Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Psarou, Anastasia, Akman, Ahmet Onur, Gorczyca, Łukasz, Hoffmann, Michał, Jamróz, Grzegorz, Kucharski, Rafał
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911005969219584
author Psarou, Anastasia
Akman, Ahmet Onur
Gorczyca, Łukasz
Hoffmann, Michał
Jamróz, Grzegorz
Kucharski, Rafał
author_facet Psarou, Anastasia
Akman, Ahmet Onur
Gorczyca, Łukasz
Hoffmann, Michał
Jamróz, Grzegorz
Kucharski, Rafał
contents Autonomous vehicles (AVs), possibly using Multi-Agent Reinforcement Learning (MARL) for simultaneous route optimization, may destabilize traffic networks, with human drivers potentially experiencing longer travel times. We study this interaction by simulating human drivers and AVs. Our experiments with standard MARL algorithms reveal that, both in simplified and complex networks, policies often fail to converge to an optimal solution or require long training periods. This problem is amplified by the fact that we cannot rely entirely on simulated training, as there are no accurate models of human routing behavior. At the same time, real-world training in cities risks destabilizing urban traffic systems, increasing externalities, such as $CO_2$ emissions, and introducing non-stationarity as human drivers will adapt unpredictably to AV behaviors. In this position paper, we argue that city authorities must collaborate with the ML community to monitor and critically evaluate the routing algorithms proposed by car companies toward fair and system-efficient routing algorithms and regulatory standards.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13188
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing
Psarou, Anastasia
Akman, Ahmet Onur
Gorczyca, Łukasz
Hoffmann, Michał
Jamróz, Grzegorz
Kucharski, Rafał
Multiagent Systems
Machine Learning
Robotics
Autonomous vehicles (AVs), possibly using Multi-Agent Reinforcement Learning (MARL) for simultaneous route optimization, may destabilize traffic networks, with human drivers potentially experiencing longer travel times. We study this interaction by simulating human drivers and AVs. Our experiments with standard MARL algorithms reveal that, both in simplified and complex networks, policies often fail to converge to an optimal solution or require long training periods. This problem is amplified by the fact that we cannot rely entirely on simulated training, as there are no accurate models of human routing behavior. At the same time, real-world training in cities risks destabilizing urban traffic systems, increasing externalities, such as $CO_2$ emissions, and introducing non-stationarity as human drivers will adapt unpredictably to AV behaviors. In this position paper, we argue that city authorities must collaborate with the ML community to monitor and critically evaluate the routing algorithms proposed by car companies toward fair and system-efficient routing algorithms and regulatory standards.
title Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing
topic Multiagent Systems
Machine Learning
Robotics
url https://arxiv.org/abs/2502.13188