Collaborative Research: Road Information Discovery through Privacy-Preserved Collaborative Estimation in Connected Vehicles
This project will promote the progress of science and advance the national prosperity and welfare, by investigating novel methodologies leading to efficient road information discovery, as well as safe and efficient transportation systems. Real-time and crowd-sourced road information, such as black ice, pothole, and road roughness, can improve vehicle performance. Existing road information discovery approaches are not always practically viable, due to limitations in road coverage and lack of robustness. This award supports development of a novel collaborative road information crowdsourcing methodology using connected vehicles. The new methodology will enable efficient, robust, and broad-coverage road information discovery by utilizing connected vehicles as mobile sensors while preserving privacy of the participating vehicles. The crowd-sourced information can be incorporated in vehicle controls to improve safety, efficiency, and comfort. In addition, the new up-to-date road condition information will help address the nation?s urgent need to rebuild and modernize road infrastructure, by informing the road maintenance and repair plans. This research involves several disciplines including vehicle dynamics, optimal estimation, iterative learning control, and privacy. The multi-disciplinary approach will help broaden participation of underrepresented groups in research and positively impact engineering education.
The privacy-preserved collaborative estimation using connected vehicles is expected to make vehicle-based road information discovery practically and economically viable. This project will support work to overcome several scientific challenges that need to be overcome to realize full application potential of such connected systems. The research team will develop jump-diffusion process-based estimation to enhance road information discovery performance when dealing with abrupt input/disturbance changes in a single vehicle setting. The team will also develop iterative learning-based collaborative estimation across heterogeneous vehicles to enable the exploitation of local estimation from a network of heterogeneous agents to iteratively improve the performance of road information discovery. Finally, the research group will design dynamics-enabled privacy preservation schemes to protect vehicle privacy without affecting computation fidelity or incurring large computation/communication overhead, and evaluate the methodology in the application of collaborative road profile estimation.