight-based fusion,the influence of the "jumping" behavior in the successive iteration steps is eliminat-ed,the particle culling mechanism optimizes the particle population and improves the execution efficiency of the algorithm. Finally,based on the design of the two-wheeled robot platform,the effectiveness of the developed robot localization method is verified by thejoint demonstration of simulation and real environment.