SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based System
Currently, deep learning and IoT collaboration is heavily invading automotive applications especially in autonomous driving throughout successful assistance functionalities. Crash avoidance, path planning, and automatic emergency braking are essential functionalities for autonomous driving. Trigger-...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/23/9108 |
| _version_ | 1797462170052591616 |
|---|---|
| author | Mohammed Abdou Hanan Ahmed Kamal |
| author_facet | Mohammed Abdou Hanan Ahmed Kamal |
| author_sort | Mohammed Abdou |
| collection | DOAJ |
| description | Currently, deep learning and IoT collaboration is heavily invading automotive applications especially in autonomous driving throughout successful assistance functionalities. Crash avoidance, path planning, and automatic emergency braking are essential functionalities for autonomous driving. Trigger-action-based IoT platforms are widely used due to its simplicity and ability of doing receptive tasks accurately. In this work, we propose SDC-Net system: an end-to-end deep learning IoT hybrid system in which a multitask neural network is trained based on different input representations from a camera-cocoon setup installed in CARLA simulator. We build our benchmark dataset covering different scenarios and corner cases that the vehicle may expose in order to navigate safely and robustly while testing. The proposed system aims to output relevant control actions for crash avoidance, path planning and automatic emergency braking. Multitask learning with a bird’s eye view input representation outperforms the nearest representation in precision, recall, f1-score, accuracy, and average MSE by more than 11.62%, 9.43%, 10.53%, 6%, and 25.84%, respectively. |
| first_indexed | 2024-03-09T17:32:41Z |
| format | Article |
| id | doaj.art-4245d29a5938453ca9c5b0e480c10f5f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T17:32:41Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4245d29a5938453ca9c5b0e480c10f5f2023-11-24T12:08:45ZengMDPI AGSensors1424-82202022-11-012223910810.3390/s22239108SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based SystemMohammed Abdou0Hanan Ahmed Kamal1Valeo Egypt, Cairo 12577, EgyptDepartment of Electronics and Communications Engineering, Faculty of Engineering, Cairo University, Giza 12613, EgyptCurrently, deep learning and IoT collaboration is heavily invading automotive applications especially in autonomous driving throughout successful assistance functionalities. Crash avoidance, path planning, and automatic emergency braking are essential functionalities for autonomous driving. Trigger-action-based IoT platforms are widely used due to its simplicity and ability of doing receptive tasks accurately. In this work, we propose SDC-Net system: an end-to-end deep learning IoT hybrid system in which a multitask neural network is trained based on different input representations from a camera-cocoon setup installed in CARLA simulator. We build our benchmark dataset covering different scenarios and corner cases that the vehicle may expose in order to navigate safely and robustly while testing. The proposed system aims to output relevant control actions for crash avoidance, path planning and automatic emergency braking. Multitask learning with a bird’s eye view input representation outperforms the nearest representation in precision, recall, f1-score, accuracy, and average MSE by more than 11.62%, 9.43%, 10.53%, 6%, and 25.84%, respectively.https://www.mdpi.com/1424-8220/22/23/9108autonomous drivingdeep learningcomputer visionmultitask learningcrash avoidancepath planning |
| spellingShingle | Mohammed Abdou Hanan Ahmed Kamal SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based System Sensors autonomous driving deep learning computer vision multitask learning crash avoidance path planning |
| title | SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based System |
| title_full | SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based System |
| title_fullStr | SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based System |
| title_full_unstemmed | SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based System |
| title_short | SDC-Net: End-to-End Multitask Self-Driving Car Camera Cocoon IoT-Based System |
| title_sort | sdc net end to end multitask self driving car camera cocoon iot based system |
| topic | autonomous driving deep learning computer vision multitask learning crash avoidance path planning |
| url | https://www.mdpi.com/1424-8220/22/23/9108 |
| work_keys_str_mv | AT mohammedabdou sdcnetendtoendmultitaskselfdrivingcarcameracocooniotbasedsystem AT hananahmedkamal sdcnetendtoendmultitaskselfdrivingcarcameracocooniotbasedsystem |