TinyLidarNet: 2D LiDAR-based End-to-End Deep Learning Model for F1TENTH Autonomous Racing

Mohammed Misbah Zarrar, Qitao Weng, Bakhbyergyen Yerjan, Ahmet Soyyigit, Heechul Yun
10/9/2024
cs.ROcs.AIcs.CV

No official code found. Best implementation: CSL-KU/TinyLidarNet (29 stars, last commit 2025-07-09).

Abstract

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).

View on arXivView PDF

Code Implementations(1)

CSL-KU/TinyLidarNetCommunity100%

2D LiDAR based end-to-end (E2E) model for F1TENTH (IROS'24)

2911C, C++Sep 9, 20241 years ago

Similar Papers

A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving

81% match2026

From Tiny Machine Learning to Tiny Deep Learning: A Survey

80% match1 repo1552025

Realistic Counterfactual Explanations for Machine Learning-Controlled Mobile Robots using 2D LiDAR

80% match2025

V2X-Lead: LiDAR-based End-to-End Autonomous Driving with Vehicle-to-Everything Communication Integration

80% match2023

Sense, Imagine, Act: Multimodal Perception Improves Model-Based Reinforcement Learning for Head-to-Head Autonomous Racing

79% match2023

Deep Reinforcement Learning with Enhanced PPO for Safe Mobile Robot Navigation

79% match1 repo532024

Cite this paper

@article{zarrar2024tinylidarnet,
  title  = {TinyLidarNet: 2D LiDAR-based End-to-End Deep Learning Model for F1TENTH Autonomous Racing},
  author = {Mohammed Misbah Zarrar and Qitao Weng and Bakhbyergyen Yerjan and Ahmet Soyyigit and Heechul Yun},
  year   = {2024},
  eprint = {2410.07447},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.07447v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.07447.svg)](https://codeofpaper.com/paper/2410.07447)

Discussion