arXiv subjects

Megan Teng

Publications and source records attributed to Megan Teng.

3 recordsLinked to original sources

arXiv2026

AI-Assisted Hyperspectral Interferometry and Single-Cell Dispersion Imaging

Interferometry techniques are essential for extracting phase information from optical systems enabling precise measurements of dispersion and highly sensitive detection of perturbations. While phase sensing offers enhanced sensitivity compared to conventional spectroscopy methods, this sensitivity often makes systems more vulnerable to external factors such as vibrations, introducing instability and noise. In this work, we demonstrate a broadband and AI-enhanced interferometry method, denoted general polarization common-path interferometry (GPCPI) that relaxes the polarization constraints of traditional common-path interferometry. The polarization decoupling feature enables simultaneous amplitude and phase measurements supplemented with deep neural autoencoders to detect phase anomalies in the spectrum through the analysis of second order derivative mapping of the phase profile, enhancing the accuracy of broadband phase measurements. The approach enables an order of magnitude improvement in phase stability compared to state-of-the-art interferometry techniques, leading to higher accuracy in phase sensing. Plasmonic metasurface phase sensing and hyperspectral single-cell dispersion imaging demonstrate the capability and sensitivity of the method over conventional spectroscopy. Our adopted version of deep learning model, ConvNeXt V2, enables real-time tracking of phase variation with minimized noise. Interference fringes affected by the cell-cultured samples reveal the fingerprints of the normal (CCD-32Sk) vs cancerous (COLO-829) skin cells, enabling cell classification and disease diagnosis at single-cell level through hyperspectral dispersion imaging. The proposed technique offers a reliable, compact, and stable solution for broadband phase measurements and single-cell dispersion imaging for applications in metrology, molecular diagnostics, drug discovery, and quantum sensing.

physics.optics↗

arXiv2025

EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks

This paper presents a framework for learning vision-based robotic policies for contact-rich manipulation tasks that generalize spatially across task configurations. We focus on achieving robust spatial generalization of the policy for the peg-in-hole (PiH) task trained from a small number of demonstrations. We propose EquiContact, a hierarchical policy composed of a high-level vision planner (Diffusion Equivariant Descriptor Field, Diff-EDF) and a novel low-level compliant visuomotor policy (Geometric Compliant ACT, G-CompACT). G-CompACT operates using only localized observations (geometrically consistent error vectors (GCEV), force-torque readings, and wrist-mounted RGB images) and produces actions defined in the end-effector frame. Through these design choices, we show that the entire EquiContact pipeline is SE(3)-equivariant, from perception to force control. We also outline three key components for spatially generalizable contact-rich policies: compliance, localized policies, and induced equivariance. Real-world experiments on PiH, screwing, and surface wiping tasks demonstrate a near-perfect success rate and robust generalization to unseen spatial configurations, validating the proposed framework and principles. The experimental videos and more details can be found on the project website: https://equicontact.github.io/EquiContact-website/

cs.RO↗

arXiv2025

Geometric Formulation of Unified Force-Impedance Control on SE(3) for Robotic Manipulators

In this paper, we present an impedance control framework on the SE(3) manifold, which enables force tracking while guaranteeing passivity. Building upon the unified force-impedance control (UFIC) and our previous work on geometric impedance control (GIC), we develop the geometric unified force impedance control (GUFIC) to account for the SE(3) manifold structure in the controller formulation using a differential geometric perspective. As in the case of the UFIC, the GUFIC utilizes energy tank augmentation for both force-tracking and impedance control to guarantee the manipulator's passivity relative to external forces. This ensures that the end effector maintains safe contact interaction with uncertain environments and tracks a desired interaction force. Moreover, we resolve a non-causal implementation problem in the UFIC formulation by introducing velocity and force fields. Due to its formulation on SE(3), the proposed GUFIC inherits the desirable SE(3) invariance and equivariance properties of the GIC, which helps increase sample efficiency in machine learning applications where a learning algorithm is incorporated into the control law. The proposed control law is validated in a simulation environment under scenarios requiring tracking an SE(3) trajectory, incorporating both position and orientation, while exerting a force on a surface. The codes are available at https://github.com/Joohwan-Seo/GUFIC_mujoco.

cs.RO↗