Connected and Automated Vehicles

Motion Planning in Understructured Road Environments with Stacked Reservation Grids

Wu, Fangyu
Wang, Dequan
Hwang, Minjune
Hao, Chenhui
Bayen, Alexandre M.
2008

Motion planning of autonomous vehicles in understructured road environments is challenging owing to a lack of an efficient and analyzable representation of the contextual information. On one hand, idealistic representations like splines, while efficient and interpretable, are not versatile enough to encode the full complexity of the environment. On the other hand, high-fidelity representations like images, although rich in contents, are computationally expensive to decode and are not readily analyzable. To address this problem, we propose a new data structure named stacked reservation grid (...

How Safe Are Driverless Cars?: Steven Shladover / Research Engineer, UC-Berkeley Institute of Transportation Studies

May 26, 2025

NHK World Japan Steven Shladover

Dr Steven Shladover, Institute of Transportation Studies and Partners for Advanced Transportation Technology (PATH) researcher, discussed How Safe Are Driverless Cars?: Steven Shladover / Research Engineer, UC-Berkeley Institute of Transportation Studies...

Viability-based computation of spatially constrained minimum time trajectories for an autonomous underwater vehicle: implementation and experiments

Tinka, Andrew
Diemer, S.
2009

A viability algorithm is developed to compute the constrained minimum time function for general dynamical systems. The algorithm is instantiated for a specific dynamics (Dubin's vehicle forced by a flow field) in order to numerically solve the minimum time problem. With the specific dynamics considered, the framework of hybrid systems enables us to solve the problem efficiently. The algorithm is implemented in C using epigraphical techniques to reduce the dimension of the problem. The feasibility of this optimal trajectory algorithm is tested in an experiment with a light autonomous...

Viability-based computation of spatially constrained minimum time trajectories for an autonomous underwater vehicle: implementation and experiments

Tinka, Andrew
Diemer, S.
Bayen, Alexandre M.
2009

A viability algorithm is developed to compute the constrained minimum time function for general dynamical systems. The algorithm is instantiated for a specific dynamics (Dubin's vehicle forced by a flow field) in order to numerically solve the minimum time problem. With the specific dynamics considered, the framework of hybrid systems enables us to solve the problem efficiently. The algorithm is implemented in C using epigraphical techniques to reduce the dimension of the problem. The feasibility of this optimal trajectory algorithm is tested in an experiment with a light autonomous...

Autonomous River Navigation Using the Hamilton–Jacobi Framework for Underactuated Vehicles

Weekly, Kevin
Tinka, Andrew
Anderson, Leah
Bayen, Alexandre M.
2014

The feasibility of drifter studies in complex and tidally forced water networks has been greatly expanded by the introduction of motorized floating sensors. This paper presents a method for such motorized sensors to accomplish obstacle avoidance and path selection using the solutions to Hamilton-Jacobi-Bellman-Isaacs (HJBI) equations. The method is then validated experimentally.

ZUbers against ZLyfts Apocalypse: An Analysis Framework for DoS Attacks on Mobility-As-A-Service Systems

Yuan, Chenyang
Thai, Jérôme
Bayen, Alexandre M.
2016

The vulnerability of Mobility-as-a-Service (MaaS) systems to Denial-of-Service (DoS) attacks is studied. We use a queuing-theoretical framework to model the re-dispatch process used by operators to maintain a high service availability, as well as potential cyber-attacks on this process. It encompasses a customer arrival rate model at different sections of an urban area to pick up vehicles traveling within the network. Expanding this re-balance model, we analyze DoS cyber-attacks of MaaS systems by controlling a fraction of the cars maliciously through fake reservations (so called Zombies)...

Future Road Transportation Technology

Wang, Junhua
Iwasaki, Randy
Bayen, Alexandre M.
Harvey, John
2016

As road transportation brings us great life changes, it also brings safety and environment problems. Near one million people died in road accidents each year and road constructions consumed un-countable ...

Emergent Behaviors in Mixed-Autonomy Traffic

Wu, Cathy
Kreidieh, Aboudy
Vinitsky, Eugene
Bayen, Alexandre M.
2017

Traffic dynamics are often modeled by complex dynamical systems for which classical analysis tools can struggle to provide tractable policies used by transportation agencies and planners. In light of the introduction of automated vehicles into transportation systems, there is a new need for understanding the impacts of automation on transportation networks. The present article formulates and approaches the mixed-autonomy traffic control problem (where both automated and human-driven vehicles are present) using the powerful framework of deep reinforcement learning (RL). The resulting...

Stabilizing Traffic with Autonomous Vehicles

Wu, Cathy
Bayen, Alexandre M.
Mehta, Ankur
2018

Autonomous vehicles promise safer roads, energy savings, and more efficient use of existing infrastructure, among many other benefits. Although the effect of autonomous vehicles has been studied in the limits (near-zero or full penetration), the transition range requires new formulations, mathematical modeling, and control analysis. In this article, we study the ability of small numbers of autonomous vehicles to stabilize a single-lane system of human-driven vehicles. We formalize the problem in terms of linear string stability, derive optimality conditions from frequency-domain analysis,...

Benchmarks for Reinforcement Learning in Mixed-Autonomy Traffic

Vinitsky, Eugene
Kreidieh, Aboudy
Flem, Luc Le
Kheterpal, Nishant
Jang, Kathy
Bayen, Alexandre M.
2018

We release new benchmarks in the use of deep reinforcement learning (RL) to create controllers for mixed-autonomy traffic, where connected and autonomous vehicles (CAVs) interact with human drivers and infrastructure. Benchmarks, such as Mujoco or the Arcade Learning Environment, have spurred new research by enabling researchers to effectively compare their results so that they can focus on algorithmic improvements and control techniques rather than system design. To promote similar advances in traffic control via RL, we propose four benchmarks, based on three new traffic scenarios,...