Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System

Yuhang Zhang; Zhiyao Zhang; Junyi Ji; Marcos Quiñones-Grueiro; William Barbour; Derek Gloudemans; Gergely Zachár; Clay Weston; Gautam Biswas; Daniel B. Work

arXiv · 2503.01017

Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System

Yuhang Zhang·Zhiyao Zhang·Junyi Ji·Marcos Quiñones-Grueiro·William Barbour·Derek Gloudemans·Gergely Zachár·Clay Weston·Gautam Biswas·Daniel B. Work

View original source ↗Read source document ↗Export metadata ↓

Abstract

This article presents the first field deployment of a multi-agent reinforcement learning (MARL) based variable speed limit (VSL) control system on Interstate 24 (I-24) near Nashville, Tennessee. We design and demonstrate a full pipeline from training MARL agents in a traffic simulator to a field deployment on a 17-mile segment of I-24 encompassing 67 VSL controllers. The system was launched on March 8th, 2024, and has made approximately 35 million decisions on 28 million trips in six months of operation. We apply an invalid action masking mechanism and several safety guards to ensure real-world constraints. The MARL-based implementation operates up to 98% of the time, with the safety guards overriding the MARL decisions for the remaining time. We evaluate the performance of the MARL-based algorithm in comparison to a previously deployed non-RL VSL benchmark algorithm on I-24. Results show that the MARL-based VSL control system achieves a superior performance. The accuracy of correctly warning drivers about slowing traffic ahead is improved by 14% and the response delay to non-recurrent congestion is reduced by 75%. The preliminary data shows that the VSL control system has reduced the crash rate by 26% and the secondary crash rate by 50%. We open-sourced the deployed MARL-based VSL algorithm at https://github.com/Lab-Work/marl-vsl-controller.

Explore related subjects

eess.SY cs.SY

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Yuhang Zhang, Zhiyao Zhang, Junyi Ji, Marcos Quiñones-Grueiro, William Barbour, Derek Gloudemans, Gergely Zachár, Clay Weston, Gautam Biswas, Daniel B. Work. 2025-03-02. Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System. https://arxiv.org/abs/2503.01017

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Ensuring Stability of Non-Minimal Modes in Input-Output Data-Driven Representation

Many recent data-driven control approaches for linear time-invariant systems are based on output trajectory prediction using input-output data matrices. The system dynamics described by this predictor, which we refer to as the input-output data-driven representation, yields non-unique autoregressive with exogenous inputs (ARX) models having possibly unstable non-minimal modes. In this note, we show that the stability of these non-minimal modes is ensured by a certain choice of ARX model, which coincides with the minimum-norm least-squares predictor using the Moore-Penrose inverse of the data matrix. This stability guarantee holds regardless of the underlying system's stability. Moreover, the stability persists under sufficiently small noise in data when a suitably truncated Moore-Penrose inverse is used. Consequently, the ARX model need not be reduced to the true system order in order to avoid unstable additional modes.

eess.SY↗

arXiv2026

Optimization-Based Formation Flight on Libration Point Orbits

A model predictive control (MPC) framework is developed for station-keeping in spacecraft formation flight along libration point orbits. At each control period, the MPC policy solves a multi-vehicle optimal control problem (MVOCP) that tracks a reference trajectory, while enforcing path constraints on the relative motion of the formation. The control policy makes use of a limited set of control nodes consistent with operational constraints that allow only a small number of maneuver opportunities per revolution. To promote recursive feasibility, path constraints are progressively tightened across the prediction horizon. An isoperimetric reformulation of the constraints is used to prevent inter-sample violations. The resulting MVOCP is a nonconvex program, which is solved via sequential convex programming. The proposed approach is evaluated in a high-fidelity ephemeris model under uncertainties for a formation along the near-rectilinear halo orbit (NRHO), and subject to path constraints on inter-spacecraft separation and relative Sun phase angle. The results demonstrate maintenance of a spacecraft formation that satisfies the path constraints with realistic cumulative propellant consumption.

eess.SY↗

arXiv2026

Certificates Synthesis for A Class of Observational Properties in Stochastic Systems: A Unified Approach

In this paper, we investigate the probabilistic formal verification of stochastic dynamical systems over continuous state spaces. Motivated by problems in state estimation and information-flow security, we introduce the notion of observational properties, which characterize the inferences an external observer can draw from system outputs. These properties are formulated as probabilistic hyperproperties based on HyperLTL over finite traces, yielding a unified framework that subsumes several existing notions studied separately in the literature. We reduce the verification problem to reachability analysis over an augmented structure that integrates the system dynamics with an automaton representation of the specification. Building on this construction, we develop stochastic barrier certificates that provide probabilistic guarantees for property satisfaction while avoiding explicit state-space discretization. The effectiveness of the proposed framework is demonstrated through a case study.

eess.SY↗