ISBN: 978-981-18-7950-0 DOI: 10.18178/wcse.2023.06.029
Algorithm for Mobile Robot Localization Based on Recurrent Convolutional Neural Networks
Abstract—Mobile robot localization has been considered to be an important task in the field of robotics research. Recurrent Convolution Neural Networks -based Mobile Robot Localization (RCNN-MRL) Algorithm is proposed in this paper. RCNN-MRL estimates self-position from the first person view captured by a camera on a robot using Recurrent Convolution Neural Networks (RCNN).It uses a regression model for localization using RCNN capable of processing consecutive images. We use simulated environments where a two-wheel robot moves randomly, and analyze the performance of localization. Our experiments show that RCNN model can estimate the self-position of the robot.
Index Terms—Mobile Robot , Localization, Convolution Neural Networks , two-wheel robot, Time Series Image
Li Shaowei, Xiang Cairong
School of Artificial Intelligence, Jianghan University, CHINA
Cite: Li Shaowei, Xiang Cairong, "Algorithm for Mobile Robot Localization Based on Recurrent Convolutional Neural Networks" Proceedings of 2023 the 13th International Workshop on Computer Science and Engineering (WCSE 2023), pp. 202-208, June 16-18, 2023.