Deep Learning for Multi-Sensor Calibration in Autonomous Driving

Abstract

This PhD thesis presents novel deep learning approaches for robust multi-sensor calibration in autonomous driving systems. The work introduces uncertainty-aware calibration methods and demonstrates their effectiveness in real-world scenarios.

The research focuses on developing practical solutions for sensor calibration challenges in autonomous vehicles, with particular emphasis on LiDAR-camera perception and uncertainty estimation. The thesis contributes to the field through publications in top-tier conferences and an international patent.

Key Contributions

• Uncertainty-Aware Calibration: Novel approaches for quantifying calibration uncertainty using conformal prediction
• Deep Learning Methods: First deep learning-based sensor calibration without manual initialization
• Multi-Sensor Fusion: Robust methods for LiDAR-camera and event camera-LiDAR calibration
• Real-World Validation: Practical solutions validated on autonomous driving datasets
• Industrial Impact: Research leading to international patent and industry applications

Publications from this Thesis

• WACV 2025: Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach
• CVPR 2024: MULi-Ev: Maintaining Unperturbed LiDAR-Event Calibration
• BMVC 2023: PseudoCal: Towards Initialization-Free Camera-LiDAR Calibration
• International Patent: UniCal: A Single-Branch Transformer-Based Model for Camera-to-LiDAR Calibration

BibTeX Citation

@phdthesis{cocheteux2025thesis,
    author = {Cocheteux, Mathieu},
    title = {Deep Learning for Multi-Sensor Calibration in Autonomous Driving},
    school = {Université de technologie de Compiègne},
    year = {2025},
    type = {PhD Thesis},
    url = {https://theses.hal.science/tel-05268827v1}
}