Lecky Advisory LLC

Physics-informed AI for robotics, vision, and manufacturing.

Since 1985, Lecky Advisory has helped organizations from early-stage startups to Fortune 100 manufacturers apply emerging technology to real production problems — before it was mainstream, before the frameworks existed, and before the vendors had it figured out.

What began as hands-on systems integration has evolved alongside the industry itself — from early machine vision and robotic workcells through programmable automation, industrial networking, and now physics-informed AI and sim-to-real or hardware-in-the-loop (real-to-real) pipelines.

The problems change. The tools change.

The discipline doesn't.

Lecky Advisory LLC

Ned Lecky, PhD

Email: ned@lecky.com

LinkedIn: www.linkedin.com/in/nedlecky

What We Do

Physics-Informed AI, ML, and Process Control

Model design and implementation that encodes process physics — reducing data requirements, improving generalization, and producing results that make sense to domain experts and ML practitioners alike.

Machine Vision and Perception Systems

From classical vision pipelines to modern deep learning architectures, applied to inspection, guidance, metrology, and robotic perception in manufacturing environments.

Sensor Fusion and Anomaly Detection

Multimodal sensing pipelines integrating acoustic emission, thermography, force/torque, and vision for process monitoring and quality control.

Sim-to-Real and Real-to-Real Pipeline Development

Digital twin and simulation environments that generate training data for real-world deployment, including Isaac Sim integration for robotic manufacturing applications. Real-to-real implementations that use hardware in the loop to enable testing and validation in places where the physics is unknown but a working proxy system can be built.

Systems Integration and Architecture Review

Independent assessment of existing implementations, gap analysis, and strategic guidance for organizations building or scaling manufacturing intelligence systems.

Defense and Aerospace Applications

Sensor-based monitoring, anomaly detection, and process control for high-consequence manufacturing environments requiring rigorous validation.

About

Ned Lecky has spent forty years solving hard problems at the intersection of physical systems, robotics, and machine intelligence — working with organizations ranging from one-person inventors to venture-backed startups to the world's largest manufacturers.

His current work focuses on physics-informed ML for manufacturing process monitoring and control, including acoustic emission sensing, thermographic monitoring, Gaussian process modeling, and GPU-accelerated inference pipelines. He has personally developed sensor fusion and control systems for over a hundred real-world processes using PLC-based, PC-based, Cloud-based, and hybrid approaches that make no use, light use, or heavy use of ML and AI techniques in imaging, control, planning, and robotics.

Prior senior roles include General Electric, Amazon, Microsoft, and Google. Ned holds a BS in Mechanical and Aerospace Engineering from Princeton University and MS and PhD degrees in Electrical and Computer Engineering focused on real-world applications of high performance and cognitive computing.

Lecky Advisory is the current practice entity of a consulting and engineering firm founded in 1985 — previously operating as Lecky Engineering, Lecky Integration, and Lecky Consulting.

Page updated

Report abuse