Design and implementation of a novel obstacle avoidance scheme based on combination of CNN-based deep learning method and liDAR-based image processing approach

Issue title: Special Section: Ambient advancements in intelligent computational sciences

Guest editors: Shailesh Tiwari, Munesh Trivedi and Mohan L. Kohle

Article type: Research Article

Authors: Zhou, Chengmin^a | Li, Fei^{a; *} | Cao, Wen^b | Wang, Cao^a | Wu, Yihuai^a

Affiliations: [a] School of Cybersecurity, Chengdu University of Information Technology, Chengdu, China | [b] School of Information Engineering, Southwest University of Science and Technology, Mianyang, China

Correspondence: [*] Corresponding author. Fei Li, School of Cybersecurity, Chengdu University of Information Technology, Chengdu, China. E-mail: [email protected].

Abstract: Contrasted with common obstacle avoidance mode based on single sensor or solo algorithm, this article put forward an intelligent pattern based on Combination from CNN-based Deep Learning Method and liDAR-based Image Processing approach. As for Deep Learning method, a 10-layer Convolutional Neural Network (CNN) is designed which comes to a high recognition accuracy of 97 percent in Tensorflow and success rate of obstacle avoidance is over 90 percent. With regard to liDAR-based Image Processing approach, decision is made by a special method of counting the number of Point Cloud Data (PCD) which is generated by 2D liDAR and a success rate over 90 percent is achieved as well. When two kinds of methods work together, a robust success rate of 100 percent is realized. Meanwhile, Inertial Measurement Unit (IMU) and Xbox360 are taken into consideration for Pose Estimation and Data Collection. Finally, all functions are integrated in Robot Operation System (ROS) on platform of nVidia Jetson TX1.

Keywords: Obstacle avoidance, deep learning, collaborative system design, 2D liDAR, ROS

DOI: 10.3233/JIFS-169706

Journal: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 2, pp. 1695-1705, 2018