no code implementations • 20 Mar 2024 • Ruolin Li, Philip N. Brown, Roberto Horowitz
In this study, we introduce a toll lane framework that optimizes the mixed flow of autonomous and high-occupancy vehicles on freeways, where human-driven and autonomous vehicles of varying commuter occupancy share a segment.
1 code implementation • 25 Apr 2022 • Xiao Tan, Jingbo Gao, Ruolin Li
As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications. One effective way to improve the security of deep learning models is to perform adversarial training, which allows the model to be compatible with samples that are deliberately created for use in attacking the model. Based on this, we propose a simple architecture to build a model with a certain degree of robustness, which improves the robustness of the trained network by adding an adversarial sample detection network for cooperative training.
no code implementations • 18 Jul 2021 • Ruolin Li, Philip N. Brown, Roberto Horowitz
We give the conditions for the proportion of altruistic vehicles and the weight configuration of the altruistic costs, under which the social delay can be decreased or reach the optimal.
no code implementations • 7 Jul 2021 • Ruolin Li, Philip N. Brown, Roberto Horowitz
We consider the scenario where human-driven/autonomous vehicles with low/high occupancy are sharing a segment of highway and autonomous vehicles are capable of increasing the traffic throughput by preserving a shorter headway than human-driven vehicles.