Development of A Stochastic Traffic Environment with Generative Time-Series Models for Improving Generalization Capabilities of Autonomous Driving Agents

Anil Ozturk, Mustafa Burak Gunel, Melih Dal, Ugur Yavas, Nazim Kemal Ure

Research output: Contribution to conferencePaperpeer-review

1 Citation (Scopus)

Abstract

Automated lane changing is a critical feature for advanced autonomous driving systems. In recent years, reinforcement learning (RL) algorithms trained on traffic simulators yielded successful results in computing lane changing policies that strike a balance between safety, agility and compensating for traffic uncertainty. However, many RL algorithms exhibit simulator bias and policies trained on simple simulators do not generalize well to realistic traffic scenarios. In this work, we develop a data driven traffic simulator by training a generative adverserial network (GAN) on real life trajectory data. The simulator generates randomized trajectories that resembles real life traffic interactions between vehicles, which enables training the RL agent on much richer and realistic scenarios. We demonstrate through simulations that RL agents that are trained on GAN-based traffic simulator has stronger generalization capabilities compared to RL agents trained on simple rule-driven simulators.

Original languageEnglish
Pages1343-1348
Number of pages6
DOIs
Publication statusPublished - 2020
Event31st IEEE Intelligent Vehicles Symposium, IV 2020 - Virtual, Las Vegas, United States
Duration: 19 Oct 202013 Nov 2020

Conference

Conference31st IEEE Intelligent Vehicles Symposium, IV 2020
Country/TerritoryUnited States
CityVirtual, Las Vegas
Period19/10/2013/11/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Funding

VIII. ACKNOWLEDGEMENTS This work is supported by Istanbul Technical University BAP Grant NO: MOA-2019-42321

FundersFunder number
Istanbul Technical University BAPMOA-2019-42321

    Fingerprint

    Dive into the research topics of 'Development of A Stochastic Traffic Environment with Generative Time-Series Models for Improving Generalization Capabilities of Autonomous Driving Agents'. Together they form a unique fingerprint.

    Cite this