Data-Driven Adaptive Optimal Control of Connected Vehicles
Authors:
- 24 August 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 18 (5) , 1122-1133
Abstract
In this paper, a data-driven non-model-based approach is proposed for the adaptive optimal control of a class of connected vehicles that is composed of n human-driven vehicles only transmitting motional data and an autonomous vehicle in the tail receiving the broadcasted data from preceding vehicles by wireless vehicle-to-vehicle (V2V) communication devices. Considering the cases of range-limited V2V communication and input saturation, several optimal control problems are formulated to minimize the errors of distance and velocity and to optimize the fuel usage. By employing an adaptive dynamic programming technique, the optimal controllers are obtained without relying on the knowledge of system dynamics. The effectiveness of the proposed approaches is demonstrated via the online learning control of the connected vehicles in Paramics' traffic microsimulation.Keywords
Funding Information
- US National Science Foundation (ECCS-1230040, ECCS-1501044)
This publication has 46 references indexed in Scilit:
- On convergence and robustness of the Extended Cooperative Cruise Control2014
- Cooperative Adaptive Cruise Control: Network-Aware Analysis of String StabilityIEEE Transactions on Intelligent Transportation Systems, 2014
- Cooperative Adaptive Cruise Control in Real Traffic SituationsIEEE Transactions on Intelligent Transportation Systems, 2013
- Evaluation of a Methodology for Scalable Dynamic Vehicular Ad Hoc Networks in a Well-Calibrated Test Bed for Vehicular MobilityTransportation Research Record: Journal of the Transportation Research Board, 2013
- Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive ControllersIEEE Control Systems, 2012
- Traffic jams: dynamics and controlPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2010
- Model Predictive Multi-Objective Vehicular Adaptive Cruise ControlIEEE Transactions on Control Systems Technology, 2010
- Reinforcement learning of dynamic collaborative driving Part I: longitudinal adaptive controlInternational Journal of Vehicle Information and Communication Systems, 2008
- Output regulation for linear systems subject to input saturationAutomatica, 1996
- On the optimal error regulation of a string of moving vehiclesIEEE Transactions on Automatic Control, 1966