AI Engineer - Learn how to integrate AI into software applications
Foundations for Product Management Success
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore how computer vision transforms manufacturing robotics through a detailed conversation with Shawn Patel, Co-Founder & CTO of Almond, focusing on practical applications of AI in handling unstructured manufacturing tasks. Discover how Almond develops custom vision pipelines for complex, high-mix picking operations in manufacturing facilities, moving beyond traditional structured robotic tasks. Learn about the integration of multiple advanced vision models including RF-DETR, Grounding DINO, SAM 2, and ViT to create highly accurate solutions for robotic arms. Examine the complete workflow from collecting and preparing training data to training custom models specifically designed for manufacturing environments. Understand the critical importance of model accuracy requirements for robotic applications and see live demonstrations of high-mix picking scenarios where vision AI enables robots to adapt to varied, unstructured tasks. Gain insights into the technical challenges and solutions involved in combining multiple AI models to achieve the precision needed for real-world manufacturing robotics applications.
Syllabus
00:00 Introduction - Vision AI for robotics in manufacturing
01:24 Getting to know Almond - AI robots for manufacturers
02:37 Why vision AI for robotic arms? Adapting to unstructured tasks
05:44 Demo: High mix picking with vision AI
07:30 Behind the scenes: Getting started with vision models
10:40 Combining multiple AI models - Grounding DINO, RF-DETR, SAM 2, ViT
12:49 Collecting training data and training custom models
17:44 Model accuracy for robotic arms
24:04 Conclusion
Taught by
Roboflow