Vision Language Models for Robotics | ROS Developers Open Class
The Construct The Construct
48K subscribers
1,800 views
0

 Published On Dec 20, 2023

Vision language models, often referred to as VLMs, are advanced AI models that combine computer vision and natural language processing (NLP) capabilities. These models are designed to understand images or videos and generate descriptions, answer questions, or perform various tasks based on the visual content.

In this Open Class, we will review some key aspects related to these VLMs and how they can be applied to robotics.

You will learn:
* What are Vision Language Models
* How to use them in a robotics application

Related course:
* Generative AI for Robotics: https://app.theconstructsim.com/cours...

ROS Project Link:
https://app.theconstructsim.com/open-...

============================
About ROS DEVELOPERS LIVE CLASS
Where you will learn and practice how to develop ROS-based robots with a ROS expert in a real-time event every single week.

FREE LIVE CLASS Tuesday @ 6 PM CET. This is a weekly LIVE class on how to develop ROS-based robots. You'll learn ROS and practice with a ROS developer in real time without any previous setup on your side. And you'll receive a rosject that contains the robot simulations and the project’s code.

You will learn ROS, ROS2, robotics theory, math for robotics, robots, and Artificial Intelligence ... and much more with us in this weekly LIVE event.

Class Creator: Alberto Ezquerro
Class cover designer: Lorena Guevara

#ROS2 #ros2 #learning #robotics #rust #programming

Music from #InAudio: https://inaudio.org/
Digital Technology Background*.
--
#ROS #Robot #ROStutorials

show more

Share/Embed