Welding Automation & Perception

The welding application layer — live weld monitoring and speed control, the EtherNet/IP welder integration, parametric weld recipes, touch-sensing and seam-finding, and the 2026 AI-perception track. Every block below is an interactive simulation of a real subsystem I built.

Owned the welding process end to end: a real-time weld-monitoring dashboard, live travel-speed control, a C++ EtherNet/IP CIP driver for the welder (packed binary I/O assemblies, 125 Hz telemetry), and a parametric weld-recipe system operators tune on the tablet.

Built the motion patterns welding actually needs — touch-sense groove search to find the joint, stitch and multipass sequencing to fill it, and a plasma-cutting mode — each driven from the same trajectory core.

Added a 2026 AI-perception track: CAD + scan-native weld-seam detection from B-rep topology and occlusion physics, plus robot-mounted 3D scanning with eye-in-hand (charuco) calibration and mesh reconstruction at ~1 mm RMSE.