An Obstacle Avoidance Method for Indoor Flaw Detection Unmanned Robot Based on Transfer Neural Network
Publication: Earth and Space 2021
ABSTRACT
The unmanned vehicle can automatically evaluate the structural safety of the building by carrying a visual crack detection camera. However, the complexity of layout within the building requires that unmanned flaw detection robot has high obstacle avoidance performance. Aiming at the difficulty of obstacle avoidance in complex environment, the direction control method based on image sensor is adopted. The image is transmitted to the convolution neural network (CNN), and the direction instruction of the neural network is output to the motor driver to realize the autonomous obstacle avoidance of the wheeled robot. Data sets are automatically classified by arranging camera arrays. In this paper, the transfer neural network is used to reconstruct the neural network by discarding the last three layers and setting up new three layers. The accuracy of the neural network trained by the simulation results can reach 89.01%.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Akbar M. A., Qidwai U., and Jahanshahi M. R. An evaluation of image-based structural health monitoring using integrated unmanned aerial vehicle platform[J]. Structural Control and Health Monitoring, 2019, 26(1): e2276.
Chen C. Y., Chang S. Y., and Wu C. T. Path planning and obstacle avoidance for omni-directional mobile robot based on Kinect depth sensor[J]. International Journal of Embedded Systems, 2016, 8(4): 343-351.
Chen J. D., Kim P., Cho Y. K., and Ueda J. Object-sensitive potential fields for mobile robot navigation and mapping in indoor environments[c]//15th International Conference on Ubiquitous Robots. Honolulu, HI, USA: 2018: 328-333.
Duan Y., Sheng D. L., and Yu X. Mobile robot environment detection and behavior learning based on Kinect sensor[J]. Chinese High Technology Letters, 2016, 26(01):8-15.
Gandhi D., Pinto L., and Gupta A. Learning to fly by crashing[c]// IEEE International Conference on Intelligent Robots and Systems. Vancouver, BC, Canada: 2017: 3948-3955.
Huang L., Zhu M., and Zhang W. F. Navigation method for indoor robot based on artificial landmark[J]. Computer Systems & Application, 2017, 26(07):1-9.
Kang D., and Cha Y. J. Autonomous UAVs for structural health monitoring using deep learning and an ultrasonic beacon system with geo-tagging[J]. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(10): 885-902.
Lee H. J., and Hwang S. S. Obstacle avoidance algorithm for indoor autonomous drone using IR sensor and forward image information[J]. Journal of Institute of Control, Robotics and Systems, 2017, 23(9): 803-809.
Li C. Y., Cai J., Fang A. Q., and Yang K. The robot navigation algorithm based on multi-sensor[J]. Machinery Design & Manufacture, 2017(05):238-240+244.
Lu X. H., and Zhang G. L. Summarization on indoor service robot navigation[J]. Robot, 2003, 25(1):80-87.
Ma L. H., Fan C. G., Wang S. P., and Zhou W. On the obstacle avoidance system for mobile robots based on depth image in indoor condition[J]. Journal of Zhejiang Normal University (Natural Sciences), 2016, 39(03):276-282.
Sanchezgarcia A. J., Riosfigueroa H. V., Marinhernandez A., et al. Decision making for obstacle avoidance in autonomous mobile robots by time to contact and optical flow[C]// International Conference on Electronics. Cholula, Mexico: 2015: 130-134.
Shin J. U., Kim D., Kim J. H., et al. Micro-aerial vehicle type wall-climbing robot mechanism for structural health monitoring[C]//Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2013. International Society for Optics and Photonics, 2013, 8692: 86921B.
Wang S. B., Liu H. T., Han Y., et al. Low-altitude remote sensing based on convolutional neural network for weed classification in ecological irrigation area[J]. IFAC-PapersOnLine, 2018, 51(17): 298-303.
Wang X. F., Zhang L. L., Hu X. X., Zhang P. Research on obstacle avoidance of robot based on monocular vision[J]. Navigation and Control, 2018, 17(01):56-64.
Xiang Y. J., and Yan H. Obstacle avoidance for mobile robots strategy based on laser radar[J]. Journal of Sichuan University (Natural Science Edition), 2017, 54(03):529-534.
Yang G. T., and Gao M. M. Research on obstacle avoidance and motion planning of indoor mobile service robot[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2011, 39(SUPPL.2): 275-278.
Yuan R., Lv Y., Kong Q., and Song G. Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network. Smart Materials and Structures, 2019, 28(12), 125001.
Zhang H., and Zhang B. W. Dynamic obstacle avoidance based on binocular vision for AS-R mobile robots[J]. Mechanical Engineering & Automation, 2016(03):139-140+142.
Zhao Y., Ma J., Li X., et al. Saliency detection and deep learning-based wildfire identification in UAV imagery[J]. Sensors, 2018, 18(3):712.
Zheng L., Cheng H., Huo L., et al. Monitor concrete moisture level using percussion and machine learning[J]. Construction and Building Materials, 2019, 229: 117077.
Zhou Q., Zou D. P., and Liu P. L. Hybrid obstacle avoidance system with vision and ultrasonic sensors for multi-rotor MAVs[J]. Industrial Robot, 2018, 45(2): 227-236.
Zhu Q. D., Liu Peng, and Cai C. T. Robust method of indoor robot localization based on artificial landmark[J]. Journal of Computer Applications, 2017, 23(S1):126-130+136.
Information & Authors
Information
Published In
Copyright
© 2021 American Society of Civil Engineers.
History
Published online: Apr 15, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.