TinyLidarNet: 2D LiDAR-based End-to-End Deep Learning Model for F1TENTH Autonomous Racing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917799887110144 |
|---|---|
| author | Zarrar, Mohammed Misbah Weng, Qitao Yerjan, Bakhbyergyen Soyyigit, Ahmet Yun, Heechul |
| author_facet | Zarrar, Mohammed Misbah Weng, Qitao Yerjan, Bakhbyergyen Soyyigit, Ahmet Yun, Heechul |
| contents | Prior research has demonstrated the effectiveness of end-to-end deep learning for robotic navigation, where the control signals are directly derived from raw sensory data. However, the majority of existing end-to-end navigation solutions are predominantly camera-based. In this paper, we introduce TinyLidarNet, a lightweight 2D LiDAR-based end-to-end deep learning model for autonomous racing. An F1TENTH vehicle using TinyLidarNet won 3rd place in the 12th F1TENTH Autonomous Grand Prix competition, demonstrating its competitive performance. We systematically analyze its performance on untrained tracks and computing requirements for real-time processing. We find that TinyLidarNet's 1D Convolutional Neural Network (CNN) based architecture significantly outperforms widely used Multi-Layer Perceptron (MLP) based architecture. In addition, we show that it can be processed in real-time on low-end micro-controller units (MCUs). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07447 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TinyLidarNet: 2D LiDAR-based End-to-End Deep Learning Model for F1TENTH Autonomous Racing Zarrar, Mohammed Misbah Weng, Qitao Yerjan, Bakhbyergyen Soyyigit, Ahmet Yun, Heechul Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Prior research has demonstrated the effectiveness of end-to-end deep learning for robotic navigation, where the control signals are directly derived from raw sensory data. However, the majority of existing end-to-end navigation solutions are predominantly camera-based. In this paper, we introduce TinyLidarNet, a lightweight 2D LiDAR-based end-to-end deep learning model for autonomous racing. An F1TENTH vehicle using TinyLidarNet won 3rd place in the 12th F1TENTH Autonomous Grand Prix competition, demonstrating its competitive performance. We systematically analyze its performance on untrained tracks and computing requirements for real-time processing. We find that TinyLidarNet's 1D Convolutional Neural Network (CNN) based architecture significantly outperforms widely used Multi-Layer Perceptron (MLP) based architecture. In addition, we show that it can be processed in real-time on low-end micro-controller units (MCUs). |
| title | TinyLidarNet: 2D LiDAR-based End-to-End Deep Learning Model for F1TENTH Autonomous Racing |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2410.07447 |