EXPLORING THE IMPACT OF DATA UNCERTAINTIES IN AUTONOMOUS GROUND VEHICLE PLATOONING

To improve robustness of autonomous vehicles, deployments have evolved from a single intelligent system to a combination of several within a platoon. Platooning vehicles move together as a unit, communicating with each other to navigate the changing environment safely. While the technology is robust, there is a large dependence on data collection and communication. Issues with sensors or communication systems can cause significant problems for the system. There are several uncertainties that impact a system’s fidelity. Small errors in data accuracy can lead to system failure under certain circumstances. We define stale data as a perturbation within a system that causes it to repetitively rely on old data from external data sources (e.g. other cars in the platoon). This paper conducts a fault injection campaign to analyze the impact of stale data in a platooning model, where stale data occurs in the car’s communication and/or perception system. The fault injection campaign accounts for different occurrences of a communication error. Our analysis provides an understanding of the sensitivity of each model parameter in causing system failures (e.g. a crash between vehicles within the platooning model). By understanding which parameters are most influential to the fidelity of the model, we enable the ability to make platooning algorithms safer.

Citation: A. St. Louis and J. C. Calhoun, “Exploring the Impact of Data Uncertainties in Autonomous Ground Vehicle Platooning,” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 15-17, 2023.