Outdoor mobile robot applications generally implement Global Positioning Systems (GPS) for localization tasks. However, GPS accuracy in outdoor localization has less accuracy in different environmental conditions. This paper presents two outdoor localization methods based on deep learning and landmark detection. The first localization method is based on the Faster Regional-Convolutional Neural Network (Faster R-CNN) landmark detection in the captured image. Then, a feedforward neural network (FFNN) is trained to determine robot location coordinates and compass orientation from detected landmarks. The second localization employs a single convolutional neural network (CNN) to determine location and compass orientation from the whole image. The dataset consists of images, geolocation data and labeled bounding boxes to train and test two proposed localization methods. Results are illustrated with absolute errors from the comparisons between localization results and reference geolocation data in the dataset. The experimental results pointed both presented localization methods to be promising alternatives to GPS for outdoor localization.
[1]
Satoshi Tadokoro,et al.
Consistent map building in petrochemical complexes for firefighter robots using SLAM based on GPS and LIDAR
,
2018
.
[2]
Vijay Kumar,et al.
System for deployment of groups of unmanned micro aerial vehicles in GPS-denied environments using onboard visual relative localization
,
2017,
Auton. Robots.
[3]
Yun Fu,et al.
Deep Geo-Constrained Auto-Encoder for Non-Landmark GPS Estimation
,
2019,
IEEE Transactions on Big Data.
[4]
Belhassen Bayar,et al.
Design Principles of Convolutional Neural Networks for Multimedia Forensics
,
2017,
Media Watermarking, Security, and Forensics.