We seek to advance our understanding of intelligent systems that perceive, learn, and interact and to use this knowledge to create innovative technologies that benefit society

Departments

Empirical Inference

The problems studied in the department can be subsumed under the heading of empirical inference, i.e., inference performed on the basis of empirical data. This includes 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 biomedical measurements to astronomical observations. Our department is conducting theoretical, algorithmic, and experimental studies to advance study of empirical inference.

Department Website

Haptic Intelligence

Have you noticed that computers can show beautiful images and play clear sounds, but they don't let you physically touch digital items? Similarly, most robots are surprisingly unskilled at physically interacting with the real world and with people.

Led by Katherine J. Kuchenbecker, the MPI-IS Haptic Intelligence department aims to elevate and formalize our understanding of touch cues while simultaneously discovering new opportunities for their use in interactions between humans, computers, and machines.

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.

Department Website
Thumb ticker sm thumb ticker kjk 2024 Katherine J. Kuchenbecker

Research

Publications

News

Open positions

Contact

Perceiving Systems

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 monocular 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.

Department Website

Physical Intelligence

The department aims to understand the underlying principles of physical intelligence of single and collectives of biological organisms at milli- and micrometer length scales, and realize advanced physical intelligence capabilities on small-scale mobile robots using such principles. As the societal and translational research mission, the team aims to apply these tiny robots as minimally invasive and implantable wireless medical robots inside our body to revolutionize medicine and healthcare. The highly interdisciplinary team has expertise in robotics, micro/nanotechnology, materials science, engineering, physics, biology, chemistry, and medicine. Until 2023, Metin Sitti headed the Physical Intelligence Department. He is now President of Koç University and a Guest Scientists at MPI-IS

Department Website

Robotic Materials

The Robotic Materials Department aims to fundamentally challenge current limitations of robotic hardware, using an interdisciplinary approach that synergizes concepts from soft matter physics and chemistry with advanced engineering technologies, to devise robotic materials capable of creating intelligent machines that mimic the astonishing versatility and adaptability of organisms in nature. Our department investigates three broad areas of research including soft robotics, functional materials and energy capture, with the current focus on soft electrostatic actuator systems based on multi-phase, multi-layer dielectrics. We aim to rapidly bring our discoveries from fundamental materials science, all the way to the development of bioinspired and wearable robotic systems.

Department Website

Social Foundations of Computation

At Social Foundations of Computation, we build scientific foundations for machine learning and artificial intelligence in the social world. To chart and implement a society’s norms and expectations, we start from concepts and work our way towards applications. Challenging existing problem formulations when necessary, we think through how the use of machine learning distributes societal resources and opportunity. Computational tools to critically evaluate - and possibly contest - algorithmic systems and their impacts are a key component of our work. Our ultimate goal is to promote a positive role of artificial intelligence in society.

 

Department Website
Thumb ticker md rs21190 p1000088 lpr
Empirical Inference Bernhard Schölkopf
Thumb ticker sm l1170153
Thumb ticker md 20241029 haptic intelligence 89.jpg
Haptic Intelligence Katherine J. Kuchenbecker
Thumb ticker sm thumb ticker kjk 2024
Thumb ticker md 8 adventskalender 2024.jpeg
Perceiving Systems Michael Black
Thumb ticker sm headshot2021
Thumb ticker md 13 adventskalender 2024.jpg
Robotic Materials Christoph Keplinger
Thumb ticker sm keplinger christoph geringauflo  send

Research Groups

Max Planck Fellow Research Groups

Thumb xl 20241209 rm department 27
Thumb xl 20241104 polybot 03
Thumb xl 20241113 haptic intelligence 144
Thumb xl 20241107 zwe robotics 55
Thumb md 20241209 rm department 27
Thumb md 20241104 polybot 03
Thumb md 20241113 haptic intelligence 144
Thumb md 20241107 zwe robotics 55