Flow: A Modular Learning Framework for Mixed Autonomy Traffic
Name
1710.05465v4.pdf
Description
Submitted version
Size
9.65 MB
Format
Adobe PDF
Checksum (MD5)
50cf762301728326950066e35e77875c
Author(s)
Wu, Cathy
Kreidieh, Abdul Rahman
Parvate, Kanaad
Vinitsky, Eugene
Bayen, Alexandre M
Date Issued
2022
Journal
IEEE Transactions on Robotics
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Wu, Cathy, Kreidieh, Abdul Rahman, Parvate, Kanaad, Vinitsky, Eugene and Bayen, Alexandre M. 2022. "Flow: A Modular Learning Framework for Mixed Autonomy Traffic." IEEE Transactions on Robotics, 38 (2).
Version
Original manuscript
Abstract
The rapid development of autonomous vehicles (AVs) holds vast potential for
transportation systems through improved safety, efficiency, and access to
mobility. However, the progression of these impacts, as AVs are adopted, is not
well understood. Numerous technical challenges arise from the goal of analyzing
the partial adoption of autonomy: partial control and observation,
multi-vehicle interactions, and the sheer variety of scenarios represented by
real-world networks. To shed light into near-term AV impacts, this article
studies the suitability of deep reinforcement learning (RL) for overcoming
these challenges in a low AV-adoption regime. A modular learning framework is
presented, which leverages deep RL to address complex traffic dynamics. Modules
are composed to capture common traffic phenomena (stop-and-go traffic jams,
lane changing, intersections). Learned control laws are found to improve upon
human driving performance, in terms of system-level velocity, by up to 57% with
only 4-7% adoption of AVs. Furthermore, in single-lane traffic, a small neural
network control law with only local observation is found to eliminate
stop-and-go traffic - surpassing all known model-based controllers to achieve
near-optimal performance - and generalize to out-of-distribution traffic
densities.
MIT Department
Massachusetts Institute of Technology. Department of Civil and Environmental Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/TRO.2021.3087314
