# A Modular Architecture Design for Autonomous Driving Racing in Controlled Environments

arXiv: https://arxiv.org/abs/2512.03886 · HTML: https://mlsanity.com/paper/2512.03886/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)

## Builds on (most cited first, 6 of 6)

- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [Multiple Object Tracking: A Literature Review](https://mlsanity.com/paper/1409.7618/) (2014)
- [AMZ Driverless: The Full Autonomous Racing System](https://mlsanity.com/paper/1905.05150/) (2019)
- [FSOCO: The Formula Student Objects in Context Dataset](https://mlsanity.com/paper/2012.07139/) (2020)
- [A Tricycle Model to Accurately Control an Autonomous Racecar with Locked Differential](https://mlsanity.com/paper/2312.14808/) (2023)

## Abstract (arXiv)

This paper presents a modular autonomous driving architecture for Formula Student Driverless competition vehicles operating in closed-circuit environments. The perception module employs YOLOv11 for real-time traffic cone detection, achieving 0.93 mAP@0.5 on the FSOCO dataset, combined with neural stereo depth estimation from a ZED 2i camera for 3D cone localization with sub-0.5 m median error at distances up to 7 m. State estimation fuses RTK-GNSS positioning and IMU measurements through an Extended Kalman Filter (EKF) based on a kinematic bicycle model, achieving centimeter-level localization accuracy with a 12 cm improvement over raw GNSS. Path planning computes the racing line via cubic spline interpolation on ordered track boundaries and assigns speed profiles constrained by curvature and vehicle dynamics. A regulated pure pursuit controller tracks the planned trajectory with a dynamic lookahead parameterized by speed error. The complete pipeline is implemented as a modular ROS 2 architecture on an NVIDIA Jetson Orin NX platform, with each subsystem deployed as independent nodes communicating through a dual-computer configuration. Experimental validation combines real-world sensor evaluation with simulation-based end-to-end testing, where realistic sensor error distributions are injected to assess system-level performance under representative conditions.