A manufacturer of high-end electronic controllers was facing quality issues in its assembly process. The electronic controllers the company produced were used in movie production, most notably in Hollywood, for overhead lighting. The lighting control panels were critical components in film and television production and demanded high precision and reliability.
Each unit costs over $5000 in raw materials alone for the company. While the scrap costs were low, the first-time yield was only 64%, which significantly affected the company’s bottom line. The assembly process also was complex and required precision and expertise. The manufacturer wants to improve efficiency to increase process yield and reduce time spent on rework.
The company implemented Assembly Copilot on the assembly line. The software uses computer vision and AI technology to provide step-by-step guidance and real-time alerts to operators, helping them avoid mistakes, which ensures that each step of the assembly is completed correctly the first time. It also provides a video traceability feature that allows industrial engineers to continuously optimize the process and quickly conduct root cause analysis.
The implementation of Assembly Copilot was efficient and user-friendly, requiring minimal disruption to operations. It began with a straightforward hardware setup, involving the installation of a standard web camera and a GPU-enabled laptop, which was completed in just 30 minutes. The process then moved to task definition, where the lighting control panel assembly steps were specified in Assembly Copilot’s intuitive portal. This was followed by a data recording phase, capturing five shifts worth of assembly data to account for various real-world scenarios. Only one complete assembly cycle needed to be timestamped for cycle labeling to provide crucial baseline data. Finally, the recorded data was sent to Retrocausal’s annotation engine for model training.
The entire process, from hardware setup to receiving the trained model, took approximately two days and required minimal effort from the manufacturer’s team, ensuring the system was accurately calibrated to their specific assembly process. This efficient implementation lays the foundation for significant improvements in the company’s production process.
The first-time yield rate was improved from 64% to 83%. Moreover, the software was able to detect erroneous steps with 87% accuracy. Assembly Copilot allowed the company to potentially operate the same production line with 20% fewer workers than before, facilitating improvement in production output.
A leading manufacturer of high-end lighting control panels for film and television production, specializing in precision equipment critical for Hollywood productions.
Electronics Manufacturing
Improving first-time yield and assembly efficiency using assembly copilot in high-end lighting control panel production.
Brandin and his team help our customers with setting up the Pathfinder platform and getting up-to-speed on all the features and functionalities, in addition to assisting them with standardizing their processes where needed.
Brandin is a seasoned manufacturing leader, who has spent more than a decade designing and setting up assembly lines in both the US and China, optimizing them, and working with human operators to maximize productivity and quality.
Jesse works closely with our marquis customers to understand their needs, and figures out the best solution that immediately adds dollars to their bottom line.
Jesse has two decades of enterprise sales experience. He has held sales leadership roles at pioneering technology startups.
Andrey takes inventions and converts them into innovations. He leads our product engineering team to turn our scientific prototypes into robust customer-facing products.
Andrey co-founded and successfully exited a startup to immigrate to the US. He spent his next eight years building the core data science infrastructure for Amazon’s supply chain planning team, and the CV/ML infrastructure for Microsoft’s HoloLens organization.
Zeeshan focuses on delighting our customers by understanding their needs and defining product and strategy to meet and exceed these needs. He works closely with our sales leadership to grow our customer base.
Zeeshan was a scientific leader at Microsoft’s HoloLens division, where he invented AI technologies to assist frontline workers across industries. Earlier, he shipped IoT platforms and visual defect detection software for manufacturers at Siemens and MVTec GmbH.
Huy takes our product roadmap and figures out what’s achievable with today’s AI advances, and what we need to invent to solve our customers’ pain points.
Huy led teams of scientists and engineers at NEC and invented technologies for driver assistance systems that are part of 500,000+ Honda cars. He is an inventor on more than 20 US patents, and his research papers are cited by every lab from MIT, Stanford, and CMU to Apple, Google, and Baidu.
