
Prof. Dr. Stephan Pareigis
Department of Computer Science
Hamburg University of Applied Sciences
Berliner Tor 7
20099 Hamburg
GERMANY
Email stephan.pareigis@haw-hamburg.de
Stephan Pareigis is a seasoned researcher and professor with over a decade of experience in developing autonomous systems. He earned his Ph.D. in Applied Mathematics from Ludwig-Maximilians-University, with a thesis on numerical methods for reinforcement learning. Since 2004, he has held a professorship of Applied Mathematics and Technical Computer Science at Hamburg University of Applied Sciences. In addition to his work as a professor, Stephan has more than a decade of experience in developing software for distributed and embedded real-time control systems in various companies. His research interests include autonomous systems, real-time and reactive programming, embedded machine learning, and reinforcement learning.
Stephan has been developing small robotic systems and autonomous miniature cars for more than 15 years and has supervised student teams participating in autonomous systems competitions. He has co-authored several publications on autonomous systems and AI-based methods and has received grants and funding for autonomous systems research. Together with his autosys research group, he is currently setting up a publicly funded test field for smart mobility in a city district in Hamburg. Stephan is currently dean of the Department of Computer Science at Hamburg University of Applied Sciences.
Topic: Navigating the Challenges of Autonomous Robots with AI-Enabled Gripper Arms
Abstract:
Autonomous robots have the potential to revolutionize many industries, from manufacturing to logistics to healthcare. However, realizing this potential requires overcoming a range of challenges, including navigation in complex urban environments, the ability to use elevators,robust object recognition, and local positioning improvement. In this keynote speech, we present a novel SLAM method that enables an autonomous robot to navigate through urban environments with high accuracy and efficiency. Furthermore, we will demonstrate how the robot can effectively use elevators by detecting and communicating with them using AI techniques. We also present a robust object recognition method that allows the robot to recognize doors and open them with its gripper arm.
To improve the robot’s local positioning, we will discuss a reinforcement learning approach that can adapt to changing environments and improve the robot’s accuracy over time. Finally, we present a new neural network architecture that helps to close the simulation to reality gap with respect to system dynamics, improving the robot’s performance in real-world scenarios. In summary, this keynote speech will present several AI-based methods that enable an autonomous robot with a gripper arm to navigate urban environments, use elevators, recognize and open doors, scan unknown objects, and improve its local positioning accuracy. We believe that these advancements represent a significant step forward in the development of truly autonomous robots, with the potential to transform a range of industries in the years to come.