Connected and Automated Vehicles

This paper presents a specification for an automated freeway in a fully formal manner. A series of safety analyses have been carried out on the specification. The objective of the program is to derive a technique of safety analysis for such systems. Readers are advised to consult " Methods for Analysis of IVHS Safety: Final Report of PATH MOU 19" by the author for background information to this report.

This document presents Dynamic Visualization, a project associated with the California PATH Program. The objective of the project is to develop a software which can animate automated highways, visualize the dynamics of automatic vehicles, and help the design and evaluation of automatic vehicle systems. This report summarizes the accomplishments of the project, describes the functions of the developed software, and provides an explanation of how to use the software.

The focus of this project was to examine the potential travel, emissions, and consumer benefits of advanced freeway automation and travel demand management measures. The Sacramento Regional Travel Demand model (SACMET 95) was used to simulate the travel effects of travel demand management measures in the Sacramento region for a twenty year time horizon. The scenarios examined included various combinations of automated freeways, new High Occupancy Vehicle (HOV) lanes, transit, land use intensification, and pricing policies.

In this article, we demonstrate a zero-shot transfer of an autonomous driving policy from simulation to University of Delaware's scaled smart city with adversarial multi-agent reinforcement learning, in which an adversary attempts to decrease the net reward by perturbing both the inputs and outputs of the autonomous vehicles during training. We train the autonomous vehicles to coordinate with each other while crossing a roundabout in the presence of an adversary in simulation. The adversarial policy successfully reproduces the simulated behavior and incidentally outperforms, in terms of...