融合退化因子的煤矿巷道SLAM算法研究
打开文本图片集
中图分类号：TD67 文献标志码：A
Abstract：To addressthe problem that existing Simultaneous Localization and Mapping （SLAM） algorithms tend tosufer from localization drift or even failure in degenerated environments of underground coal mine roadways，acoal mine roadway SLAMalgorithm incorporatingdegeneration factors was proposed.Thealgorithm was built onanExtended KalmanFilter（EKF）framework and integrated encoder information with data froman Inertial Measurement Unit （IMU）andLiDAR to achieve localization and mapping.The method for calculating he degeneration factor was improvedbyobtaining eigenvaluesand degeneration factors through lineand plane featureregistration，where the magnitude of the degeneration factorcharacterized the degreeof environmental degeneration，thereby enabling environmental degenerationassessment.Aconfidence fusion mechanismbasedon degeneration factors was designed to maintain high-precision localization and mapping while significantly enhancing system robustnessTheresidual was designed by increasing the weights of high-precision feature pointsand reducing those of low-precision ones，thereby improving the accuracy of degeneration factor characterization.Experimental results showed that，compared with existingalgorithms such as the tightly coupled LiDAR-Inertial Odometry via Smoothing and Mapping （LIOSAM） and LiDAR Odometry and Mapping （LOAM）， the proposed algorithm demonstrated stronger adaptability to degenerated coal mine environments and could stably complete localization and mapping tasks. The positioning error of the proposed algorithm in degenerated environments was 1.222m ，whichwasreducedby 26.506m compared with the LIOSAM algorithm. In nondegenerated environments， its Root Mean Square Error （RMSE） averaged 0.116m ，which was lower than those of the LOAM and LIOSAM algorithms. The algorithm could also operate stably in roadway segments where features were degenerated .
Key words： underground wheeled robot; simultaneous localization and mapping; roadway degeneration environment; degeneration assessment mechanism; confidence fusion mechanism; degeneration factor; LiDAR odometry and mapping
0引言
2019年，国家煤矿安全监察局发布的《煤矿机器人重点研发目录》中强调应重点研发应用掘进、采煤、运输、安控和救援5类、38种煤矿机器人，对煤矿机器人提出了自主、自动、替代人工的明确要求。（剩余14196字）
