Robotics

Building on its internationally renowned expertise in embodied Artificial Intelligence, the Lamarr Institute drives innovation on safe AI-based Robotics such as assistence systems, humanoid robots and in diverse applications in logistics and industry. Meet our experts in Canada!

Our Robotics Experts in Canada

Pushing the Boundaries of Robotic Capabilities in the Real World

As lead of the domestic service robot team NimbRo@Home, Raphael Memmesheimer has a deep passion for robot competitions, particularly those that push the boundaries of robotic capabilities in challenging, real-world environments outside the lab. He and his colleagues are looking for research collaborations related to Embodied AI, like generating autonomous actions from guided demonstrations via teleoperations by Visual Language Action (VLA) models or policy diffusion approaches.

Dr. Raphael Memmesheimer

Postdoctoral Researcher Embodied AI to the profile

Implementing Embodied AI in Versatile Environments and Logistics

Julian Eßer’s research centers on AI in Robotics, also known as Embodied or Physical AI. He looks forward to establishing future collaborations between Canadian partners and the Lamarr Institute at the intersection of robotics, reinforcement learning, and physics-based simulation to develop robust control methods for robots that move and interact dynamically with their environments. Additionally, he is seeking partners for a study on the potential applications of humanoid robots in logistics.

Julian Eßer

Scientific Coordinator Embodied AI to the profile

Ensuring the Safety of Autonomous Sytems

With a background in industry on embedded vision algorithms, Stefan Weigand’s research lies at the intersection of computer vision, robot simulation, and embodied intelligence. To this end, he focuses on control methods that transfer well from simulation to real robots despite sim-to-real gaps, the generalization of reinforcement learning to unseen visual domains and guaranteeing the safe and robust control for robots under domain shifts.