In recent years, there had been a tremendous progress in the capabilities of computer systems to classify image or video clips taken from the Internet or to analyze human pose in real-time for gaming applications. These systems, however, analyze the past or in the case of real-time systems the present with a delay of a few milliseconds. “For applications, where a moving system has to react or interact with humans, this is insufficient,” says Prof. Jürgen Gall, a computer scientist and the speaker of the Research Unit. “For instance, robots collaborating with humans need not only to perceive the current situation, but they need to anticipate human actions and the resulting future situations in order to plan their own actions.”
In their project, the researchers aim to develop the technology that lays the foundation for applications that require the anticipation of human behavior. Instead of addressing the problem at a limited scope, the project addresses all relevant aspects including time horizons ranging from milliseconds to hours and granularity ranging from detailed human motion to coarse action labels. “To ensure that the developed methods are not limited to a single task but can be applied for a large variety of applications, we do not solve sub-problems in isolation but address all relevant aspects jointly,” says Jürgen Gall. The goal is therefore to develop a framework that seamlessly anticipates human behavior at all levels ranging from discrete activity labels for long-term prediction to detailed human motion for short term prediction.
Increasing importance of service robots
As a scenario for an application, the researchers focus on human support robots that support impaired or elderly people at home. Human support robots can fill the gap that needs to be faced due to the demographic change that will change the population structure in Germany and other countries dramatically. However, the robots need the ability to anticipate human behavior at various levels of granularity in order to be accepted and be efficient. The robot needs to know when its help is needed, but it should not stand in the way. In a collaborative setting, the robot is expected to complete tasks together with a human. This requires to anticipate both the intention but also detailed movements, e.g., when jointly assembling an object or preparing a meal.
The Research Unit is at the intersection of the two Transdisciplinary Research Areas “Mathematics, Modelling and Simulation of Complex Systems” and “Innovation and Technology for Sustainable Futures” since it develops computational tools for analyzing complex interactions between humans and robots as well as methods and technology for human support robots in order to address the demographic change, which is one of the global challenges for a sustainable future. In the six Transdisciplinary Research Areas at the University of Bonn researchers from different faculties and disciplines come together to work together on research topics relevant to the future.
DFG Research Unit 2535 “Anticipating Human Behavior”: http://for2535.cv-uni-bonn.de/#/start
Contact:
Prof. Dr. Jürgen Gall
University of Bonn
Department of Information Systems and Artificial Intelligence
E-mail: gall@iai.uni-bonn.de
Phone: +49 228 73 69600
