The Manufacturing Executive · 7 Jun 2022 · 32m · Episode 105
Dr. Prasad Akella, Founder and CEO of Drishti, explains how his company uses AI-powered video analytics to empower manufacturing workers rather than replace them. He details how Drishti’s technology captures production line video to create searchable 'video birth certificates' for products, enabling root cause analysis and quality control. Akella highlights specific applications like action recognition for error detection, optimizing line balancing, and using video to accelerate training and improve employee retention by identifying and leveraging 'brilliant outliers' on the floor.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Quality & testDrishti proprietary computer vision models
The AI system analyzes video footage of assembly stations to detect deviations from standard work procedures, such as incorrect tightening sequences, and automatically flags errors for quality assurance teams.
“our system identified it that bottom top, top bottom. He's not following sunrise procedures. … there's absolutely no human being in all of this. This is automatically detected by the AI system…”
Speaker 1 · Hear it at 13:10
Running the companyDrishti video data and AI
AI-driven video analysis identifies high-performing operators and their unique techniques, which are then codified into standard processes to improve overall line efficiency and training.
“digging in further into the video, they realized that this gentleman would show up with a cup of water. … They made that a standard process across the line…”
Speaker 1 · Hear it at 18:47
Running the companyDrishti video data and AI
The system uses video data to measure operator performance and cycle times, enabling the company to identify bottlenecks and optimize line balancing without manual data collection.
“you're looking at what's called a line balance chart, identifying the bottleneck stations on this chart, and you now know where to take your industrial engineers…”
Speaker 1 · Hear it at 13:10
companies scaling up
Other shows on the same ground, closest first.
Anna-Katrina Shedletsky, CEO and co-founder of Instrumental, explains how her platform uses AI and aggregated product data to optimize manufacturing and reduce waste. Drawing from her experience leading product design teams at Apple, including the high-risk Apple Watch program, she details how Instrumental helps companies close feedback loops in development and production. She highlights specific use cases, such as using unsupervised learning to correlate visual inspection data with functional test failures, to improve yield and accelerate time-to-market. Additionally, Shedletsky discusses her Women in STEM Mentorship Program and Instrumental's recent recognition on the Inc. 5000 list.
Dunchadhn Lyons, Director of Engineering at Spot AI, explains how the company uses existing IP cameras and AI agents to monitor manufacturing safety and operations in real time. He details a case study where a safety manager reduced incidents by 40% by automating the review of 16,000 hours of footage, allowing her to focus on targeted training. Lyons also describes how these AI teammates preserve tribal knowledge from retiring workers and help clothing manufacturers avoid millions in downtime by detecting operational bottlenecks before they cause full stops.
Mike White, Founder and President of Secchi, explains how his company uses data-driven employee relationship management to cut manufacturing turnover in half. Drawing on his experience at Johns Manville and Caterpillar, White details the origin of Secchi as a tool to document performance and remove bad actors, which evolved into a platform for recognition and retention. He argues that the 'age of the frontline worker' is here, with skilled trades becoming more valuable than traditional degrees, and discusses how Secchi empowers supervisors with transparent data to make fair, defensible decisions.
Tanuj Thapliyal, Co-Founder and CEO of Spot AI, explains how his company transforms industrial video surveillance into operational intelligence for manufacturers. He details the origin of Spot AI from Stanford, its focus on empowering frontline workers with easy-to-use video data, and the company's recent $20 million Series A funding. Thapliyal also discusses critical cybersecurity architectures, including zero-trust models and local storage, and shares examples of how video intelligence solves real-world manufacturing problems like conveyor belt failures.
Dr. Brian Kang, Director and Head of R&D at Koh Young Research America, discusses the application of AI in electronic manufacturing and inspection during an interview at APEX 2023. He explains that AI helps mitigate labor shortages by optimizing human effort in programming, quality improvement, and review processes. Kang emphasizes that data quality is more critical than data volume for training effective machine learning models. He notes that the industry has moved from conceptual AI to realizing practical, deployable solutions on the factory floor.
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.