The Physical Exploration Challenge: Robots Learning to Discover, Actuate and Explore Degrees of Freedom in the World
Project leaders: Oliver Brock (Berlin), Marc Toussaint (Stuttgart)
Researchers: Johannes Kulick (Stuttgart), Sebastian Höfer (Berlin), Roberto Martin Martin (Berlin), Peter Englert (Stuttgart)
Administration: Janika Urig (Berlin), Carola Stahl (Stuttgart)
Associates: Shlomo Zilberstein (Massachusetts)
This project addresses a fundamental challenge in the intersection of machine learning and robotics. The machine learning community has developed formal methods to generate behaviour for agents that learn from their own actions. However, several fundamental questions are raised when trying to realize such behaviour on real-world robotics systems that shall learn to perceive, actuate and explore degrees of freedom (DoF) in the world. These questions pertain to basic theoretical aspects as well as the tight dependencies between exploration strategies and the perception and motor skills used to realize them. To properly frame the proposed research with respect to the state of the art, we first describe the theory of active learning and exploration and then summarize relevant work in manipulation, the real-world domain chosen here.
The goal of this project is to equip real-world robotic systems with one of the most interesting aspects of intelligence: an internal drive to learn, i.e., the ability to organize their behavior so as to maximize learning progress towards an objective. If successful, we believe that this will make a transitional change in the way such systems behave, in their autonomy of learning, in the way they ground acquired knowledge, and eventually also in the way they will interact with humans and play their part in application in industry and in the private sector.