Intelligent Transportation Systems

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...

A wide range of reinforcement learning (RL) problems --- including robustness, transfer learning, unsupervised RL, and emergent complexity --- require specifying a distribution of tasks or environments in which a policy will be trained. However, creating a useful distribution of environments is error prone, and takes a significant amount of developer time and effort. We propose Unsupervised Environment Design (UED) as an alternative paradigm, where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid,...

A left-turning vehicle (Subject Vehicle, SV) attempting to cross the path of an oncoming vehicle (Principal Other Vehicle, POV) at an intersection typically does not have the right of way. The main task of the SV driver is to find an adequate opportunity in opposing traffic to initiate the left-turn maneuver. To reduce the probability of a conflict, warning systems, such as Intersection Decision Support (IDS) systems, are being developed. These systems alert drivers of SV vehicles attempting to negotiate a left turnabout traffic approaching from the opposite direction. The current paper (i...

This bibliography is intended to serve as a guide to sources of information in Intelligent Transportation Systems. While it focuses primarily on U.S. and Canadian publications, some international materials have been included. Emphasis is on current publications, however, some materials of historical interest have also been included. Although the term ITS (Intelligent Transportation Systems) is considered to be the more current terminology, the term IVHS (Intelligent Vehicle Highway Systems) has been retained and used when appropriate to reflect older publications of historical significance...