Mitigating Bus Bunching via Bus Substitution in Modular Vehicle Systems

Bus bunching, where buses arrive at stops in quick succession rather than at evenly spaced intervals, disrupts public transit systems by increasing passenger waiting times and decreasing system reliability. To address this issue, we propose a novel strategy featuring automated modular bus units that can either operate individually or be combined en route to form a larger bus. Our strategy systematically combines this new modular technology with bus bunching mitigation techniques, including stop skipping and bus substitution, to minimize passenger waiting times and operational costs. Our strategy is formulated as a Markov Decision Process and solved by an Advantage Actor-Critic algorithm. Our approach is validated through numerical experiments using real-world data, demonstrating significant improvements in system reliability and passenger satisfaction in various traffic conditions.

Authors

Institutions

Publication Details

Published
2025-06-24
DOI
https://doi.org/10.23919/ecc65951.2025.11187237
Primary Topic
Real-Time Systems Scheduling
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Mitigating Bus Bunching via Bus Substitution in Modular Vehicle Systems

Andy Dai, Kaidi Yang
Real-Time Systems Scheduling
article

Mitigating Bus Bunching via Bus Substitution in Modular Vehicle Systems

Andy Dai, Kaidi Yang
article en

Abstract

Bus bunching, where buses arrive at stops in quick succession rather than at evenly spaced intervals, disrupts public transit systems by increasing passenger waiting times and decreasing system reliability. To address this issue, we propose a novel strategy featuring automated modular bus units that can either operate individually or be combined en route to form a larger bus. Our strategy systematically combines this new modular technology with bus bunching mitigation techniques, including stop skipping and bus substitution, to minimize passenger waiting times and operational costs. Our strategy is formulated as a Markov Decision Process and solved by an Advantage Actor-Critic algorithm. Our approach is validated through numerical experiments using real-world data, demonstrating significant improvements in system reliability and passenger satisfaction in various traffic conditions.

National University of Singapore (SG)
Openalex Percentile: Top 68%
Real-Time Systems Scheduling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.