Short Title: Int. J. Mech. Eng. Robot. Res.
Frequency: Bimonthly
Professor of School of Engineering, Design and Built Environment, Western Sydney University, Australia. His research interests cover Industry 4.0, Additive Manufacturing, Advanced Engineering Materials and Structures (Metals and Composites), Multi-scale Modelling of Materials and Structures, Metal Forming and Metal Surface Treatment.
2024-10-25
2024-09-24
Abstract—The environmental perception is very important for autonomous intelligent ground robots in the outdoor areas. One of the essential tasks for these robots is to detect the unstructured regions autonomously with low computational complexity. Thus, this paper presents the modeling of a computer vision-based robot which is capable of adjusting itself into various structured and unstructured environments. To resolve the variety of road types, the learning algorithm architecture is designed to formulate the problem as a sequential road type classification. The classification is designed to contain two types: normal road and curved road. In normal road, the vanishing point estimated is proposed by using the artificial neural network. Then, the appearance model based upon multivariate Gaussian is quickly constructed from a sample region that is determined by the vanishing point and dominant left and right borders. The trapezoidal fuzzy membership functions is proposed to find the threshold value that depends on the orientation of pixel and given regions to ensure the accuracy of the segmentation. In curved road, the improved Fuzzy C-means algorithm which is fast superpixel algorithm based upon membership filtering is implemented. This provides the full capability of achieving better pre-segmentation results with significantly shorter runtime and more robustly results. The proposed approach is evaluated by using two datasets. Implementation the proposed method on the rover bogie robot has shown its ability in the real-time navigation. Index Terms—ConvNets, fuzzy logic, detection, road detection, vanishing point Cite: Rami A. AL-Jarrah, "Intelligent Vision-Based Real-Time Detection for Rough Terrain Navigation Robot," International Journal of Mechanical Engineering and Robotics Research, Vol. 10, No. 12, pp. 645-659, December 2021. DOI: 10.18178/ijmerr.10.12.645-659 Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.