一种低数据传输的多机器人实时视觉SLAM  

A Real-time Multi-robot Visual SLAM with Lower Data Transmission

作　　者：段胜青 熊智[1,2] 赵耀 崔雨晨[1] 周帅琳 DUAN Sheng-qing;XIONG Zhi;ZHAO Yao;CUI Yu-chen;ZHOU Shuai-lin(College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;Key Laboratory of Navigation, Guidance and Health-Management Technologies of Advanced Aerocraft, Ministry of Industry and Information Technology, Nanjing 211106, China)

机构地区：[1]南京航空航天大学自动化学院,南京211106 [2]先进飞行器导航、控制与健康管理工业和信息化部重点实验室,南京211106

出　　处：《导航定位与授时》2021年第5期71-78,共8页Navigation Positioning and Timing

基　　金：国家自然科学基金(61873125);江苏省自然科学基金(BK20181291);中央高校基本科研业务费专项资金(NZ2020004,NZ2019007);上海航天科技创新基金(SAST2019-085)。

摘　　要：针对多机器人视觉SLAM在实际应用中带宽受限的问题,设计了一种低数据传输的多机器人实时视觉SLAM系统。系统中引入了NetVLAD神经网络模型,通过改进NetVLAD降低了多机器人回环检测的计算资源占用,提高了回环检测的实时性。提出了一种针对描述子缺失情况下的特征匹配算法,提高了回环检测与相对量测的鲁棒性,并提出了一种增量式多机器人位姿图共享和优化方法。最后,通过在KITTI数据集进行测试,验证了该SLAM系统能有效减少多机器人通信过程中的数据传输,具有与单机器人SLAM相当的定位精度和实时性。A real-time and low-data-transmission multi-robot visual SLAM system is designed for bandwidth limited environment.This system integrates a modified NetVLAD network,which has less computing resource occupation and better real-time performance during the multi-robot loop detection.A feature matching algorithm for the absence of descriptor information is proposed to improve the robustness of loop detection and relative measurement.Moreover,an incremental multi-robot pose graph sharing and optimization method is proposed.Finally,by testing on the KITTI dataset,it is verified that the proposed system has the same positioning accuracy and real-time performance as single-robot SLAM,and can effectively reduce data transmission.

关 键 词：多机器人SLAM 低数据传输 改进的NetVLAD 位姿图优化 

分 类 号：TP701[自动化与计算机技术—检测技术与自动化装置]