MCTR: Midpoint Corrected Triangulation for Autonomous Racing via Digital Twin Simulation in CARLA

TL;DR

This paper introduces MCTR, a new trajectory planning algorithm for autonomous racing that enhances smoothness and robustness using digital twin simulation in CARLA with 3D LiDAR perception, validated through extensive tests.

Contribution

MCTR improves trajectory smoothness with curvature correction and employs a digital twin in CARLA for realistic 3D LiDAR validation, advancing reactive controllers in autonomous racing.

Findings

MCTR achieves smoother trajectories compared to baseline methods.

The digital twin system enhances robustness in simulated and real-world tests.

Validation confirms improved performance in autonomous racing scenarios.

Abstract

In autonomous racing, reactive controllers eliminate the computational burden of the full See-Think-Act autonomy stack by directly mapping sensor inputs to control actions. This bypasses the need for explicit localization and trajectory planning. A widely adopted baseline in this category is the Follow-The-Gap method, which performs trajectory planning using LiDAR data. Building on FTG, the Delaunay Triangulation-based Racing algorithm introduces further enhancements. However, DTR's use of circumcircles for trajectory generation often results in insufficiently smooth paths, ultimately degrading performance. Additionally, the commonly used F1TENTH-simulator for autonomous racing competitions lacks support for 3D LiDAR perception, limiting its effectiveness in realistic testing. To address these challenges, this work proposes the MCTR algorithm. MCTR improves trajectory smoothness through the use of Curvature Corrected Moving Average and implements a digital twin system within the CARLA simulator to validate the algorithm's robustness under 3D LiDAR perception. The proposed algorithm has been thoroughly validated through both simulation and real-world vehicle experiments.