Current Projects
 | CRII: III: Explainable Multi-Source Data Integration with Uncertainty Funding Agency: NSF PI: Xiaoxiao Du Sensors are all around us collecting data. Each sensor may provide complementary or reinforced information that supports tasks such as target detection, classification, or scene understanding. This project develops weakly supervised learning methods for multi-source data integration accounting for both data and label uncertainty. |
 | Instructional Development Fund: A Physical Robot Arm Prototype and Website Design for EECS 467 Autonomous Robotic Design Experience course Funding Agency: University of Michigan CRLT PI: Xiaoxiao Du This grant funds a course development effort for EECS 467: Autonomous Robotics Design Experience course, where a 2DoF robotic arm prototype and a website will be developed. |
Completed Projects (at UM)
 | Automated Video Processing Algorithms to Detect and Classify High-Level Behaviors with Speed and Accuracy Funding Agency: FHWA EAR Role: Task Lead and Co-PI. PI: C. Flannagan. Developed computer vision approaches for pedestrian detection and trajectory, behavior, and intent analysis. |
 | UM Ford Center for Autonomous Vehicles Funding Agency: Ford Motor Company Role: Task Lead and Researcher. PI: R. Vasudevan, K. Skinner, and M. Johnson-Roberson. Worked on multiple projects under the UM-Ford Alliance. |