Graph neural network reinforcement learning for autonomous mobility-on-demand systems

D Gammelli, K Yang, J Harrison… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
Autonomous mobility-on-demand (AMoD) systems represent a rapidly develo** mode of
transportation wherein travel requests are dynamically handled by a coordinated fleet of …

Graph meta-reinforcement learning for transferable autonomous mobility-on-demand

D Gammelli, K Yang, J Harrison, F Rodrigues… - Proceedings of the 28th …, 2022 - dl.acm.org
Autonomous Mobility-on-Demand (AMoD) systems represent an attractive alternative to
existing transportation paradigms, currently challenged by urbanization and increasing …

The+ 1 method: model-free adaptive repositioning policies for robotic multi-agent systems

C Ruch, J Gächter, J Hakenberg… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Robotic multi-agent systems can efficiently handle spatially distributed tasks in dynamic
environments. Problem instances of particular interest, and generality are the dynamic …

Data-driven h-infinity control with a real-time and efficient reinforcement learning algorithm: An application to autonomous mobility-on-demand systems

A Aalipour, A Khani - arxiv preprint arxiv:2309.08880, 2023 - arxiv.org
Reinforcement learning (RL) is a class of artificial intelligence algorithms being used to
design adaptive optimal controllers through online learning. This paper presents a model …

Modeling, Analysis, and Control of Autonomous Mobility-on-Demand Systems: A Discrete-Time Linear Dynamical System and a Model Predictive Control Approach

A Aalipour, A Khani - IEEE Transactions on Intelligent …, 2024 - ieeexplore.ieee.org
Autonomous vehicles are rapidly evolving and will soon enable large-scale mobility-on-
demand (MoD) systems applications. Managing the fleets of available vehicles, commonly …

A modular and transferable reinforcement learning framework for the fleet rebalancing problem

E Skordilis, Y Hou, C Tripp, M Moniot… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
Mobility on demand (MoD) systems show great promise in realizing flexible and efficient
urban transportation. However, significant technical challenges arise from operational …

Learning to control autonomous fleets from observation via offline reinforcement learning

C Schmidt, D Gammelli, FC Pereira… - 2024 European …, 2024 - ieeexplore.ieee.org
Autonomous Mobility-on-Demand (AMoD) systems are an evolving mode of transportation in
which a centrally coordinated fleet of self-driving vehicles dynamically serves travel …

A survey of machine learning-based ride-hailing planning

D Wen, Y Li, FCM Lau - IEEE Transactions on Intelligent …, 2024 - ieeexplore.ieee.org
Ride-hailing is a sustainable transportation paradigm where riders access door-to-door
traveling services through a mobile phone application, which has attracted a colossal …

Maximum throughput dispatch for shared autonomous vehicles including vehicle rebalancing

J Robbennolt, MW Levin - IEEE Transactions on Intelligent …, 2023 - ieeexplore.ieee.org
Shared autonomous vehicles (SAVs) provide on demand point-to-point transportation for
passengers. This service has been extensively studied using dispatch heuristics and agent …

Implementing reinforcement learning for on-demand vehicle rebalancing in MATSim

T Chouaki, S Hörl, J Puchinger - Procedia Computer Science, 2022 - Elsevier
In this paper, we present a software architecture that extends the MATSim mobility
simulation framework by providing an external rebalancing server, which offers a set of …