Collaborative Research: CPS: Medium: Transforming Connected and Automated Transportation with Smart Networking, Cooperative Sensing, and Edge Computing

Principal Investigator: Yiheng Feng

Several recent technology trends are expected to transform ground transportation systems: much higherspeed wireless connectivity, improved on-vehicle and infrastructure sensing capabilities, and advances in machine learning. So far, most research and development efforts on connected and automated vehicles (CAVs) focused on individual technology. This leads to limited benefits, as communication, sensing, and computation functionalities are inherently tightly coupled. This project makes two foundational contributions in the ground transportation CPS domain. First, it advances the state-of-the-art of communication (focusing on the emerging 5G while embracing other wireless technologies), sensing (drastically scaling up cooperative raw sensor data sharing), and computation (applying distributed learning to a new domain) for CAV applications. Second, it proposes a run-time optimization framework that performs context-aware adaptation to meet application-specific requirements by jointly considering the networking, sensing, and computation dimensions. The project then applies the above innovations to support three CAV applications: enhancement of public service personnel's safety, alleviation of congestion at bottleneck areas, and protection of vulnerable road users (VRUs). In addition to simulationbased evaluations using CARMA, the team will prototype and evaluate the proposed work in Mcity, the world's first purpose-built proving ground for testing the performance of CAVs under controlled and realistic conditions.

Keywords: Data analytics and machine learning, Networking, Transportation including air and ground