The Robot Report Podcast

Design for manufacturing is changing faster than most robotics teams can keep up - and if you are building physical products, this conversation could save you months of rework. Marc Kermisch shares how Protolabs is using AI, simulation, and deep manufacturing expertise to turn CAD files into real parts in as little as 24 hours, while helping engineers avoid the design mistakes that quietly kill speed, quality, and scale.

Mike Oitzman and Gene Demaitre sit down with Marc, who has returned to the show since episode 138 with a new role as CTO and AI leader at Protolabs. He explains how the company’s software-driven approach links CAD models directly to manufacturing tool paths, G code, and production workflows across CNC machining, 3D printing, injection molding, and sheet metal - all built around the challenge of helping engineers get parts made faster without sacrificing precision.

You’ll discover:

- Why Protolabs treats AI as a practical manufacturing tool, not hype

- How machine learning helps catch manufacturability issues before a part is ever built

- What ProDesk does when it flags ejector locations, tight tolerances, seam issues, and other hidden design risks

- How part similarity search and simulation speed up internal decisions for engineers

- Where AI is already paying off in visual inspection, cobot programming, and print-box optimization

Marc also breaks down the real-world tradeoffs between 3D printing, CNC machining, and injection molding, including when a prototype should stay a prototype - and when it’s time to redesign for production. He gets specific about common failure points like draft angles, wall thickness, shrink, resin changes, tooling assumptions, and the gap between prototype tolerances and production reality.

If you’re dealing with robotics, hardware, manufacturing, or any physical product that must move from concept to production, this episode shows what happens when software, AI, and manufacturing expertise work together instead of in silos. It’s especially valuable for founders, roboticists, and engineers who need to make smarter decisions before the first expensive mistake happens.

Protolabs is also building for the future of compliance, supply chain resilience, and low-volume production, with a network that helps customers de-risk sourcing, reduce complexity, and stay aligned with regulated industries like defense, aerospace, and medical devices. The result is a rare inside look at how modern manufacturing is evolving - and how the next wave of physical products will get made.

Essential listening if you are building hardware, scaling production, or trying to make your robot, part, or process easier to manufacture the first time.

This episode explores how Nomagic is applying AI and robotics to warehouse operations, with a focus on each picking, recovery workflows, and production-grade deployment.
Josh Cloer, General Manager for North America, explains why the company leans into “physical AI,” how its systems are designed for always on operations, and why real-world production data matters more than simulation alone.
Mike Oitzman and Gene Demaitre also dig into the practical side of automation adoption, from pilot-to-production failures to the pressure on supply chain leaders to move faster without getting stuck in vendor hype.
The conversation is especially useful for teams evaluating warehouse robotics, AI-assisted recovery, or flexible automation strategies.
Learn more: https://nomagic.ai/

Our guest this week is Derik Pridmore, CEO and co-founder of OSARO.
OSARO develops intelligent AI robotics for real-world warehouse automation, delivering scalable fulfillment solutions that optimize throughput, uptime, and overall performance.
In this conversation, Pridmore breaks down how warehouse robotics has evolved from limited perception systems to adaptable AI-driven automation. He shares why hardware-agnostic design, continuous learning, and real-world monitoring matter more than flashy demos — and why the biggest breakthroughs in robotics still depend on balancing specificity, reliability, and safety.
Learn more: https://www.osaro.com

Also this week, cohosts Steve Crowe, Mike Oitzman, and Gene Demaitre discuss the recent news about the FCC announcement to ban foreign legged and mobile robots from import to the U.S.

– SPONSORS –

This episode is brought to you by Tiger Data

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, extends 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.

Try it free at https://www.tigerdata.com/go/trial?utm_source=content-syndication&utm_medium=referral&utm_campaign=robotics-ads

In this episode, Doug Pagnutti, Developer Advocate at Tiger Data, discusses how time series databases like TimescaleDB are transforming industrial automation, robotics, and AI applications. He shares insights on integrating these databases with various sensors, managing data at scale, and optimizing performance both on the cloud and on the edge.
Key Topics:
- The role of time series data in robotics and industrial automation
- How TimescaleDB extends PostgreSQL for high-performance time series workloads
- Differences between open source and managed cloud versions
- Strategies for integrating various industrial controllers and messaging pipelines
- Techniques for managing intermittent connectivity with edge devices
- Advanced tools like continuous aggregates and data compression for big data
- Enabling multimodal data queries with hybrid search stacks
- Future applications of time series data in AI-driven environments and energy systems
- Best practices for storing telemetry, spatial, and metadata efficiently

– SPONSORS –

This episode is brought to you by Tiger Data

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, extends 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.

Try it free at https://www.tigerdata.com/go/trial?utm_source=content-syndication&utm_medium=referral&utm_campaign=robotics-ads

On the show this week, Deise Yumi Asami shares how her AI-enabled robotics startup, Maximo, is transforming solar panel installation and making solar panel installation faster, safer, and more efficient. In this conversation, you’ll hear how robotics, AI vision, and smart field deployment are helping reshape the future of renewable energy infrastructure.
Deise also shares the experience of starting a new company from the ground up while being incubated within a larger parent company. Learn how innovation is encouraged and celebrated inside a large organization, and how AES organizes its innovation group.
Learn more: https://maxrobotics.ai/
– SPONSORS –

This episode is brought to you by Tiger Data

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, extends 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.

Try it free at https://www.tigerdata.com/go/trial?utm_source=content-syndication&utm_medium=referral&utm_campaign=robotics-ads