FUSE-AI launches a cooperation project on robotics

We are excited to announce a pioneering collaboration between the Helmut-Schmidt-University/University of the Federal Armed Forces (HSU/UniBw H) and FUSE-AI, a partnership that will be used to transform the field of robotics.

Christian Kreischer, Professor of Electrical Machines and Drive Systems at the Faculty of Electrical Engineering at HSU/UniBw H, is leading the KIKU project. We are pleased to develop an AI-based, modular platform to be used with an UR10 robot as part of the project.

Our project aims to create a versatile and user-friendly robotic system that will be able to perform a wide range of tasks by receiving instructions via a chat interface.

By integrating cutting-edge technologies such as computer vision, reinforcement learning and natural language processing into the field of robotics, this project aims to enable users to achieve automation to increase efficiency, safety and productivity.

We integrate a chat interface that controls the robot via a Large Language Model (LLM), which generates a sequence of robot instructions.

Reinforcement learning (RL) is evolving as a key solution for controlling robots in laboratories or warehouses. These AI models enable robots to learn autonomously and optimize their workflows depending on the obtained results, allowing them to adapt to environment variations more efficiently.

Reinforcement learning does not require training data that must be provided as an external data set, because the data is generated automatically while the robot is being trained.