# How Path Robotics uses AI to optimize robotic welding

> Source: <https://www.therobotreport.com/how-path-robotics-uses-ai-optimize-robotic-welding/>
> Published: 2026-07-10 23:02:23+00:00

In Episode 252 of *The Robot Report* Podcast, we connect with Andy Lonsberry, co-founder and CEO of Path Robotics. He discusses the difficulties in setting up and using robots for welding applications.

Path Robotics has applied [AI](https://www.therobotreport.com/category/design-development/ai-cognition/) to identify the path of a torch and then move the robot through the [welding](https://www.therobotreport.com/tag/welding/) operation, using real-time [vision](https://www.therobotreport.com/category/technologies/cameras-imaging-vision/) guidance to maintain an optimal path.

As CEO of Path Robotics, [Lonsberry](https://www.linkedin.com/in/andrew-lonsberry-32154448/) leads the company’s strategy and operations with a focus on applying physical AI to longstanding challenges in [manufacturing](https://www.therobotreport.com/category/markets-industries/manufacturing/).

His work centers on building adaptive, AI-driven robotic systems designed for real-world production environments.

The Columbus, Ohio-based [company](https://www.therobotreport.com/tag/path-robotics/) is also deploying Boston Dynamics’ Spot quadruped robots into [mobile welding applications in shipbuilding](https://www.therobotreport.com/hii-partners-path-robotics-graymatter-robotics-accelerate-shipbuilding/).

Our other interviewee this week is [Michael Yip](https://yip.eng.ucsd.edu/), an assistant professor of electrical and computer engineering at the [University of California San Diego](https://www.therobotreport.com/tag/university-of-california-san-diego/), an IEEE RAS distinguished lecturer, a Hellman Fellow, and the director of the Advanced Robotics and Controls Laboratory ([ARCLab](https://ucsdarclab.com/)).

His group currently focuses on solving problems in data-efficient and computationally efficient robot control and [motion](https://www.therobotreport.com/category/robot-components/motioncontrol/) planning through the use of various forms of learning representations, including deep learning and reinforcement learning strategies. Yip’s lab applies these ideas to [surgical](https://www.therobotreport.com/tag/surgical/) robotics and the automation of surgical procedures.

## Show timeline

- 7:15 –
**News of the week** - 10:15 –
**Michael Yip,** assistant professor of electrical and computer engineering at UC San Diego - 35:27 –
**Andy Lonsberry**, co-founder and CEO of Path Robotics

## News of the week

[Beyond da Vinci: Why versatile humanoid robots are the next frontier in surgery](https://www.therobotreport.com/beyond-da-vinci-why-versatile-humanoid-robots-are-next-frontier-surgery/)[Ahead of stock market debut, Agility co-founder discusses physical AI and Digit V5](https://www.automate.org/robotics/industry-insights/ahead-of-stock-market-debut-agility-cofounder-discusses-physical-ai-and-digit-v5)[NHTSA getting fed up with autonomous vehicles interfering with first responders](https://www.roadandtrack.com/news/a71883246/federal-regulators-autonomous-vehicles-first-responder-interference/)[Tickets, geofences, and 1M miles: The new reality of California AV compliance](https://www.therobotreport.com/tickets-geofences-1m-miles-new-reality-california-av-compliance/)

## Sponsors

*Thanks to our sponsors who make this content possible.*

Every growing Postgres database eventually hits a wall. Queries slow down, dashboards lag, and teams consider adding a second database.

Tiger Data, creators of TimescaleDB, extend Postgres with time-series primitives, columnar storage, and automatic partitioning so your queries stay fast on live data. No pipelines, no migration, no second system. Just Postgres, built for the workload you actually have.

Learn more at: **tigerdata.com/go/trial**

To learn how you can sponsor a future episode of *The Robot Report* Podcast, contact: Jami Brownlee at [[email protected]](/cdn-cgi/l/email-protection#bdd7dfcfd2cad3d1d8d8fdcac9cad5d0d8d9d4dc93ded2d0)

Would you like to be a guest on a future episode? Contact Mike Oitzman at [[email protected]](/cdn-cgi/l/email-protection#eb8684829f91868a85ab9c9f9c83868e8f828ac5888486)