TY - GEN
T1 - Obstacle-Avoidance Algorithm Using Deep Learning Based on RGBD Images and Robot Orientation
AU - Saleem, Ashraf
AU - Jabri, Khadija Al
AU - Maashri, Ahmed Al
AU - Maawali, Waleed Al
AU - Mesbah, Mostafa
N1 - Funding Information:
ACKNOWLEDGMENT This work was funded in part by Omantel (EG/SQU-OT/19/05) and BP Oman (EG/ENG/ECED/18/01).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/4
Y1 - 2020/4
N2 - Inspired by the advantages of the hierarchical feature extraction of deep learning, this work investigates the development of a Convolutional Neural Network (CNN) algorithm to solve the problem of the mobile robot obstacle avoidance in an indoor environment. The algorithm takes raw images and robot orientation as input and generates control commands as network output. Control commands include go-straight-forward, turn-full-left, turn-half-left, turn-full-right, and turn-half-right. A dataset compiled using depth images (RGBD) and robot orientation data obtained by an Inertial Measurement Unit (IMU). In addition, the performance of the algorithm in terms of training options, hyperparameters, and output precision is evaluated and recommendations are provided accordingly. The final results show that the accuracy can be improved by including the robot orientation in the dataset, increasing the size of data, and tuning the network's hyperparameters. The CNN algorithm has shown great potential to get high path classification accuracy for obstacle avoidance for mobile robots.
AB - Inspired by the advantages of the hierarchical feature extraction of deep learning, this work investigates the development of a Convolutional Neural Network (CNN) algorithm to solve the problem of the mobile robot obstacle avoidance in an indoor environment. The algorithm takes raw images and robot orientation as input and generates control commands as network output. Control commands include go-straight-forward, turn-full-left, turn-half-left, turn-full-right, and turn-half-right. A dataset compiled using depth images (RGBD) and robot orientation data obtained by an Inertial Measurement Unit (IMU). In addition, the performance of the algorithm in terms of training options, hyperparameters, and output precision is evaluated and recommendations are provided accordingly. The final results show that the accuracy can be improved by including the robot orientation in the dataset, increasing the size of data, and tuning the network's hyperparameters. The CNN algorithm has shown great potential to get high path classification accuracy for obstacle avoidance for mobile robots.
KW - computer vision
KW - deep learning
KW - mobile robot
KW - obstacle avoidance
UR - http://www.scopus.com/inward/record.url?scp=85086465463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086465463&partnerID=8YFLogxK
U2 - 10.1109/ICEEE49618.2020.9102526
DO - 10.1109/ICEEE49618.2020.9102526
M3 - Conference contribution
AN - SCOPUS:85086465463
T3 - 2020 7th International Conference on Electrical and Electronics Engineering, ICEEE 2020
SP - 268
EP - 272
BT - 2020 7th International Conference on Electrical and Electronics Engineering, ICEEE 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on Electrical and Electronics Engineering, ICEEE 2020
Y2 - 14 April 2020 through 16 April 2020
ER -