Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.06473 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913346096201728 |
|---|---|
| author | Jukić, Ana Petra Šelek, Ana Seder, Marija Žarko, Ivana Podnar |
| author_facet | Jukić, Ana Petra Šelek, Ana Seder, Marija Žarko, Ivana Podnar |
| contents | The technology of autonomous driving is currently attracting a great deal of interest in both research and industry. In this paper, we present a deep learning dual-model solution that uses two deep neural networks for combined braking and steering in autonomous vehicles. Steering control is achieved by applying the NVIDIA's PilotNet model to predict the steering wheel angle, while braking control relies on the use of MobileNet SSD. Both models rely on a single front-facing camera for image input. The MobileNet SSD model is suitable for devices with constrained resources, whereas PilotNet struggles to operate efficiently on smaller devices with limited resources. To make it suitable for such devices, we modified the PilotNet model using our own original network design and reduced the number of model parameters and its memory footprint by approximately 60%. The inference latency has also been reduced, making the model more suitable to operate on resource-constrained devices. The modified PilotNet model achieves similar loss and accuracy compared to the original PilotNet model. When evaluated in a simulated environment, both autonomous driving systems, one using the modified PilotNet model and the other using the original PilotNet model for steering, show similar levels of autonomous driving performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06473 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Autonomous Driving with a Deep Dual-Model Solution for Steering and Braking Control Jukić, Ana Petra Šelek, Ana Seder, Marija Žarko, Ivana Podnar Robotics Computer Vision and Pattern Recognition The technology of autonomous driving is currently attracting a great deal of interest in both research and industry. In this paper, we present a deep learning dual-model solution that uses two deep neural networks for combined braking and steering in autonomous vehicles. Steering control is achieved by applying the NVIDIA's PilotNet model to predict the steering wheel angle, while braking control relies on the use of MobileNet SSD. Both models rely on a single front-facing camera for image input. The MobileNet SSD model is suitable for devices with constrained resources, whereas PilotNet struggles to operate efficiently on smaller devices with limited resources. To make it suitable for such devices, we modified the PilotNet model using our own original network design and reduced the number of model parameters and its memory footprint by approximately 60%. The inference latency has also been reduced, making the model more suitable to operate on resource-constrained devices. The modified PilotNet model achieves similar loss and accuracy compared to the original PilotNet model. When evaluated in a simulated environment, both autonomous driving systems, one using the modified PilotNet model and the other using the original PilotNet model for steering, show similar levels of autonomous driving performance. |
| title | Autonomous Driving with a Deep Dual-Model Solution for Steering and Braking Control |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.06473 |