Abstract:

To ultimately achieve Embodied Artificial Intelligence, we need robots with the capability to robustly perceive their environments and execute their actions. The key challenge is that no sensors and actuators are perfect, which means that robots need the ability to deal properly with the resulting uncertainty. In this presentation, I will discuss the opportunities of the probabilistic and deep-learning approaches to robotics and how they can be combined to get the best of both worlds. Finally, I will present several describe how we can utilize the potential of foundation models to even better deal with complex and changing real-world environments.

Bibliography:

Wolfram Burgard is a professor of Computer Science at the University of Technology Nuremberg, where he heads the research group on Robotics and Artificial Intelligence. Before this, he was a professor of autonomous intelligent systems at the University of Freiburg, Germany. From 2019 until 2021, he was VP for Automated Driving and Machine Learning at the Toyota Research Institute. In his career, he published over 400 papers. He received multiple awards, including the IEEE Technical Field Award, the IEEE RAS Pioneer Award, and the Leibniz Prize of the German Research Foundation.