TY - GEN
T1 - Soccer Robot Localization Based on Sensor Fusion From Odometry and Omnivision
AU - Ismail, Muhammad Azhar
AU - Purwanto, Djoko
AU - Arifin, Achmad
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Mobile robots have ability to move their entire body and doing some tasks automatically. One of them is RoboCup Middle Size League (MSL) soccer robot. Main systems in the MSL robots are a self-localization. Localization system is very important because it can help some important aspects such as ability to navigate and control. The common localization method of mobile robots is odometry because the process is fast, but the weakness is that the error from odometry will increase over time due to gyro drifting and encoder wheels are slipping. Meanwhile, MSL robots generally use omnivision with the particle filter method for localization. Localization error with omnivision does not increase over time but requires heavy computational processing. Therefore, a sensor fusion system was designed to combine odometry and omnivision. Thus, they can cover each other's disadvantages, and make localization become more accurate. From the experimental results on the soccer field with size 9 m × 6 m, sensor fusion can provide good localization data. The localization error results x = 10.5 ± 7.8 cm, y = 7.6 ± 6.8 cm, and θ = 1.9 ± 1.2°, with average time response 1.6 ms. This system is expected to give soccer robot more accurate localization in Robocup MSL matches and help robot navigation when avoiding obstacles.
AB - Mobile robots have ability to move their entire body and doing some tasks automatically. One of them is RoboCup Middle Size League (MSL) soccer robot. Main systems in the MSL robots are a self-localization. Localization system is very important because it can help some important aspects such as ability to navigate and control. The common localization method of mobile robots is odometry because the process is fast, but the weakness is that the error from odometry will increase over time due to gyro drifting and encoder wheels are slipping. Meanwhile, MSL robots generally use omnivision with the particle filter method for localization. Localization error with omnivision does not increase over time but requires heavy computational processing. Therefore, a sensor fusion system was designed to combine odometry and omnivision. Thus, they can cover each other's disadvantages, and make localization become more accurate. From the experimental results on the soccer field with size 9 m × 6 m, sensor fusion can provide good localization data. The localization error results x = 10.5 ± 7.8 cm, y = 7.6 ± 6.8 cm, and θ = 1.9 ± 1.2°, with average time response 1.6 ms. This system is expected to give soccer robot more accurate localization in Robocup MSL matches and help robot navigation when avoiding obstacles.
KW - odometry
KW - omnivision
KW - particle filter
KW - self-localization
KW - sensor fusion
KW - soccer robot
UR - http://www.scopus.com/inward/record.url?scp=85137859325&partnerID=8YFLogxK
U2 - 10.1109/ISITIA56226.2022.9855313
DO - 10.1109/ISITIA56226.2022.9855313
M3 - Conference contribution
AN - SCOPUS:85137859325
T3 - 2022 International Seminar on Intelligent Technology and Its Applications: Advanced Innovations of Electrical Systems for Humanity, ISITIA 2022 - Proceeding
SP - 273
EP - 278
BT - 2022 International Seminar on Intelligent Technology and Its Applications
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd International Seminar on Intelligent Technology and Its Applications, ISITIA 2022
Y2 - 20 July 2022 through 21 July 2022
ER -