Max Planck Institute for Intelligent Systems
Exploration and development of intelligent systems
Intelligent systems are able to optimize their structure and properties in such a way that they can act successfully in a complex, partially changing environment. Three subdomains - perception, learning and action - can be differentiated in this context. Scientists at the Max Planck Institute for Intelligent Systems are dedicated to the fundamental research and development of intelligent systems in all three subdomains. Research expertise in the fields of computer and material sciences as well as biology are combined in one institute at two locations. Machine learning, image recognition, robotics and biological systems will be investigated in Tübingen; so-called learning material systems, micro- and nanorobotics and self-organization in Stuttgart. Although the focus is on basic research, the institute has high potential for practical applications, including robotics, medical technology and innovative technologies based on new materials.
Abteilungen
Director: Prof. Dr. Bernhard Schölkopf
The type of inference can vary, including for instance inductive learning (estimation of models such as functional dependencies that generalize to novel data sampled from the same underlying distribution), or the inference of causal structures from statistical data (leading to models that provide insight into the underlying mechanisms, and make predictions about the effect of interventions). Likewise, the type of empirical data can vary, ranging from sparse experimental measurements (e. g., microarray data) to visual patterns. Our department is conducting theoretical, algorithmic, and experimental studies to try and understand the problem of empirical inference.
Director: Katherine J. Kuchenbecker, PhD
We leverage scientific knowledge about the sense of touch to create haptic interfaces that enable a user to interact with virtual objects and distant environments as though they were real and within reach. One key insight in this endeavor has been that tactile cues, such as high-frequency tool vibrations and the making and breaking of contact, convey rich mechanical information that is necessary to make the interaction feel real. This research led us to realize that autonomous robots can also benefit from attending to the dynamic tactile cues that occur as they manipulate objects in their environment and engage in social physical interaction with humans.
Director: Michael Black, PhD
Our research uses Computer Vision to learn digital humans that can perceive, learn, and act in virtual 3D worlds. This involves capturing the shape, appearance, and motion of real people as well as their interactions with each other and the 3D scene using monoculr video. We leverage this to learn generative models of people and their behavior and evaluate these models by synthesizing realistic looking humans behaving in virtual worlds. This work combines Computer Vision, Machine Learning, and Computer Graphics.
Director: Prof. Dr. Christoph Kepplinger
Dr. Keplinger’s research focuses on fundamentally challenging current limitations of materials and components used to build robots. He is regarded as a pioneer in the field of bio-inspired soft robotics and a rising star in the international robotics and materials science communities. As an MPI-IS director, he has founded the new “Robotic Materials” department. Dr. Keplinger will have a decisive influence on the future development of the institute as well as on the excellence of Cyber Valley, Europe’s largest research consortium in the field of AI.
Director: Prof. Dr. Moritz Hardt
Moritz Hardt founded the department "Social Foundations of Computation" in 2021, which extends the institute's deep expertise in machine learning, artificial intelligence, robotics, and physical systems to include social issues within computer science. The research is intended to contribute to a paradigm shift within computer science that treats computer science from the ground up as a social science that takes into account the role of society as a whole, as well as the actions and dynamic behavior of individuals - especially when algorithms have an impact on the reality of people's lives.
