Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal SPEKTRUM
Cokorda Gde Wahyu Pramana
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
RANCANG BANGUN OBJECT DETECTION PADA ROBOT SOCCER MENGGUNAKAN METODE SINGLE SHOT MULTIBOX DETECTOR (SSD MOBILENETV2) Cokorda Gde Wahyu Pramana; Duman Care Khrisne; Nyoman Putra Sastra
Jurnal SPEKTRUM Vol 8 No 2 (2021): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (621.454 KB) | DOI: 10.24843/SPEKTRUM.2021.v08.i02.p4

Abstract

Artificial intelligence or AI is a technology that emphasizes machine intelligence in respondinglike humans, developed to help support human work. AI has widely applied in various fieldssuch as industry, medical, education, business, and robotics. The development of AI in the fieldof robotics produces autonomous robots, one example is the KRSBI-Beroda soccer robot. Thisresearch discusses the application of AI in the design of object detection systems using thesingle-shot multibox detector (SSD) model on the KRSBI-Beroda soccer robot. This study aimsto produce an AI model in the form of an artificial neural network (ANN) implanted in the soccerrobot to distinguish between ball, goal, robot, and obstacle objects. This object detection systemwas built using a deep learning method assisted by the TensorFlow Object Detection APIframework using the MobileNetV2 SSD model which is run using the python programminglanguage on the NVIDIA Jetson Nano board which is integrated into the C922 Pro webcamcamera. The model was built using a dataset of 977 images consisting of 3064 objects thatwere trained as many as 200,000 steps on Google Colaboratory. The results showed a modelwith an average mAP of 0.80 with an average total loss of 1.5. Validation of the model resultedin a success rate of object prediction with an average accuracy of up to 98.45%.
Co-Authors Duman Care Khrisne Nyoman Putra Sastra