From early concepts and laboratory validation to proven field deployments on live infrastructure, we develop technologies that sense the physical world, transform observations into intelligence, and enable informed action. Building on our expertise in optics and photonics, we are expanding toward multimodal sensing, AI-powered understanding, and intelligent systems that interact with the physical world.
PROJECTS
PEOPLE
PUBLICATIONS
PATENTS
Deployed telecom cables, urban fiber networks, and emerging optical sensors provide a powerful foundation for observing the physical world at scale. Our research spans forward-looking theoretical studies, cutting-edge experiments, artificial intelligence, and world- and industry-first field trials. We transform existing infrastructure into dense, real-time sensing platforms capable of monitoring complex environments over large areas.
Our research follows a broad sense–understand–act vision. We develop optical and distributed fiber sensing technologies that capture physical phenomena; AI methods that interpret complex signals, combine information across sensors, diagnose events, and predict changing conditions; and intelligent solutions that translate these insights into decisions and responses. Looking ahead, we envision extending this foundation beyond optical sensing to multimodal sensing and autonomous systems, including robotics, that can perceive, reason about, and respond to the physical world.
Our current work spans optical sensing, infrared imaging and spectroscopy, radio-frequency spectrum sensing and AI-enabled sensing analytics. These technologies can detect, localize, and characterize vibrations, intrusions, equipment conditions, and environmental changes along an infrastructure network’s physical route. By integrating sensing with edge computing and AI, we seek to move beyond data collection toward real-time understanding, prediction, and automated response.
By uniting advanced sensing, physical-world AI, and intelligent action, Optical Sensing & Solutions aims to create safer, more resilient, and more autonomous systems for infrastructure, utilities, transportation, environmental monitoring, public safety, smart cities, and intelligent manufacturing.
Are you interested in joining us? We seek the next generation of thought leaders in optical sensing for researcher positions. Outstanding applicants pursuing a career in optical sensing are encouraged to visit our careers page to learn more and apply for available positions.
Exciting internship opportunities for Summer 2027 will be available on our internship page this fall. We are looking for students pursuing advanced degrees in Computer Science and Electrical Engineering. Internships are typically 3 months long during the summer. The benefits of working for us include the opportunity to quickly join a project team applying cutting-edge technology to industry-leading concepts.
To apply for a Summer Internship, visit our Internship page.
Want to learn more about our optical sensing & solutions department? Meet our team of experts, check out our blog posts, or read our latest publications.
In this research area, we first focus on developing new optoelectronic designs and FPGA-based signal-processing technologies to improve the sensitivity, dynamic range, and stability of both backscattering- and forward-transmission-based DFOS systems.
READ MORE
Our research and development focus on innovative applied machine learning and signal processing algorithms that convert low-level sensory inputs into high-level information, providing solutions for real-world sensing applications in safety, security, smart city, infrastructure health monitoring, power & energy industry, and more.
READ MORE
Vector beams are spatial modes that have spatially inhomogeneous states of polarization. Any light beam is a linear combination of vector beams, the coefficients of which comprise a vector beam spectrum. In this work, through numerical calculations, a novel method of free-space optical sensing is
Contrastive Language-Audio Pretraining (CLAP) models have demonstrated unprecedented performance in various acoustic signal recognition tasks. Fiber optic-based acoustic recognition is one of the most important downstream tasks and plays a significant role in environmental sensing. Adapting CLAP for
Scalable methods for optical transmission performance prediction using machine learning (ML) are studied in metro reconfigurable optical add-drop multiplexer (ROADM) networks. A cascaded learning framework is introduced to encompass the use of cascaded component models for end-to-end (E2E) optical path
As the adoption of large language models increases and the need for per-user or per-task model customization grows, the parameter-efficient fine-tuning (PEFT) methods, such as low-rank adaptation (LoRA) and its variants, incur substantial storage and transmission costs. To further reduce stored parameters,
The noise figure ripple of a dual-stage EDFA is studied starting from experimental measurements under full spectral load conditions and defining device characteristics. Asemi-analytical model is then proposed showing 0.1 dB standard deviation on the error distribution in all cases of operation.
In Optical Multiplex Section (OMS) control and optimization framework, end-to-end (Global) and span-by-span (Local) DNN gray-box strategies are compared in terms of scalability and accuracy of the output signal and noise power predictions. Experimental measurements are carried out in OMSs with increasing