Object picking based on CAD model and 2D camera
Event address
The objective of this course is to learn how to train an object pose estimation neural network for robot picking applications. This includes:
- Generating synthetic data
- Training an detection detection model
- Training a pose estimation model
- Learning basics of robot picking
Your Teachers
Cyril Blanc, Manuel Arteaga and Aaron De Rybel are Flanders Make Research Engineers specialized in Vision AI for the manufacturing industry. They bring hands-on knowledge of machine vision, robotics, and AI to help bridge the gap between theory and real-world applications. Their work empowers industries to enhance automation, precision, and efficiency with intelligent, vision-driven systems.
Practical Information
Tuesday February 25, Flanders Make Leuven
Programme
09:00 - Welcome coffee
09:30-12:00 - Theoretical introduction on AI training from CAD file
12:00-13:00 - Lunch
13:00-15:00 - Hands-on experiment: rendering of synthetic data, application of network on images, communication with robot
15:00-17:00 - Discussion of alternative pose estimation and picking strategies
Language: English
Participation is free, after registration via the form below.
Registration
This training is part of the Digital Europe project "RebootSkills".
