PLS-Calib: A Partial Least Squares Framework for Event Camera and Odometry Calibration under Ground Motion Constraints

2026-08-04

AI Summary

This work addresses the challenge of extrinsic rotational calibration between an event camera and an odometer on ground-constrained robots, where insufficient motion excitation hinders reliable estimation. The authors propose a novel calibration framework based on Partial Least Squares (PLS) regression, which, to the best of their knowledge, is the first application of PLS to sensor calibration. By modeling the latent kinematic relationships between asynchronous and heterogeneous sensor streams, the method yields a closed-form, numerically stable solution that circumvents the matrix singularity issues inherent in traditional Canonical Correlation Analysis (CCA). Additionally, a polarity-aware event representation is introduced to enhance the spatiotemporal contrast of circular calibration patterns, thereby improving feature detection robustness. Experiments demonstrate that the proposed approach significantly outperforms existing methods on both synthetic and real-world datasets, achieving high accuracy and strong robustness, and offering a theoretically sound and practical solution for multi-sensor calibration under motion-limited conditions.

Abstract

Accurate extrinsic rotation calibration between sensors is fundamental to the performance of robotic perception systems. However, most existing calibration techniques rely on full 6-DoF motion to excite all degrees of freedom, which is often infeasible for ground-constrained robots with limited motion capabilities. Recent approaches designed for such restricted settings, such as Canonical Correlation Analysis (CCA)-based methods, suffer from ill-conditioned covariance matrices that lead to numerical instability and suboptimal calibration accuracy. To overcome these limitations, we present a novel rotation calibration framework named PLS-Calib that, for the first time, leverages Partial Least Squares (PLS) regression to model the latent kinematic correlations between asynchronous, heterogeneous sensor streams. Specifically, we apply our method to the calibration of an event camera and an odometry onboard a ground robot. To improve event-based pattern detection, we introduce a polarity-aware event representation, which enhances spatiotemporal contrast in circular calibration targets. Our PLS-based formulation yields a closed-form, stable solution that avoids matrix singularities inherent in CCA-based approaches. Extensive experiments on both synthetic and real-world datasets validate the effectiveness of our approach, demonstrating significant improvements in calibration robustness and accuracy over state-of-the-art methods. This work offers a practical and theoretically grounded solution for rotation calibration in constrained robotic systems and opens up new directions for applying statistical learning techniques in neuromorphic vision.

Problem

• rotation calibration
• ground-constrained robots
• event camera
• odometry
• numerical instability

Innovation

• Partial Least Squares
• Event Camera Calibration
• Ground Robot
• Extrinsic Rotation Estimation
• Polarity-aware Event Representation