UruBots Autonomous Cars Team One Description Paper for FIRA 2024

TL;DR

This paper tackles autonomous navigation for a race-capable RC car targeting the 2024 FIRA Autonomous Cars Race Challenge. It presents an integrated hardware-software stack centered on a Jetson Nano and a monocular camera, using a five-layer CNN trained on 5,000 images within the Donkey Car framework to produce steering and throttle commands. On a 13 m test track, the system completed the course in under 20 seconds, demonstrating real-time perception, decision-making, and control on embedded hardware. The work contributes a practical, low-cost autonomous racing platform and dataset, potentially accelerating development and competition readiness for FIRA participants.

Abstract

This document presents the design of an autonomous car developed by the UruBots team for the 2024 FIRA Autonomous Cars Race Challenge. The project involves creating an RC-car sized electric vehicle capable of navigating race tracks with in an autonomous manner. It integrates mechanical and electronic systems alongside artificial intelligence based algorithms for the navigation and real-time decision-making. The core of our project include the utilization of an AI-based algorithm to learn information from a camera and act in the robot to perform the navigation. We show that by creating a dataset with more than five thousand samples and a five-layered CNN we managed to achieve promissing performance we our proposed hardware setup. Overall, this paper aims to demonstrate the autonomous capabilities of our car, highlighting its readiness for the 2024 FIRA challenge, helping to contribute to the field of autonomous vehicle research.

Figures (4)

• Figure 1: The Autonomous car during the construction phase.
• Figure 2: Components of our autonomous vehicle.
• Figure 3: Network Structure
• Figure 4: Track Scenario used to validate our vehicle