Alex Gorodetsky

By |

Alex Gorodetsky’s research is at the intersection of applied mathematics, data science, and computational science, and is focused on enabling autonomous decision making under uncertainty. He is especially interested in controlling, designing, and analyzing autonomous systems that must act in complex environments where observational data and expensive computational simulations must work together to ensure objectives are achieved. Toward this goal, he pursues research in wide-ranging areas including uncertainty quantification, statistical inference, machine learning, control, and numerical analysis. His methodology is to increase scalability of probabilistic modeling and analysis techniques such as Bayesian inference and uncertainty quantification. His current strategies to achieving scalability revolve around leveraging computational optimal transport, developing tensor network learning algorithms, and creating new multi-fidelity information fusion approaches.

Sample workflow for enabling autonomous decision making under uncertainty for a drone operating in a complex environment. We develop algorithms to compress simulation data by exploiting problem structure. We then embed the compressed representations onto onboard computational resources. Finally, we develop approaches to enable the drone to adapt, learn, and refine knowledge by interacting with, and collecting data from, the environment.

Gabor Orosz

By |

Gabor Orosz is an Associate Professor of Mechanical Engineering and Civil and Environmental Engineering. His theoretical research include dynamical systems, control, and reinforcement learning with particular interests in the roles of nonlinearities and time delays in such systems. In terms of applications he focuses on connected and automated vehicles, traffic flow, and biological networks. His research has been supported by the National Science Foundation and industrial funds. His recent work appeared in journals like IEEE Transactions on Automated Control, IEEE Transactions on Control Systems Technology, IEEE Transactions on Intelligent Transportation Systems, and Transportation Research Part C. For the latter journal he has also be serving as an Editor. WIRED magazine reported on his experimental results when his team built a connected automated vehicle and evaluated it in real traffic. He served as the program chair for the 12th IFAC Workshop on Time Delay Systems and served as the general chair for 3rd IAVSD Workshop on Dynamics of Road Vehicles, Connected and Automated Vehicles.

Jing Sun

By |

My areas of interest are control, estimation, and optimization, with applications to energy systems in transportation, automotive, and marine domains. My group develops model-based and data-driven tools to explore underlying system dynamics and understand the operational environments. We develop computational frameworks and numerical algorithms to achieve real-time optimization and explore connectivity and data analytics to reduce uncertainties and improve performance through predictive control and planning.

Jaerock Kwon

By |

My research interests are in the areas of brain-inspired machine intelligence and its applications such as mobile robots and autonomous vehicles. To achieve true machine intelligence, I have taken two different approaches: bottom-up data-driven and top-down theory-driven approach. For the bottom-up data-driven approach, I have investigated the neuronal structure of the brain to understand its function. The development of a high-throughput and high-resolution 3D tissue scanner was a keystone of this approach. This tissue scanner has a 3D virtual microscope that allows us to investigate the neuronal structure of a whole mammalian brain in a high resolution. The top-down theory-driven approach is to study what true machine intelligence is and how it can be implemented. True intelligence cannot be investigated without embracing the theory-driven approach such as self-awareness, embodiment, consciousness, and computational modeling. I have studied the internal dynamics of a neural system to investigate the self-awareness of a machine and model neural signal delay compensation. These two meet in the middle where machine intelligence is implemented for mechanical systems such as mobile robots and autonomous vehicles. I have a strong desire to bridge the bottom-up and top-down approaches that lead me to conduct research focusing on mobile robotics and autonomous vehicles to combine the data-driven and theory-driven approaches.

9.9.2020 MIDAS Faculty Research Pitch Video.

High-Throughput and High-Resolution Tissue Scanner – NSF Funded

David Fouhey

By |

David works on computer vision and machine learning with the end goal of developing autonomous systems that can learn to build representations of the underlying state and dynamics of the world through observation (and potentially interaction).

Towards this end, he is particularly interested in understanding physical and functional properties from images. His research interest in physical properties aims to address how we can recover a rich 3D world from a 2D image. He is especially interested in representations — the answers that are obvious are also obviously defective — as well as how we should reconcile our strong prior knowledge about this structure of the problem with data-driven techniques. In recent work, he has become interested in applying this more broadly in the hope that we can develop AI systems that can learn how the physical world works from observation, including work on solar physics. In functional properties, he is interested in inferring and understanding opportunities for interaction with the environment by both robots and humans, both in terms of how one would learn this and what this implies for a physical understanding of the world.

Harm Derksen

By |

Current research includes a project funded by Toyota that uses Markov Models and Machine Learning to predict heart arrhythmia, an NSF-funded project to detect Acute Respiratory Distress Syndrome (ARDS) from x-ray images and projects using tensor analysis on health care data (funded by the Department of Defense and National Science Foundation).

Yi Lu Murphey

By |

Dr. Yi Lu Murphey is an Associate Dean for Graduate Education and Research, a Professor of the ECE(Electrical and Computer Engineering) department and the director of the Intelligent Systems Lab at the University of Michigan, Dearborn. She received a M.S. degree in computer science from Wayne State University, Detroit, Michigan, in 1983, and a Ph.D degree with a major in Computer Engineering and a minor in Control Engineering from the University of Michigan, Ann Arbor, Michigan, in 1989. Her current research interests are in the areas of machine learning, pattern recognition, computer vision and intelligent systems with applications to automated and connected vehicles, optimal vehicle power management, data analytics, and robotic vision systems. She has authored over 130 publications in refereed journals and conference proceedings. She is an editor for the Journal of Pattern Recognition, a senior life member of AAAI and a fellow of IEEE.

Jason Corso

By |

The Corso group’s main research thrust is high-level computer vision and its relationship to human language, robotics and data science. They primarily focus on problems in video understanding such as video segmentation, activity recognition, and video-to-text; methodology, models leveraging cross-model cues to learn structured embeddings from large-scale data sources as well as graphical models emphasizing structured prediction over large-scale data sources are their emphasis. From biomedicine to recreational video, imaging data is ubiquitous. Yet, imaging scientists and intelligence analysts are without an adequate language and set of tools to fully tap the information-rich image and video. His group works to provide such a language.  His long-term goal is a comprehensive and robust methodology of automatically mining, quantifying, and generalizing information in large sets of projective and volumetric images and video to facilitate intelligent computational and robotic agents that can natural interact with humans and within the natural world.

Relating visual content to natural language requires models at multiple scales and emphases; here we model low-level visual content, high-level ontological information, and these two are glued together with an adaptive graphical structure at the mid-level.

Relating visual content to natural language requires models at multiple scales and emphases; here we model low-level visual content, high-level ontological information, and these two are glued together with an adaptive graphical structure at the mid-level.

Matthew Johnson-Roberson

By |

Matthew Johnson-Roberson, PhD, is Assistant Professor of Naval Architecture and Marine Engineering and Assistant Professor of Electrical Engineering and Computer Science, College of Engineering, the University of Michigan, Ann Arbor.

The increasing economic and environmental pressures facing the planet require cost-effective technological solutions to monitor and predict the health of the earth. Increasing volumes of data and the geographic dispersion of researchers and data gathering sites has created new challenges for computer science. Remote collaboration and data abstraction offer the promise of aiding science for great social benefit. Prof. Johnson-Roberson’s research in this field has been focused on developing novel methods for the visualization and interpretation of massive environments from multiple sensing modalities and creating abstractions and reconstructions that allow natural scientists to predict and monitor the earth through remote collaboration. Through the promotion of these economically efficient solutions, his work aims to increase access to hundreds of scientific sites instantly without traveling. In undertaking this challenge he is constantly aiming to engage in research that will benefit society.

Traditional marine science surveys will capture large amounts of data regardless of the contents or the potential value of the data. In an exploratory context, scientists are typically interested in reviewing and mining data for unique geological or benthic features. This can be a difficult and time consuming task when confronted with thousands or tens of thousands of images. The technique shown here uses information theoretic methods to identify unusual images within large data sets.

Traditional marine science surveys will capture large amounts of data regardless of the contents or the potential value of the data. In an exploratory context, scientists are typically interested in reviewing and mining data for unique geological or benthic features. This can be a difficult and time consuming task when confronted with thousands or tens of thousands of images. The technique shown here uses information theoretic methods to identify unusual images within large data sets.