同时定位和映射
计算机科学
Orb(光学)
约束(计算机辅助设计)
机器人
人工智能
计算机视觉
算法
移动机器人
图像(数学)
数学
几何学
作者
Liuxin Sun,Junyu Wei,Shaojing Su,Peng Wu
出处
期刊:Sensors
[MDPI AG]
日期:2022-09-15
卷期号:22 (18): 6977-6977
被引量:2
摘要
Simultaneous localization and mapping (SLAM) is a core technology for mobile robots working in unknown environments. Most existing SLAM techniques can achieve good localization accuracy in static scenes, as they are designed based on the assumption that unknown scenes are rigid. However, real-world environments are dynamic, resulting in poor performance of SLAM algorithms. Thus, to optimize the performance of SLAM techniques, we propose a new parallel processing system, named SOLO-SLAM, based on the existing ORB-SLAM3 algorithm. By improving the semantic threads and designing a new dynamic point filtering strategy, SOLO-SLAM completes the tasks of semantic and SLAM threads in parallel, thereby effectively improving the real-time performance of SLAM systems. Additionally, we further enhance the filtering effect for dynamic points using a combination of regional dynamic degree and geometric constraints. The designed system adds a new semantic constraint based on semantic attributes of map points, which solves, to some extent, the problem of fewer optimization constraints caused by dynamic information filtering. Using the publicly available TUM dataset, SOLO-SLAM is compared with other state-of-the-art schemes. Our algorithm outperforms ORB-SLAM3 in accuracy (maximum improvement is 97.16%) and achieves better results than Dyna-SLAM with respect to time efficiency (maximum improvement is 90.07%).
科研通智能强力驱动
Strongly Powered by AbleSci AI