Connected and Automated vehicles (CAVs) use internet connectivity and telecommunication systems to interact with other vehicles, infrastructure and devices in the driving environment.
Our research explores the technical properties CAV technology, its applications and how implementation will impact existing data sources and infrastructure. By prioritizing CAV research, we can improve the safety, efficiency, mobility and sustainability of transportation systems in our highly digitized and connected world.
Source: U.S. Department of Transportation
Imagine a world where your vehicle can “talk” with the road, traffic lights and other cars around it. We work with cutting-edge technologies like 5G (the latest generation of mobile networking) and MEC (the most powerful computing network architecture) to create an optimal communications framework to support CAVs and smart roadways. We compare traditional dedicated short-range communications (DSRC) systems to 5G Cellular Vehicle-to-Everything (C-V2X) systems in safety, information and entertainment CAV use cases.
Lead Researcher: Kaizhe Hou (PhD student)
Research Team Members: Huiyu Chen (Postdoctoral Fellow), Gary Zhang (PhD Student)
Funding Organizations: NSERC IRC and TELUS
Current Road Weather Information Systems (RWIS) installed at roadsides provide information only for their immediate geographical area, and often these systems are miles apart, resulting in information gaps. What if vehicles themselves could be road-condition sensors, capable of gathering data directly and in real time?
We seek to revolutionize real-time road monitoring by using onboard vehicle sensors in CAVs to supplement existing RWIS, to better detect and communicate winter road surface conditions. Our research uses machine learning algorithms to automatically classify road surface conditions via a variety of data sources.
Lead Researcher: Gary Zhang (PhD Student)
Research Team Members: Mingwei Lu (MSc Student) and Kevin Wu (Engineering Undergraduate Student)
Funding Organizations: NSERC IRC, Arcadis IBI Group
Work zones are potentially hazardous areas, and CAVs have the potential to increase safety if physical boundary markers like barricades and cones are digitized. We are developing algorithms to estimate the coordinates of work zones using cameras as the main source of input data. The goal is to design a real-time digital navigation system for work zones that uses computer vision algorithms and C-V2X communication technology to detect and transmit information about work zone boundaries and the presence of workers.
Lead Researcher: Siqi Yan (PhD student)
Research Team Members: Gary Zhang (PhD Student), Mingwei Lu (MSc Student)
Funding Organizations: NSERC IRC and ATS Traffic
CAV technology promises to transform traffic operations and mobility in a multi-modal transportation system. We are developing a future-proof and highly efficient control method to tackle traffic challenges in mixed traffic environments. Our objective is to integrate the benefits of C-V2X into the next generation of ITS to enhance traffic operation efficiency and advance mobility safety by developing and improving various C-V2X use cases like traffic signal control and vulnerable road users detection.
Lead Researcher: Fan Wu (PhD student)
Research Team Members: Kaizhe Hou (PhD student), Dr. Xuelong Zhao (Visiting Scholar)
Funding Organizations: NSERC IRC and Stantec
The development of vehicle control technologies, including automated and semi-automated vehicles, is accelerating faster than ever, but with a consequent lag in the development of safety frameworks for their deployment. There is an emergent and urgent need to develop what might be called a safety deployment framework (SDF) to exploit the value of new technologies while ensuring the provision of operating and training support for their safe deployment. New research and development are needed to build quantitative data-driven frameworks for evaluation of safety.
In this challenge, three important areas must be considered: 1) disciplined capture of operating data within a general framework, 2) the integration of data to inform the construction of predictive models to predict dynamic safety conditions of an SDF, and 3) the development of a human-vehicle interface dashboard that serves as both operator training simulator and operator control dashboard. This project seeks to develop and integrate prototype solutions to these three challenges.
Co-Principal Investigators: Dr. Randy Goebel and Dr. Tony Qiu
Research Team Members: Gary Zhang (PhD Student) and Jiayi Dai (Research Assistant)
Funding Organization: Government of Alberta
Latest Publications
Shuhuan Wen, Xin Liu, Jing Zhao, Tony Z. Qiu and Zhang Hong. Edge-Assisted Multi-Robot Visual-Inertial SLAM with Efficient Communication. IEEE Transactions on Automation Science and Engineering, 2024. DOI: 10.1109/TASE.2024.3376427
Shuxian He, Yuhao Du, Jiangchen Li, Liqun Peng, Tony Z. Qiu, Yi Zhang and Jianhua Zhang. Second-based queue length estimation with fusing MMW and low penetration rate CAV trajectory data. Transportmetrica B: Transport Dynamics. Vol. 12, no. 1, 2024. DOI: 10.1080/21680566.2024.2315509
Shuxian He, Yi He, Yi Zhang, Qiuling Shi and Tony Z. Qiu. Back-Pressure-based Traffic Signal and Discretized Trajectory Joint Control for Low CAV Penetration Rate Environment. IEEE Transactions on Intelligent Vehicles, 2024. DOI: 10.1109/TIV.2024.3382243.
Huiyu Chen, Fan Wu and Tony Z. Qiu. Achieving Energy-Efficient and Travel Time-Optimized Trajectory and Signal Control for CAEVs. IEEE Transactions on Intelligent Transportation Systems, 2024.
Huiyu Chen, Fan Wu, Kaizhe Hou and Tony Z. Qiu. Leveraging Dynamic Right-of-Way Allocation and Tolling Policy for CAV Dedicated Lane Management to Promote CAV and Improve Mobility. IEEE Transactions on Intelligent Transportation Systems, 2024. DOI: 10.1109/TITS.2023.3347392.
Amir Zakerimanesh, Tony Z. Qiu and M. Tavakoli. Stability and Intervehicle Distance Analysis of Vehicular Platoons: Highlighting the Impact of Bidirectional Communication Topologies. IEEE Transactions on Control Systems Technology, Jan. 2024. DOI: 10.1109/TCST.2023.3348072.
Peng Li, Shuhuan Wen, Chengrui Xu and Tony Z. Qiu. Visual Place Recognition for Opposite Viewpoints and Environment Changes. IEEE Transactions on Instrumentation and Measurement. Vol. 73, pp. 1-9, 2024, Art no. 5007509, DOI: 10.1109/TIM.2024.3350152.
For a full list of all publications, click here.