Single Camera Data Augmentation in End-To-End Deep Learning Simulated Self-Driving Car
Developing a self-driving car is a daunting task. Usually there are multiple steps involved in the learning pipeline to generate a feasible model. This research offers an alternative approach using end-to-end deep learning with vast data generated from a simulated environment. The dataset, combin...
| Main Authors: | , , , |
|---|---|
| Format: | Other |
| Language: | English |
| Published: |
ICIC Express Letters, Part B: Applications
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/283882/1/SINGLE-CAMERA-DATA-AUGMENTATION-IN-ENDTOEND-DEEP-LEARNING-SIMULATED-SELFDRIVING-CARICIC-Express-Letters-Part-B-Applications.pdf |
| _version_ | 1797037756795322368 |
|---|---|
| author | Timur, Muhammad Idham Ananta Istiyanto, Jazi Eko Dharmawan, Andi Setiadi, Beatrice Paulina |
| author_facet | Timur, Muhammad Idham Ananta Istiyanto, Jazi Eko Dharmawan, Andi Setiadi, Beatrice Paulina |
| author_sort | Timur, Muhammad Idham Ananta |
| collection | UGM |
| description | Developing a self-driving car is a daunting task. Usually there are multiple
steps involved in the learning pipeline to generate a feasible model. This research offers
an alternative approach using end-to-end deep learning with vast data generated from a
simulated environment. The dataset, combined with data augmentation, is expected to
contain enough features to be learned. The dataset for training is taken by manually
driving the car, using the record feature in the simulator to store the dataset. It consists
of vehicle’s driving behaviour labels and images which are taken from a single camera
mounted on the car’s dashboard. Convolutional Neural Network (CNN) is used to pro-
cess the copy and labels of the dataset while training the model. The result of this research
is a simulation that is able to steer the car, in which the trained model makes the pre-
dictions for the steering angle based on image input from the camera. The accuracy of
the trained model is measured through the RMSE calculation, which results in a value of
0.178. We also evaluate the model according to their time and distance in autonomous
driving testing from different start points on the map. |
| first_indexed | 2024-03-14T00:08:49Z |
| format | Other |
| id | oai:generic.eprints.org:283882 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-14T00:08:49Z |
| publishDate | 2022 |
| publisher | ICIC Express Letters, Part B: Applications |
| record_format | dspace |
| spelling | oai:generic.eprints.org:2838822023-11-24T09:09:56Z https://repository.ugm.ac.id/283882/ Single Camera Data Augmentation in End-To-End Deep Learning Simulated Self-Driving Car Timur, Muhammad Idham Ananta Istiyanto, Jazi Eko Dharmawan, Andi Setiadi, Beatrice Paulina Electrical and Electronic Engineering Developing a self-driving car is a daunting task. Usually there are multiple steps involved in the learning pipeline to generate a feasible model. This research offers an alternative approach using end-to-end deep learning with vast data generated from a simulated environment. The dataset, combined with data augmentation, is expected to contain enough features to be learned. The dataset for training is taken by manually driving the car, using the record feature in the simulator to store the dataset. It consists of vehicle’s driving behaviour labels and images which are taken from a single camera mounted on the car’s dashboard. Convolutional Neural Network (CNN) is used to pro- cess the copy and labels of the dataset while training the model. The result of this research is a simulation that is able to steer the car, in which the trained model makes the pre- dictions for the steering angle based on image input from the camera. The accuracy of the trained model is measured through the RMSE calculation, which results in a value of 0.178. We also evaluate the model according to their time and distance in autonomous driving testing from different start points on the map. ICIC Express Letters, Part B: Applications 2022 Other NonPeerReviewed application/pdf en https://repository.ugm.ac.id/283882/1/SINGLE-CAMERA-DATA-AUGMENTATION-IN-ENDTOEND-DEEP-LEARNING-SIMULATED-SELFDRIVING-CARICIC-Express-Letters-Part-B-Applications.pdf Timur, Muhammad Idham Ananta and Istiyanto, Jazi Eko and Dharmawan, Andi and Setiadi, Beatrice Paulina (2022) Single Camera Data Augmentation in End-To-End Deep Learning Simulated Self-Driving Car. ICIC Express Letters, Part B: Applications. https://www.researchgate.net/publication/363731195_SINGLE_CAMERA_DATA_AUGMENTATION_IN_END-TO-END_DEEP_LEARNING_SIMULATED_SELF-DRIVING_CAR 10.24507/icicelb.13.09.975 |
| spellingShingle | Electrical and Electronic Engineering Timur, Muhammad Idham Ananta Istiyanto, Jazi Eko Dharmawan, Andi Setiadi, Beatrice Paulina Single Camera Data Augmentation in End-To-End Deep Learning Simulated Self-Driving Car |
| title | Single Camera Data Augmentation in End-To-End Deep
Learning Simulated Self-Driving Car |
| title_full | Single Camera Data Augmentation in End-To-End Deep
Learning Simulated Self-Driving Car |
| title_fullStr | Single Camera Data Augmentation in End-To-End Deep
Learning Simulated Self-Driving Car |
| title_full_unstemmed | Single Camera Data Augmentation in End-To-End Deep
Learning Simulated Self-Driving Car |
| title_short | Single Camera Data Augmentation in End-To-End Deep
Learning Simulated Self-Driving Car |
| title_sort | single camera data augmentation in end to end deep learning simulated self driving car |
| topic | Electrical and Electronic Engineering |
| url | https://repository.ugm.ac.id/283882/1/SINGLE-CAMERA-DATA-AUGMENTATION-IN-ENDTOEND-DEEP-LEARNING-SIMULATED-SELFDRIVING-CARICIC-Express-Letters-Part-B-Applications.pdf |
| work_keys_str_mv | AT timurmuhammadidhamananta singlecameradataaugmentationinendtoenddeeplearningsimulatedselfdrivingcar AT istiyantojazieko singlecameradataaugmentationinendtoenddeeplearningsimulatedselfdrivingcar AT dharmawanandi singlecameradataaugmentationinendtoenddeeplearningsimulatedselfdrivingcar AT setiadibeatricepaulina singlecameradataaugmentationinendtoenddeeplearningsimulatedselfdrivingcar |