Bucket Robotics
Defect detection for manufacturing built from CAD and synthetic data.
250M lbs of plastic is wasted annually in US manufacturing. Bucket Robotics is making defect detection faster and easier to deploy to prevent that. Our products are designed to be easy to integrate into existing automation and technology stacks, flexible enough to bring retooling costs down, and reliable enough to make you forget that it's a robot. Matt and Steph are leveraging their experience from the self-driving industry, where we've integrated high-performance computing and quality sensing into complex, noise-filled environments. We focus on robust hardware and user-friendly software for a new generation of end-users, ensuring ease of use and rapid deployment. Secure and efficient handling of user data can make customers in the manufacturing space nervous to invest in sensing — our team's extensive experience handling self-driving car data in these regulated environments positions us uniquely to tackle these challenges. Companies like Keyence, National Instruments, and FLIR offer either outdated hardware or prohibitively expensive systems, along with software that hasn’t evolved to meet modern user needs. US manufacturing is undergoing a significant transformation, with construction spending hitting a record annualized pace of over $200 billion. The need for a more reliable supply chain has seen over $700 billion in manufacturing megaprojects across North America since 2021, and this growth requires heavy automation. Bucket Robotics is at the forefront of this shift, offering a scalable, cost-effective solution that enhances automation and positions manufacturers closer to their end customers.
Active Founders
Matt Puchalski, Founder/CEO
Matt is co-founder and CEO of Bucket Robotics. Before co-founding Bucket Robotics, Matt distinguished himself in the autonomous vehicle industry through pivotal roles at Stack AV, Latitude AI, and Argo AI. His work at these companies brought the deployment of autonomous vehicles to public roads across the United States and Germany. With deep expertise in integrating and operationalizing AVs, Matt brings a unique vision to revolutionize the robotics industry.
Steph Wolski, Founder/CTO
Steph is co-founder and CTO of Bucket Robotics. Steph began college at the age of 13 and started working in robotics at 18. He was the Remote Guidance Tech Lead at Argo AI where he met Matt. Later, Steph was an early engineer at Stack AV, working on the Autonomy Integration team where he stood up core infrastructure for their self-driving trucks.
Company Launches
☕ TL;DR
Bucket Robotics makes defect detection models way faster and easier to deploy. CAD goes in — detection model comes out.
👥 The Team
Hi everyone, we’re Matt and Steph, and we’re Bucket Robotics!
📉 The Problem
Defects are a universal challenge in manufacturing, particularly with methods like injection molding, die casting, and 3D printing. Factories using these methods frequently retool their lines for different products making it difficult and costly to gather enough data to train defect detection models.
Manufacturers strive to ensure that only the highest quality products reach their customers. Avoiding the shipment of defective products not only protects their reputation but also safeguards expensive machinery from damage, maximizes yield by leveraging advanced analytics, and prevents the progression of faulty parts through the production line, which can lead to compounded waste and increased costs.
A 2017 study estimates that yield losses account for 44% of sheet metal used in the production of passenger vehicles — and we want to bring that number down, saving money and the environment.
Traditionally, defect detection comes in two flavors:
- Pay a person to watch your line.
- Train a vision model the old-fashioned way — wait for defective parts to come out and add your sample to the dataset.
Paying people to check parts is inefficient and a miserable job. Collecting enough labeled data samples to train a model is impractical for rapidly retooled outputs, and the labeling is expensive. This often leaves manufacturers with a critical gap in quality assurance, leading to increased scrap, downtime, and potentially unhappy customers with defective parts.
📈 The Solution
We help eliminate the need for inefficient human monitoring and outdated defect detection by providing a system where we generate defect detection models using CAD files—something every part designed for modern manufacturing has. Our models can run on an edge computing device as small as a Jetson Orin Nano and be continually refined with real-world data.
Here’s why this is a game-changer:
- Early Deployment: Your defect detector can arrive at your manufacturing line before you’ve manufactured any parts. This means you can catch defects right from the get-go.
- Continuous Improvement: As defects start to appear, we can automatically refine and improve the model, ensuring your system remains top-notch.
- Classification: The system tells you how the part is defective, allowing you to dial in your tooling configuration and maintenance cycle—e.g. when it's time to create a new mold.
Check out a video on our process here: Bucket Robotics | Defect Detection
🙏How You Can Help
We are seeking connections and collaborations to drive our mission forward. If you or anyone in your network is interested in learning more or helping out, we want to hear from you! We’re specifically looking to connect with:
- Quality Assurance and Factory Automation leaders
- Companies and brands in high-volume and precision manufacturing
- Experts in the manufacturing and defect detection industries
If that’s you or someone you know, please get in touch!
YC Sign Photo
Company Photo
