A Markov Decision Process Model for a Reinforcement Learning-based Autonomous Pedestrian Crossing Protocol

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21260%2F21%3A00357837" target="_blank" >RIV/68407700:21260/21:00357837 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/MENACOMM50742.2021.9678310" target="_blank" >https://doi.org/10.1109/MENACOMM50742.2021.9678310</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/MENACOMM50742.2021.9678310" target="_blank" >10.1109/MENACOMM50742.2021.9678310</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Markov Decision Process Model for a Reinforcement Learning-based Autonomous Pedestrian Crossing Protocol

Popis výsledku v původním jazyce

Autonomous Traffic Management (ATM) systems empowered with Machine Learning (ML) technics are a promising solution for eliminating traffic light and decreasing traffic congestion in the future. However, few efforts have focused on integrating pedestrians in ATM, namely the static programming-based cooperative protocol called Autonomous Pedestrian Crossing (APC). In this paper, we model a Markov Decision Process (MDP) to enable a Deep Reinforcement Learning (DRL)-based version of APC protocol that is able to dynamically achieve the same objectives (i.e. decreasing traffic delay at the crossing area). Using concrete state space, action set and reward functions, our model forces the Autonomous Vehicle (AV) to "think"and behave according to APC architecture. Compared to the traditional programming APC system, our approach permits the AV to learn from its previous experiences in non-signalized crossing and optimize the distance and the velocity parameters accordingly.

Název v anglickém jazyce

A Markov Decision Process Model for a Reinforcement Learning-based Autonomous Pedestrian Crossing Protocol

Popis výsledku anglicky

Autonomous Traffic Management (ATM) systems empowered with Machine Learning (ML) technics are a promising solution for eliminating traffic light and decreasing traffic congestion in the future. However, few efforts have focused on integrating pedestrians in ATM, namely the static programming-based cooperative protocol called Autonomous Pedestrian Crossing (APC). In this paper, we model a Markov Decision Process (MDP) to enable a Deep Reinforcement Learning (DRL)-based version of APC protocol that is able to dynamically achieve the same objectives (i.e. decreasing traffic delay at the crossing area). Using concrete state space, action set and reward functions, our model forces the Autonomous Vehicle (AV) to "think"and behave according to APC architecture. Compared to the traditional programming APC system, our approach permits the AV to learn from its previous experiences in non-signalized crossing and optimize the distance and the velocity parameters accordingly.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2021 3rd IEEE Middle East and North Africa COMMunications Conference (MENACOMM)

ISBN

978-1-6654-3443-0

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

147-151

Název nakladatele

IEEE

Místo vydání

Piscataway, NJ

Místo konání akce

Agadir

Datum konání akce

3. 12. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—