The Autonomous Racing Software Stack of the KIT19d

TL;DR

This paper details the software architecture of KA-RaceIng's autonomous race car for the 2019 Formula Student Driverless competition, highlighting system modules, development methods, and performance results.

Contribution

It provides a comprehensive overview of the software stack for autonomous racing, including perception, localization, mapping, planning, and control, with insights into implementation and performance.

Findings

System modules successfully integrated for autonomous racing

Achieved competitive performance in 2019 competitions

Runtime measurements demonstrate real-time capabilities

Abstract

Formula Student Driverless challenges engineering students to develop autonomous single-seater race cars in a quest to bring about more graduates who are well-prepared to solve the real world problems associated with autonomous driving. In this paper, we present the software stack of KA-RaceIng's entry to the 2019 competitions. We cover the essential modules of the system, including perception, localization, mapping, motion planning, and control. Furthermore, development methods are outlined and an overview of the system architecture is given. We conclude by presenting selected runtime measurements, data logs, and competition results to provide an insight into the performance of the final prototype.