Lane Detection using Graph Search and Geometric Constraints for Formula Student Driverless

TL;DR

This paper introduces a fast, robust lane detection algorithm for autonomous racing that effectively handles sparse, noisy data and outperforms existing methods in accuracy and speed, enabling high-speed driving on unknown tracks.

Contribution

The paper presents a novel deterministic graph search algorithm with geometric constraints for lane detection, achieving global optimality in many cases and robustness to false positives.

Findings

Finds the global optimum in 45% of instances

Robust to up to 50% false positives

Detects long lanes over 100 meters with 0.6% critical failures

Abstract

Lane detection is a fundamental task in autonomous driving. While the problem is typically formulated as the detection of continuous boundaries, we study the problem of detecting lane boundaries that are sparsely marked by 2D points with many false positives. This problem arises in the Formula Student Driverless (FSD) competition and is challenging due to its inherent ambiguity. Previous methods are inefficient and unable to find long-horizon solutions. We propose a deterministic algorithm called CLC that uses backtracking graph search with a learned likelihood function to overcome these limitations. We impose geometric constraints on the lane candidates to guarantee a geometrically sound lane. Our exhaustive search leads to finding the global optimum in 45% of instances, and the algorithm is overall robust to up to 50% false positives. Our algorithm runs in less than 15 ms on a single CPU core, meeting the low latency requirements of autonomous racing. We extensively evaluate our method on real data and realistic racetrack layouts, and show that it outperforms the state-of-the-art by detecting long lanes over 100 m with few (0.6%) critical failures. This allows our autonomous racecar to drive close to its physical limits on a previously unknown racetrack without being limited by perception. We release our dataset with realistic Formula Student racetracks to enable further research.