The Manufacturing Executive · 25 Oct 2022 · 27m · Episode 125
Austin Appel, Co-Founder of Overview, discusses how AI-driven vision inspection has democratized quality control, moving from expensive, rule-based systems to affordable, deep-learning platforms. He contrasts modern hardware and software capabilities with legacy systems, highlighting how Overview provides turnkey solutions for industries like automotive, medical, and food. Appel explains that lowering the barrier to entry allows manufacturers to automate inspection cost-effectively and use historical image data for supply chain debugging and liability protection.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Quality & testOverview
The company uses AI deep-learning vision systems to automate quality inspection for customers, replacing manual labor and traditional rule-based algorithms to detect defects like scratches or missing components.
“we provide turnkey AI solutions. … we basically are like a shop where you call us and we'll automate your inspection for you using all this new tech.”
Speaker 1 · Hear it at 20:40
Quality & testOverview
The company leverages AI to handle environmental variability in inspection tasks, allowing systems to function correctly without the precise, controlled lighting and hardware setups required by older machine vision technologies.
“it can handle variability a lot better. … you can build a system that is able to handle that, uh, without having to go crazy on the hardware and crazy on the engineering.”
Speaker 1 · Hear it at 15:12
Quality & testOverview$50,000 saved
The company utilizes AI to identify specific defective parts within a batch, enabling customers to isolate bad items rather than rejecting entire shipments, thereby saving significant money on returns and sorting.
“can we go through our pictures and see, oh, you actually only have 3 bad parts in there? Here's your serial numbers, sort done. right? $50,000 saved.”
Speaker 1 · Hear it at 23:00
early-stage companies
Other shows on the same ground, closest first.
Priyansha Bagaria, founder and CEO of Loopr.ai, explains how her company uses AI-powered computer vision to automate quality inspection in aerospace, automotive, and general manufacturing. She details the deployment of their software applications, IQ Inspect for defect identification and IQ Verify for assembly verification, which are hardware-agnostic and integrate with existing camera infrastructure. Bagaria highlights key industry pain points, including the high cost of quality, labor shortages, and the loss of institutional knowledge as experienced workers retire, arguing that AI provides the consistency and scalability that human inspection cannot. She also discusses Loopr's strategic partnership with Microsoft and the importance of starting with high-value pilot projects to demonstrate clear ROI before scaling across factory floors.
Matt Puchalski, founder and CEO of Bucket Robotics, explains how his Y Combinator-backed startup uses synthetic data generated from STEP files to automate visual inspection in manufacturing, bypassing the need for physical 'golden samples.' He contrasts this approach with legacy systems from Keyence and Cognex, highlighting how starting from CAD models allows for rapid simulation of good and bad parts. Puchalski also shares his background in autonomous vehicles at Argo AI and Latitude AI, discussing the unique reliability challenges of deploying Level 4 AVs and how those lessons inform his current work in flexible manufacturing.
Scott Everett, Co-Founder and CEO of Eigen Innovations, explains how his company uses industrial vision systems and AI to transform manufacturing quality control from reactive, destructive testing to proactive, insight-driven decision-making. He argues that while IoT infrastructure for data capture is mature, the industry struggles with 'insight architecture,' requiring contextualized data to provide explainable stories that empower non-technical operators to make real-time adjustments. Everett highlights specific applications in the automotive sector, such as ensuring the hermetic seal of vehicle headlights, where 100% inline inspection replaces random sampling to achieve zero-defect manufacturing.
Eliyahu Davis, lead engineer at Deepview AI, explains how his company uses deep learning to automate factory inspection, reducing setup time from 40 hours to minutes. Davis details his transition from aerospace software engineering to hardware, describing how he learned Altium Designer through online resources and mentorship to design the camera's PCB. He discusses the technical challenges of running neural network training on edge devices and the future of foundation models in industrial automation.
Jeff Bier, founder of the Embedded Vision Alliance (now Edge AI and Vision Alliance), explains how embedded vision has evolved from expensive industrial inspection to ubiquitous consumer applications like automotive safety and smartphone face ID, driven by domain-specific processors and deep learning. Jens Gamperl, CEO of Sourceability, describes his company's hybrid distribution model, which uses tools like Source Engine to integrate real-time supply chain data directly into design workflows via APIs, bridging the gap between engineering and procurement.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by The Manufacturing Executive. The episode itself belongs to its publisher.