| 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。 |
| 关键词: 多机器人SLAM 低数据传输 改进的NetVLAD 位姿图优化 |
| DOI： |
|
| 基金项目: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） |
|
| A Real-time Multi-robot Visual SLAM with Lower Data Transmission |
| 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;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) |
| Abstract: |
| 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. |
| Key words: Multi-robot SLAM Low data transmission Modified NetVLAD Pose graph optimization |
