Scalable Multiagent Driving Policies For Reducing Traffic Congestion

  title={Scalable Multiagent Driving Policies For Reducing Traffic Congestion},
  author={Jiaxu Cui and William Macke and Harel Yedidsion and Aastha Goyal and Daniel Urielli and Peter Stone},
Traffic congestion is a major challenge in modern urban settings. The industry-wide development of autonomous and automated vehicles (AVs) motivates the question of how can AVs contribute to congestion reduction. Past research has shown that in small scale mixed traffic scenarios with both AVs and human-driven vehicles, a small fraction of AVs executing a controlled multiagent driving policy can mitigate congestion. In this paper, we scale up existing approaches and develop new multiagent… 

Figures and Tables from this paper

Learning Generalizable Multi-Lane Mixed-Autonomy Behaviors in Single Lane Representations of Traffic
This paper designs a curriculum learning paradigm that exploits the natural extendability of the network to effectively learn behaviors that reduce congestion over long horizons and suggests that introducing lane change behaviors that even approximately match trends in more complex systems can significantly improve the generalizability of subsequent learned models.
Learning a Robust Multiagent Driving Policy for Traffic Congestion Reduction
A learned multiagent driving policy that is robust to a variety of open-network traffic conditions, including vehicle flows, the fraction of AVs in traffic, AV placement, and different merging road geometries is presented.


Multiagent traffic management: a reservation-based intersection control mechanism
  • K. Dresner, P. Stone
  • Computer Science
    Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004.
  • 2004
This paper proposes a reservation-based system for alleviating traffic congestion, specifically at intersections, and under the assumption that the cars are controlled by agents, and specifies a precise metric for evaluating the quality of traffic control at an intersection.
Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control
This work uses Flow to develop reliable controllers for complex problems, such as controlling mixed-autonomy traffic (involving both autonomous and human-driven vehicles) in a ring road, and shows that even simple neural network policies can solve the stabilization task across density settings and generalize to out-of-distribution settings.
Simulation to scaled city: zero-shot policy transfer for traffic control via autonomous vehicles
Using deep reinforcement learning, a set of two autonomous vehicles are successfully trained to lead a fleet of vehicles onto a round-about and then this policy is transferred from simulation to a scaled city without fine-tuning and leads to a 5% reduction of average travel time and a reduction of maximum travel time in the UDSSC.
Large-scale traffic control using autonomous vehicles and decentralized deep reinforcement learning
A scalable, decentralized deep reinforcement learning (RL) scheme for optimizing vehicle traffic consisting of both autonomous and human-driven vehicles and can be applied in conjunction with systems in which neighboring controllers are not RL-based.
Flow: Deep Reinforcement Learning for Control in SUMO
A contribution of this work is a variety of practical techniques for overcoming challenges with SUMO, including parallelizing policy rollouts, smart exception and collision handling, and leveraging subscriptions to reduce computational overhead.
Benchmarks for reinforcement learning in mixed-autonomy traffic
We release new benchmarks in the use of deep reinforcement learning (RL) to create controllers for mixed-autonomy traffic, where connected and autonomous vehicles (CAVs) interact with human drivers
AIM: autonomous intersection management
A future in which vehicles themselves handle the vast majority of the driving task is predicted, once autonomous vehicles become popular, autonomous interactions amongst multiple vehicles will be possible and current methods of vehicle coordination will be outdated.
Stabilizing Traffic with Autonomous Vehicles
This article introduces two conditions which simultaneously stabilize traffic while imposing a safety constraint on the autonomous vehicle and limiting degradation of performance, and formalizes the problem in terms of linear string stability, derive optimality conditions from frequency-domain analysis, and pose the resulting nonlinear optimization problem.
The Intelligent Driver Model with Stochasticity -New Insights Into Traffic Flow Oscillations
Abstract: Traffic flow oscillations, including traffic waves, are a common yet incompletely understood feature of congested traffic. Possible mechanisms include traffic flow instabilities,
Dissipation of stop-and-go waves via control of autonomous vehicles: Field experiments
It is demonstrated experimentally that intelligent control of an autonomous vehicle is able to dampen stop-and-go waves that can arise even in the absence of geometric or lane changing triggers, suggesting a paradigm shift in traffic management.