Development of Following Algorithm for Human-Following Robots using Deep-Learning Technology and Depth Camera

被引：0

作者：

Son H.-S. ^{[1
,3
]}

Kim D.-K. ^{[2
,3
]}

Yang S.-H. ^{[3
]}

机构：

[1] Department of Electrical Engineering, Pusan National University

[2] Interdisciplinary Program in Agricultural and Life Science, Chonnam National University

[3] Smart Agricultural Machinery R&D Group, Korea Institute of Industrial Technology

来源：

Journal of Institute of Control, Robotics and Systems | 2022年 / 28卷 / 02期

关键词：

Automated guided vehicle; Deep learning; Following robot; Mobile robot; Position measurement;

D O I：

10.5302/J.ICROS.2022.21.0226

中图分类号：

学科分类号：

摘要：

For robots that follow humans, the ability to estimate the location information of the robot and the person is essential. This paper proposes a method for estimating location information between a robot and a human, and evaluates the performance of the proposed method using a self-made mobile robot. In this paper, humans are recognized through the Tiny-YOLOv3 model and distance and angle information between the robot and the person is estimated using a depth camera. The distance is obtained using the depth image of the recognized person, and the angle is obtained using the recognized person-centered X pixel. In an experiment measuring distance and angle at five points, the average error of the distance was 0.077m and the average error of the angle was 0.675°. Through real-time human-following experiments, it was confirmed that the proposed method can be used to control human-following robots. © ICROS 2022.

引用

页码：95 / 101

页数：6

共 13 条

[1]

Sathyamoorthy A.J., Patel U., Savle Y.A., Paul M., Manocha D., Covid-Robot: Monitoring Social Distancing Constraints in Crowded Scenarios

[2]

Fanti M.P., Mangini A.M., Roccotelli M., Silvestri B., Hospital drugs distribution with autonomous robot vehicles, 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), IEEE, pp. 1025-1030, (2020)

[3]

Jeong D.B., Ko N.Y., Song G.S., You S.H., Position and attitude estimation of a mobile robot in lie group, Journal of Institute of Control Robotics and Systems, 26, 12, pp. 1099-1108, (2020)

[4]

Seo D.-J., Noh S.-W., Ko N.-Y., Moving object following control for differential drive robot based on two distance sensors, The Journal of the Korea Institute of Electronic Communication Sciences, 6, 5, pp. 765-773, (2011)

[5]

People tracking using a robot in motion with laser range finder, IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2936-2942, (2006)

[6]

Scheutz M., McRaven J., Cserey G., Fast, reliable, adaptive, bimodal people tracking for indoor environments, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2, pp. 1347-1352, (2004)

[7]

Kim H.R., Cui X.N., Lee J.H., Lee S.J., Kim H., Person-following of a mobile robot using a complementary tracker with a camera-laser scanner, Journal of Institute of Control, 20, 1, pp. 78-86, (2014)

[8]

Heo S.N., Lee J.M., Predictive control of an efficient human following robot using Kinect sensor, Journal of Institute of Control, 20, 9, pp. 957-963, (2014)

[9]

Yin X., Noguchi N., Choi J., Development of a target recognition and following system for a field robot, Computers and Electronics in Agriculture, 98, pp. 17-24, (2013)

[10]

Lee S., Choi J.W., van Dang C., Kim J.W., Development of human following method of mobile robot using QR code and 2D LiDAR sensor, IEMEK Journal of Embedded Systems and Applications, 15, 1, pp. 35-42, (2020)

← 1 2 →