基于非结构化月面复杂环境下SLAM技术研究进展
A Survey of Simultaneous Localization and Mapping on Unstructured Lunar Complex Environment

综述了非结构化月面复杂环境下同时定位与地图构建（SLAM）领域的最新研究进展，重点介绍和总结了视觉SLAM的特征提取方式，以及基于EKF，PF滤波器的SLAM方法和基于图优化的3种主流SLAM方法，并对SLAM技术面临的挑战做了深入的研究，最后对未来发展方向进行了展望。研究表明：在非结构化复杂环境下多传感器融合SLAM、多机器人协作SLAM、主动SLAM及结合人工智能技术等前沿性课题已取得一定的研究成果，但在完善方法模型、相关问题分支研究及语义地图创建等方面仍待突破，应作为下一步的重点研究方向。
Latest research progresses of SLAM (simultaneous localization and mapping) using in the unstructured complex environment of lunar surface were summarized. In addition, we focued on summarizing and comparing the detection and matching of features of SIFT, SURF and ORB, and analyzed the three main methods: SLAM Based on Extended Kalman Filter, SLAM Based on Particle Filter and SLAM Based on Graph Optimization (EKF-SLAM, PF-SLAM and Graph-based SLAM). Furthermore, the challenge of SLAM technology was studied deeply. Finally, the future research directions of advanced SLAM were discussed. The research showed that certain research achievements were made in the study of s multi-sensor fusion SLAM, multi-robot cooperative SLAM, active SLAM and combined with artificial intelligence technology. However, there were few research in this field aiming at optimization method model, related problem branch research and semantic mapping which should be taken as the primary research direction in the next step．