Abstract
Autonomous parking is a valuable feature in many mobile robot applications. As compared to self-driving automobiles, auto-parking is more challenging for a small scale robot equipped with a front camera only, due to the camera view limited by the height of robot and the narrow Field of View (FOV) provided by the inexpensive camera. In this research, auto-parking of such a small scale mobile robot is accomplished in a four-step process: identification of available parking space using transfer learning based on the AlexNet; image processing for the detection of parking space boundary lines; kinematics-based target prediction when the parking space disappears from the camera view partially or completely; and motion control on the robot navigating towards the center of the parking space. Results show that a 95% accuracy has been achieved on identification of available parking spaces. The detection of boundary lines and prediction of target have also been successfully implemented in MATLAB. The testing of motion control and image capture for deep learning is performed on a self-built small-scale mobile robot.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
West, J., Ventura, D., Warnick, S.: Spring research presentation: a theoretical foundation for inductive transfer. Brigham Young Univ. Coll. Phys. Math. Sci. 1, 8 (2007)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Duda, R.O., Hart, P.E.: Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM 15(1), 11–15 (1972)
Li, L., Zhang, L., Li, X., Liu, X., Shen, Y., Xiong, L.: Vision-based parking-slot detection: a benchmark and a learning-based approach. In: Proceedings of 2017 IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, pp. 649–654(2017)
Singh, A., Chandra, A., Priyadarshni, D., Joshi, N.: Self parking car prototype. In: Proceedings of 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Bangalore, India, pp. 2251–2254 (2018)
Wu, T.-F., Tsai, P.-S., Hu, N.-T., Chen, J.-Y.: Research and implementation of auto parking system based on ultrasonic sensors. In: Proceedings of International Conference on Advanced Materials for Science and Engineering (ICAMSE), Taiwan (2016)
Shet, A.J., Killikyatar, A., Kumar, A., Ropmay, F.B.: Autonomous self-parking robot, In: Proceedings of 2018 International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C), Bangalore, India (2018)
ROBOTIS e-Manual: TurtleBot3. https://emanual.robotis.com/docs/en/platform/turtlebot3/autonomous_driving/#autonomous-driving
Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679–698 (1986)
Beggs, J.S.: Kinematics, Springer-Verlag, Berlin (1983)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, M., Ni, L.G. (2022). Small Scale Mobile Robot Auto-parking Using Deep Learning, Image Processing, and Kinematics-Based Target Prediction. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2021. Lecture Notes in Networks and Systems, vol 296. Springer, Cham. https://doi.org/10.1007/978-3-030-82199-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-82199-9_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82198-2
Online ISBN: 978-3-030-82199-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)