基于DS证据理论的井下UWB/LiDAR组合定位方法

打开文本图片集

中图分类号：TD67 文献标志码：A

Abstract： LightLaser Detection and Ranging （LiDAR） and Ultra Wide Band （UWB） are currently widely usedunderground positioning technologies.To address the problem that single LiDAR positioning in mine roadways with sparse and repetitive structural features produces deviations due to insuficient geometric constraints，and UWB positioning is prone toaccuracy degradationcaused byNon-Line-of-Sight （NLOS）errors， this paper proposed an underground UWB/LiDAR integrated positioning method based on DS evidence theory. Signal energy inchannel statistical parameters wasusedas the feature parameter，and kernel density estimation Was employed for feature extraction.Basedontheextracted energyfeatures，SimulatedAnnealing-Support Vector Machine （SA-SVM） was applied to identify NLOS environments，achieving efective handling of NLOS errors in UWB positioning.DS evidence theory was thenadopted to fuse UWBand LiDAR positioning data to improve positioning accuracy.Experiments were carried out inanunderground roadway of a coal mine.The results showed that SA-SVMachieved 94% accuracy in NLOS environment identification. The maximum error of the UWB/LiDAR integrated positioningmethod based onDS evidence theorywas 1.073 50m， the minimum error was 0.00205m ，the mean error was 0.25934m ，the standard deviation was 0.11005m ，and the root mean square error was 0.33108m . This method outperforms UWB positioning， LiDAR positioning， and the integrated positioning method based on Extended Kalman Filter.

Key words： underground positioning; UWB positioning; LiDAR positioning; DS evidence theory; integrated positioning

0引言

在煤矿井下机器人导航、自动驾驶、接近探测等应用中，精确定位是高效、安全执行任务的基础[1]。（剩余12828字）