Automated Vehicle

Connected and automated vehicle (CAV) technologies endow great potentials for future transportation systems, and stand for a new way forward in mobility. As a transformative technology that is capable of sensing its environment and moving safely with little or no human input, automated vehicle has the significant potential of enhancing traffic safety, improving traffic congestion, and reducing energy consumption. The impact of driverless vehicles will be profound, touching almost every aspect of our lives, and the level of disruption will be staggering.

Our efforts in this field include the following aspects:

(1) Systematic development, testing, validation, and operation of autonomous vehicles. We are excited about the opportunities that are made possible by the brand new Chrysler Pacifica-based autonomous vehicle and LTI’s test track facility. We are currently working on the HD Map generation, Perception, Prediction, and Control of the autonomous vehicle. We look forward to exploring many more exciting opportunities with the colleagues at PSU and beyond.

Demo video 1: Way Point Following Demonstration on the Test Track (check out Youtube Channel for more videos)

 

Demo video 2: AV demo with real-time Lidar and camera data

Demo video 3: Test of CARMA CDA stack on Penn State campus 

(2) Development, testing, and deployment of Leader-Follower Cooperative Driving Automation technologies, in particular, Autonomous Truck Mounted Attenuator (ATMA), to reduce fatalities of DOT engineers in work zone locations. Self-driving technologies, although possibly years away from wide application to general public travel, are receiving attention from many State DOTs in a niche area of using Autonomous Maintenance Technology (AMT) to safely maintain transportation infrastructure. As a newly developed technology, the federal regulation and industrial standard are essential missing, which call for the research from academia to establish the foundations. My research team has been working closely with USDOT/FHWA, Colorado DOT, Missouri DOT, and AMT pool fund with over a dozen state DOT members in this effort.

For more details of ATMA research please click here

ATMA Field Testing in Colorado 

 

(3) Analysis of the impact of autonomous vehicles to transportation infrastructure, and what it takes to prepare infrastructure to support system wide autonomous vehicles deployment. As autonomous vehicles rely on sensors like LiDAR and cameras to perceive the surrounding environment, and they follow the command from computer algorithms to operate, the transportation infrastructure that is needed for their deployment can be very different from those currently in place.

Sponsored Projects:

  1. 10 projects on ATMA, sponsored by USDOT, AMT pooled fund (through Colorado DOT), Missouri DOT, Pennsylvania Department of Community and Economic Development (DCED), and industry
  2. PSU PI. “Preparation of Pavement Infrastructure for Connected and Autonomous Vehicle Deployment – Phase I”. USDOT through National Center for Transportation Infrastructure Durability and Life Extension (NCTriDurLE). 2022-2023.
  3. PSU PI. “AI-Based Prediction Models for Transportation Infrastructure Asset Management Data Hub – Phase I”. USDOT through National Center for Transportation Infrastructure Durability and Life Extension (NCTriDurLE). 2022-2023.
  4. Co-PI. Transportation Safety Training in Rural Areas: An Exploration of Virtual Reality and Driving Simulation in Driver Response and Awareness. US Department of Transportation through Mid-America Transportation Center. 2020-2021.
  5. Co-PI. GAANN: A Fellowship Program in Civil Engineering for Infrastructure Preservation and Resilience with Emerging Technologies. Department of Education. 2022-2024.
  6. PI. “Socially Responsible AI for Autonomous Vehicles”. Center for Socially Responsible Artificial Intelligence. PennState. 2022-2023

Publications

  1. H. Qi, C. Chen#, X. Hu (2024). Bridging Specified States With Stochastic Behavioral-Consistent Vehicle Trajectories for Enhanced Digital Twin Simulation Realism,” in IEEE Internet of Things Journal, https://doi.org/10.1109/JIOT.2024.3365657
  2. Chen, C.#, Tang, Q.#, Hu, X., Huang, Z. (2023). Infrastructure Sensor-based Cooperative Perception for Early Stage Connected and Automated Vehicle Deployment. Journal of Intelligent Transportation Systems Technology Planning and Operations. https://doi.org/10.1080/15472450.2023.2257596
  3. Chen, C.#, Song, Y. #, Hu, X., Wang, D., Liu, J. (2023). A Machine Learning-Based Approach to Assess Impacts of Autonomous Vehicles on Pavement Roughness. Philosophical Transactions of the Royal Society A. https://doi.org/10.1098/rsta.2022.0176
  4. Qi, H., Hu, X. (2023). Behavioral Investigation of Stochastic Lateral Wandering Patterns in Mixed Traffic Flow. Transportation Research Part C. https://doi.org/10.1016/j.trc.2023.104310
  5. Qi, H., Song, Y. #, Huang, Z., Hu, X.* (2023). Deadlock Detection, Cooperative Avoidance and Recovery Protocol for Mixed Autonomous Vehicles in Unstructured Environment. IET Intelligent Transport Systems. https://doi.org/10.1049/itr2.12338
  6. Tang, Q.#, Hu, X.* (2022). A Multi-State Merging Based Analytical Model for an Operation Design Domain of Autonomous Vehicles in Work Zones on Two-lane Highways. Journal of Intelligent Transportation Systems Technology Planning and Operations. https://doi.org/10.1080/15472450.2022.2130697
  7. Qi, H., Chen, C. #, Hu, X.*, Zhang, J. (2022) Online Inference of Lane Changing Events for Connected and Automated Vehicle Applications with Analytical Logistic Diffusion Stochastic Differential Equation. Transportation Research Part C: Emerging Technologies. 144, 103874. https://doi.org/10.1016/j.trc.2022.103874
  8. Cheng, Y. #, Hu, X. *, Chen, K., Yu, X., Luo, Y. (2022). Online Longitudinal Trajectory Planning for Connected and Autonomous Vehicles in Mixed Traffic Flow with Deep Reinforcement Learning Approach. Journal of Intelligent Transportation Systems Technology Planning and Operations. https://doi.org/10.1080/15472450.2022.2046472
  9. Tang, Q.#, Hu, X.*, Ru, Q. (2021). Development of Operation Guidelines for Leader-Follower Autonomous Maintenance Vehicles at Work Zone Locations. Transportation Research Record: Journal of the Transportation Research Board. https://doi.org/10.1177/03611981211056644
  10. Tang, Q.#, Hu, X.*, Yang, H. (2021). Identification of Operational Design Domain for Autonomous Truck Mounted Attenuator System on Multilane Highways. Transportation Research Record: Journal of the Transportation Research Board. https://doi.org/10.1177/03611981211061555
  11. Cheng, Y.#, Chen, C.#, Hu, X.*, Chen, K., Tang, Q.#, Song, Y.# (2021). Enhancing Mixed Traffic Flow Safety via Connected and Autonomous Vehicle Trajectory Planning with a Reinforcement Learning Approach. Journal of Advanced Transportation. https://doi.org/10.1155/2021/6117890
  12. Qi, H., Dai, R., Tang, Q.#, Hu, X.* (2020). Quasi-Real Time Estimation of Turning Movement Spillover Events Based on Partial Connected Vehicle Data. Transportation Research Part C: Emerging Technologies. https://doi.org/10.1016/j.trc.2020.102824
  13. Cheng, Y.#, Tang, Q.#, Hu, X.*, Qi, H., Yang, H. (2020). A Monte Carlo Tree Search-Based Mixed Traffic Flow Control Algorithm for Arterial Intersection. Transportation Research Record: Journal of the Transportation Research Board.  https://doi.org/10.1177%2F0361198120919746
  14. Tang, Q., Cheng, Y., Hu, X.*, Chen, C. , Song, Y. , Qin, R. (2020). Evaluation Methodology of Leader-Follower Autonomous Vehicle System for Work Zone Maintenance. Transportation Research Record: Journal of the Transportation Research Board. https://doi.org/10.1177%2F0361198120985233