摘要
本文设计了一辆多传感器融合的无人配送小车,并且在校园环境下进行了实车配送实验。系统采用Jetson nano实现上层视觉检测,采用STM32与Pixhawk飞控联合控制小车底盘,采用YOLOv4-Tiny算法进行行人检测与局部路径的避障,采用L1制导算法完成无人配送小车的全局路径规划。无人配送小车成功完成了校园配送实验,运行稳定,具备良好的人机交互功能,在提升校园配送灵活性、保障疫情下校园安全防护等方面具有重要意义。
A multi-sensor unmanned distribution vehicle is designed in this paper, and the unmanned vehicle is subjected to real distribution experiments in the campus. Jetson nano is used as the upper computer to realize target detection, the car chassis is controlled by STM32 unit and Pixhawk flight controller unit, Yolov4-tiny algorithm is used for pedestrian detection and obstacle avoidance in local path, and L1guidance algorithm is used to complete the global path planning of the unmanned distribution vehicle. The unmanned distribution vehicle has successfully completed the campus distribution experiment, it is proved by experiments that the unmanned distribution vehicle performs well both in stability and man-machine interaction, and the research of distribution vehicle has great influence in improving the flexibility of campus distribution and strengthening campus safety protection under the epidemic situation.
作者
方博汇
杨璐
王冰倩
李浩铭
康喜乐
张海凤
赵晨阳
FANG Bo-hui;YANG Lu;WANG Bing-qian;LI Hao-ming;KANG Xi-le;ZHANG Hai-feng;ZHAO Chen-yang(Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control,Tianjin University of Technology,Tianjin 300384 China;National Demonstration Center for Experimental Mechanical and Electrical Engineering Education,Tianjin University of Technology,Tianjin 300384 China;School of Computer Science and Engineering,Tianjin University of Technology,Tianjin 300384 China)
出处
《科技创新与生产力》
2022年第11期103-108,111,共7页
Sci-tech Innovation and Productivity
关键词
无人配送小车
校园配送
多传感器融合
行人检测
路径规划
unmanned distribution vehicle
campus distribution
multi-sensor fusion
pedestrian detection
path planning
