3D generation for dental restorations
Our generation models produce natural looking restorations for every unique patient. The models produce tens of thousands of unique restorations per week, millions per year.
Explore the projectOur generation models produce natural looking restorations for every unique patient. The models produce tens of thousands of unique restorations per week, millions per year.
Explore the projectThe left UR20 unfolds from rest and picks the base plate. The right arm stays folded.
Illustrative sequence · simplified tooling & cell layoutI was the lead engineer for Path’s autonomous assembly and weld product. This involved creating state-of-the-art bin picking, control algorithms for high-precision assembly, and vision algorithms for weld localization.
US20260077420A1 · Jordan Ott, co-inventor · Published March 19, 2026

Autonomous bin picking, high-precision assembly, and weld localization.
Patent application · Co-inventor ↗Explore the workcell
Welding demands extreme precision. We developed vision algorithms that combine 2D images and 3D sensor data to localize weld seams in 3D space, correct their positions relative to the robot’s reference frame, and estimate weld profiles for highly precise robotic welding.
Explore weld perceptionIllustrative assembly motions · Each station runs its own task and timing.

Teaching robots to perform high precision fit up and assembly tasks for manufacturing applications.
Explore the assembly lab
Learning fixture placement through physics simulation. Constraining parts while preserving weld access and assembly clearance.
Explore the fixture search