Search papers, labs, and topics across Lattice.
This paper introduces PLS-Calib, a novel rotation calibration framework that utilizes Partial Least Squares (PLS) regression to accurately calibrate the extrinsic rotation between an event camera and odometry in ground-constrained robots. By addressing the limitations of existing methods that rely on full 6-DoF motion, PLS-Calib employs a polarity-aware event representation to enhance pattern detection, yielding a stable closed-form solution that mitigates numerical instability. Experimental results demonstrate that PLS-Calib significantly outperforms state-of-the-art calibration techniques in both robustness and accuracy, marking a substantial advancement in robotic perception systems under motion constraints.
Calibration accuracy improves dramatically when using PLS regression, solving issues that plague traditional methods in constrained robotic environments.
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.
