Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming

Mengzhe Huang, Weinan Gao, Zhong-Ping Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Cooperative driving with V2V communication is under extensive investigation, because of its potential to increase the safety, reliability, connectivity, and autonomy of transportation systems. This paper studies the problem of connected cruise control (CCC) for a platoon of human-driven and autonomous vehicles. Motional data, such as distance and velocity information, are transmitted by vehicle-to-vehicle (V2V) communication between connected vehicles. Taking into account the communication latency and unpredictable behavior in the leading vehicle, we formulate the CCC problem as an adaptive optimal control problem with input delay and disturbance. A novel data-driven control solution is proposed for the vehicle platoon, which guarantees that each vehicle can achieve safe distance and desired common velocity. Incorporating adaptive dynamic programming technique with sampled-data system theory, a data-driven adaptive optimal controller is learned from sampled data, without the knowledge of the human or vehicle dynamics of the platooning vehicles. Stability and robustness analyses are provided by means of input-to-state stability theory. Numerical results confirm the efficacy of our method.

Original languageEnglish (US)
Title of host publicationProceedings of the 36th Chinese Control Conference, CCC 2017
PublisherIEEE Computer Society
Pages9478-9483
Number of pages6
ISBN (Electronic)9789881563934
DOIs
StatePublished - Sep 7 2017
Event36th Chinese Control Conference, CCC 2017 - Dalian, China
Duration: Jul 26 2017Jul 28 2017

Other

Other36th Chinese Control Conference, CCC 2017
CountryChina
CityDalian
Period7/26/177/28/17

Fingerprint

Cruise control
Adaptive Dynamics
Vehicle Dynamics
Autonomous Vehicles
Dynamic programming
Dynamic Programming
Data-driven
Sampled-data Systems
Input Delay
Stability Theory
Systems Theory
Adaptive Control
Latency
Optimal Control Problem
Efficacy
Control Problem
Connectivity
Disturbance
Safety
Robustness

Keywords

  • Adaptive dynamic programming (ADP)
  • Connected vehicles
  • Delayed feedback

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Applied Mathematics
  • Modeling and Simulation

Cite this

Huang, M., Gao, W., & Jiang, Z-P. (2017). Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming. In Proceedings of the 36th Chinese Control Conference, CCC 2017 (pp. 9478-9483). [8028869] IEEE Computer Society. https://doi.org/10.23919/ChiCC.2017.8028869

Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming. / Huang, Mengzhe; Gao, Weinan; Jiang, Zhong-Ping.

Proceedings of the 36th Chinese Control Conference, CCC 2017. IEEE Computer Society, 2017. p. 9478-9483 8028869.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huang, M, Gao, W & Jiang, Z-P 2017, Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming. in Proceedings of the 36th Chinese Control Conference, CCC 2017., 8028869, IEEE Computer Society, pp. 9478-9483, 36th Chinese Control Conference, CCC 2017, Dalian, China, 7/26/17. https://doi.org/10.23919/ChiCC.2017.8028869
Huang M, Gao W, Jiang Z-P. Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming. In Proceedings of the 36th Chinese Control Conference, CCC 2017. IEEE Computer Society. 2017. p. 9478-9483. 8028869 https://doi.org/10.23919/ChiCC.2017.8028869
Huang, Mengzhe ; Gao, Weinan ; Jiang, Zhong-Ping. / Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming. Proceedings of the 36th Chinese Control Conference, CCC 2017. IEEE Computer Society, 2017. pp. 9478-9483
@inproceedings{66b681cba47e426fbb451ce0b97a474d,
title = "Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming",
abstract = "Cooperative driving with V2V communication is under extensive investigation, because of its potential to increase the safety, reliability, connectivity, and autonomy of transportation systems. This paper studies the problem of connected cruise control (CCC) for a platoon of human-driven and autonomous vehicles. Motional data, such as distance and velocity information, are transmitted by vehicle-to-vehicle (V2V) communication between connected vehicles. Taking into account the communication latency and unpredictable behavior in the leading vehicle, we formulate the CCC problem as an adaptive optimal control problem with input delay and disturbance. A novel data-driven control solution is proposed for the vehicle platoon, which guarantees that each vehicle can achieve safe distance and desired common velocity. Incorporating adaptive dynamic programming technique with sampled-data system theory, a data-driven adaptive optimal controller is learned from sampled data, without the knowledge of the human or vehicle dynamics of the platooning vehicles. Stability and robustness analyses are provided by means of input-to-state stability theory. Numerical results confirm the efficacy of our method.",
keywords = "Adaptive dynamic programming (ADP), Connected vehicles, Delayed feedback",
author = "Mengzhe Huang and Weinan Gao and Zhong-Ping Jiang",
year = "2017",
month = "9",
day = "7",
doi = "10.23919/ChiCC.2017.8028869",
language = "English (US)",
pages = "9478--9483",
booktitle = "Proceedings of the 36th Chinese Control Conference, CCC 2017",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Connected cruise control for a platoon of human-operated and autonomous vehicles using adaptive dynamic programming

AU - Huang, Mengzhe

AU - Gao, Weinan

AU - Jiang, Zhong-Ping

PY - 2017/9/7

Y1 - 2017/9/7

N2 - Cooperative driving with V2V communication is under extensive investigation, because of its potential to increase the safety, reliability, connectivity, and autonomy of transportation systems. This paper studies the problem of connected cruise control (CCC) for a platoon of human-driven and autonomous vehicles. Motional data, such as distance and velocity information, are transmitted by vehicle-to-vehicle (V2V) communication between connected vehicles. Taking into account the communication latency and unpredictable behavior in the leading vehicle, we formulate the CCC problem as an adaptive optimal control problem with input delay and disturbance. A novel data-driven control solution is proposed for the vehicle platoon, which guarantees that each vehicle can achieve safe distance and desired common velocity. Incorporating adaptive dynamic programming technique with sampled-data system theory, a data-driven adaptive optimal controller is learned from sampled data, without the knowledge of the human or vehicle dynamics of the platooning vehicles. Stability and robustness analyses are provided by means of input-to-state stability theory. Numerical results confirm the efficacy of our method.

AB - Cooperative driving with V2V communication is under extensive investigation, because of its potential to increase the safety, reliability, connectivity, and autonomy of transportation systems. This paper studies the problem of connected cruise control (CCC) for a platoon of human-driven and autonomous vehicles. Motional data, such as distance and velocity information, are transmitted by vehicle-to-vehicle (V2V) communication between connected vehicles. Taking into account the communication latency and unpredictable behavior in the leading vehicle, we formulate the CCC problem as an adaptive optimal control problem with input delay and disturbance. A novel data-driven control solution is proposed for the vehicle platoon, which guarantees that each vehicle can achieve safe distance and desired common velocity. Incorporating adaptive dynamic programming technique with sampled-data system theory, a data-driven adaptive optimal controller is learned from sampled data, without the knowledge of the human or vehicle dynamics of the platooning vehicles. Stability and robustness analyses are provided by means of input-to-state stability theory. Numerical results confirm the efficacy of our method.

KW - Adaptive dynamic programming (ADP)

KW - Connected vehicles

KW - Delayed feedback

UR - http://www.scopus.com/inward/record.url?scp=85032185701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032185701&partnerID=8YFLogxK

U2 - 10.23919/ChiCC.2017.8028869

DO - 10.23919/ChiCC.2017.8028869

M3 - Conference contribution

SP - 9478

EP - 9483

BT - Proceedings of the 36th Chinese Control Conference, CCC 2017

PB - IEEE Computer Society

ER -