ITS
Information Technology Services
ITS
Information Technology Services
The Women in AI speaker series, a collaboration between the Schwartz Reisman Institute for Technology and Society and Deloitte, welcomes Maren Bennewitz, a professor for humanoid robots at the University of Bonn whose research focuses on robots acting in human environments. Bennewitz has developed innovative solutions for robotic systems co-existing with humans, including machine learning techniques for navigation, detection, and prediction.
In this talk, Bennewitz will explore her solutions work utilizing convolutional neural networks and reinforcement learning to enable service robots to act with foresight when navigating human environments.
“Foresighted robot navigation in human environments”
Service robots acting in human environments need to be able to navigate in challenging scenes, act foresightedly, and avoid interferences with the users while respecting their navigation preferences. In this talk, I will first introduce our framework to enable humanoid robots to navigate through cluttered scenes. Our method exploits knowledge about different obstacle classes and selects appropriate robot actions. To classify objects from RGB images and decide whether an obstacle can be overcome by the robot with a corresponding action, e.g., by pushing or carrying it aside or stepping over or onto it, we train a convolutional neural network (CNN). As I will demonstrate in our experiments, using the CNN the robot can robustly classify the observed obstacles into the different classes and exploit this information to efficiently compute solution paths. In the second part of my talk, I will present an approach to predict human navigation goals based on learned object interactions. I will then show how this knowledge can be used by a robot to realize foresighted navigation in service robotic applications. Finally, I will introduce a reinforcement learning framework to train a personalized navigation controller with an intuitive virtual reality demonstration interface. Our user study provides evidence that the personalized approach significantly outperforms classical navigation approaches with more comfortable human-robot experiences.
Maren Bennewitz is a professor (W3 equivalent) for humanoid robots and vice rector for digitalization at the University of Bonn, and an executive board member of the Cluster of Excellence PhenoRob. Her research focuses on robots acting in human environments. In the last few years, she has been developing several innovative solutions for robotic systems co-existing and interacting with humans. Among them are machine learning techniques for efficient navigation with humanoid and wheeled robots as well as for reliably detecting and tracking humans from sensor data and predicting their motions. Bennewitz has published over 100 peer-reviewed scientific papers, and regularly serves as editor or associate editor for top-tier robotics conferences, in the editorial board of top-tier robotics journals, and as program committee member for international workshops. She also serves as reviewer for the European Commission (EC) and the German Research Foundation (DFG) and has been PI in several national and European projects.
Women in AI is a six-part virtual speaker and mentorship series developed by the Schwartz Reisman Institute for Technology and Society in collaboration with Deloitte that connects a global audience with a diverse group of female thought leaders in the field of AI research. The Women in AI series convenes leading female AI researchers to share knowledge and mentorship opportunities through seminar events that promote opportunities for women across the technology sector. Participants will explore how women are leading the development of new technologies and approaches, and investigating emerging trends across the sector. The series provides insights into cutting-edge research, bold points of views, and help business and community leaders elevate diverse voices while promoting opportunities for women to share their perspectives.
To register for the event, visit the official event page.
