Main research Areas
Machine learning, data science, reinforcement learning, probabilistic learning
Control theory and design, dynamical systems, learning-based control, state estimation
Networks, cyber-physical systems, distributed systems, resource-aware algorithms, robotics
...and any combination thereof.
Research at DSME focuses on fundamental questions at the intersection of data science and engineering, as well as innovative applications. We develop general methods and algorithms that enable robots and other physical machines to autonomously learn from data, to interact with their environment through feedback, and to interconnect with each other to form collaborative networks. Turning mathematical and theoretical insight into enhanced autonomy and performance of real-world physical systems is an essential and driving facet of our work.
The Institute for Data Science in Mechanical Engineering (DSME) aims to develop machine learning, data science, and decision algorithms and methods for machines in the physical world. Our research often starts with fundamental theoretical questions that arise at the intersection of data science and engineering, leading us to develop new methods and algorithms, which we finally implement and demonstrate on physical machines such as robots, vehicles, and other autonomous systems.
When learning on physical machines, some special challenges arise, which are different from other machine learning domains typically involving pure software or computer systems. For example, learning in the real world often has to cope with imperfect and relatively small data sets, because physical systems cannot be sampled arbitrarily and exhibit high-dimensional and continuous state-action spaces. A constant stream of data (e.g., from sensors) requires online and lifelong learning, but often on embedded hardware with limited computational resources. Finally, theoretical guarantees on safety, robustness, and reliability are essential for physical learning systems, but often not available in standard machine learning. These are some of the fundamental challenges that arise when artificial intelligence meets the physical world – and that drive our research.
In addition to learning, control, and decision making for a single physical system, we are also interested in distributed and networked problems, where multiple intelligent agents cooperate to achieve a common goal. How can a team of robots efficiently coordinate their actions? What information should they exchange, and when? And how to design for limited embedded resources such as bandwidth, computation, or energy? These are some of the questions that we address in this research direction.
As we seek to bridge computational and physical intelligence, research at DSME is highly interdisciplinary. In particular, we combine and intersect the disciplines of machine learning, systems & control theory, applied mathematics, and robotics.
The video was produced by the Max Planck Institute for Intelligent Systems, where Prof. Trimpe was previously running the Max Planck & Cyber Valley Research Group on Intelligent Control Systems (ICS). Our research activities are now continued at DSME at RWTH Aachen University.