The latest advances in Artificial Intelligence include Visual and Large Language Models (e.g. ChatGPT), that are capable of context understanding, situational awareness, and reasoning from various input such as text and images. This paves the way for applications in robotics, empowering machines with the ability to understand complex environments, adapt to new and dynamic scenarios, and execute precise manipulation actions based on a nuanced understanding of both visual and textual information. This project will develop such models for industrial robot manipulators to solve new tasks in new situations. Evaluation of the models will be done with different use cases from different application areas.

2025

2029