检索结果-内蒙古大学图书馆

Reinforcement Learning for Robust Advisories Under Driving Compliance Errors

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Transportation systems 2025年

作者： Kim, Jeongyun Cho, Jung-Hoon Wu, Cathy Korea Advanced Institute of Science and Technology Department of Civil and Environmental Engineering Daejeon34141 Korea Republic of Massachusetts Institute of Technology Department of Civil and Environmental Engineering Laboratory for Information and Decision Systems CambridgeMA02139 United States Massachusetts Institute of Technology Laboratory for Information and Decision Systems Department of Civil and Environmental Engineering the Institute for Data Systems and Society CambridgeMA02139 United States

There has been considerable interest in recent years regarding how a small fraction of autonomous vehicles (AVs) can mitigate traffic congestion. However, the reality of vehicle-based congestion mitigation remains elusive, due to challenges of cost, technology maturity, and regulation. As a result, recent works have investigated the necessity of autonomy by exploring driving advisory systems. Such early works have made simplifying assumptions such as perfect driver compliance. This work relaxes this assumption, focusing on compliance errors caused by physical limitations of human drivers, in particular, response delay and speed deviation. These compliance errors introduce significant unpredictability into traffic systems, complicating the design of real-time driving advisories aimed at stabilizing traffic flow. Our analysis reveals that performance degradation increases sharply under compliance errors, highlighting the associated difficulties. To address this challenge, we develop a reinforcement learning (RL) framework based on an action-persistent Markov decision process (MDP) combined with domain randomization, designed for robust coarse-grained driving policies. This approach allows driving policies to effectively manage the cumulative impacts of compliance errors by generating various scenarios and corresponding traffic conditions during training. We show that in comparison to prior RL-based work which did not consider compliance errors, our policies achieve up to 2.2 times improvement in average speed over non-robust training. In addition, analytical results validate the experiment results, highlighting the benefits of the proposed framework. Overall, this paper advocates the necessity of incorporating human driver compliance errors in the development of RL-based advisory systems, achieving more effective and resilient traffic management solutions. © 2000-2011 IEEE.

关键词： Traffic congestion

User-Friendly Game-Theoretic Modeling and Analysis of Multi-Modal Transportation systems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zambrano, Margarita Li, Xinling Fiorista, Riccardo Zardini, Gioele Laboratory for Information and Decision Systems the Department of Civil and Environmental Engineering Massachusetts Institute of Technology United States

The evolution of existing transportation systems, mainly driven by urbanization and increased availability of mobility options, such as private, profit-maximizing ride-hailing companies, calls for tools to reason about their design and regulation. To study this complex socio-technical problem, one needs to account for the strategic interactions of the stakeholders involved in the mobility ecosystem. In this paper, we present a game-theoretic framework to model multi-modal mobility systems, focusing on municipalities, service providers, and travelers. Through a user-friendly, Graphical User Interface, one can visualize system dynamics and compute equilibria for various scenarios. The framework enables stakeholders to assess the impact of local decisions (e.g., fleet size for services or taxes for private companies) on the full mobility system. Furthermore, this project aims to foster STEM interest among high school students (e.g., in the context of prior activities in Switzerland, and planned activities with the MIT museum). This initiative combines theoretical advancements, practical applications, and educational outreach to improve mobility system design. Copyright © 2025, The Authors. All rights reserved.

关键词： Urban transportation

Routing Guidance for Emerging Transportation systems with Improved Dynamic Trip Equity

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Bai, Ting Li, Anni Xu, Gehui Cassandras, Christos G. Malikopoulos, Andreas A. Information and Decision Science Lab School of Civil & Environmental Engineering Cornell University IthacaNY United States Division of Systems Engineering Center for Information and Systems Engineering Boston University BrooklineMA United States Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom

In this letter, we present a dynamic routing guidance system that optimizes route recommendations for individual vehicles within an emerging transportation system while enhancing travelers’ trip equity. We develop a framework to quantify trip quality and equity in a dynamic travel environment, providing new insights into how routing guidance influences equity in road transportation. Our approach enables real-time routing by incorporating both monitored and anticipated traffic congestion. We provide conditions that ensure achieving perfect trip equity for all travelers in a free-flow network. Finally, simulation studies on 1,000 vehicles traversing an urban road network in Boston demonstrate that our proposed method improves trip equity by approximately 13.3% compared to the shortest-route strategy. In addition, the results reveal that our approach redistributes travel costs across vehicle types through route optimization, contributing to a more equitable transportation system. Copyright © 2025, The Authors. All rights reserved.

关键词： Traffic congestion

Strategic Pricing and Routing to Maximize Profit in Congested Roads Considering Interactions With Travelers

学校读者我要写书评

暂无评论

IEEE Transactions on Control of Network systems 2025年

作者： Kim, Youngseo Duan, Ning Zardini, Gioele Samaranayake, Samitha Wischik, Damon Cornell University Civil and Environmental Engineering IthacaNY United States Cornell University Operations Research and Information Engineering IthacaNY United States Massachusetts Institute of Technology Laboratory for Information and Decision Systems CambridgeMA United States University of Cambridge Department of Computer Science and Technology Cambridge United Kingdom

We introduce an innovative approach for analyzing strategic interactions in transportation networks featuring Mobility-on-Demand (MoD) services. This study focuses on achieving company-traveler equilibria, whereby a single company optimizes pricing and routing decisions to maximize profitability while considering travelers' mode choices, modeled via a multinomial logit model (MNL). Although profit maximization problems have been extensively studied in the field of revenue management across various domains, their application to transportation networks poses unique challenges, such as the influence of network topology and additional constraints (e.g., flow conservation, rebalancing, etc.). To address the inherent non-linear relationship arising from endogenous travel demand, we shift our domain space from price to market share. Subsequently, we derive prices using a direct one-toone correspondence within the MNL. This work is the first effort in leveraging such novel techniques in the context of transportation network analysis. Remarkably, the proposed reformulation results in an equivalent problem exhibiting convexity, offering computational efficiency and interpretability. By solving the Karush-Kuhn-Tucker (KKT) conditions, we characterize user equilibrium with the generalized route cost, which incorporates the operating cost by rebalancing and travelers' disutility caused by congestion. Our approach is empirically validated through a numerical analysis conducted on the widely recognized Sioux Falls network. The results underscore the effectiveness and practical applicability of our method in analyzing transportation networks featuring MoD services, and open the stage for important future investigations. © 2014 IEEE.

关键词： Profitability

Safe Street for Kids: Evaluating Traffic Hazard Through a Multi-Criteria decision-Aiding Approach

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Abdollahi, Shabnam Waygood, E.D. Owen Cloutier, Marie Soleil Abi-Zeid, Irene Department of Civil Geological and Mining Engineering Polytechnique Montréal Canada Institut National de la Recherche Scientifique Centre Urbanisation Culture Société Montréal Canada Department of Operations and Decision Systems Université Laval Québec Canada

Background: Traffic related accidents kill over a million people each year. They put people’s lives at risk and limit the freedom to travel of many. Previous research has focused on where collisions happen, but no tool exists to consistently measures the hazard that traffic ***: To develop a comprehensive tool to measure traffic hazard of all ***: A multi-criteria decision aiding (MCDA) method called MACBETH was applied. Focus groups with children, parents, and experts helped construct the criteria. Experts representing academia and professional practice from engineering, urbanism, and public health worked together to build the MCDA model to evaluate street hazard. For each criterion, streets performance levels were developed and their relationship to traffic hazard determined. A scenario technique was used to determine the relative weights between criteria through consensus. The resulting hazard score was computed and then visualized through a GIS program, OTHELLO. The accuracy of the tool was validated with ***: Six criteria were constructed and their relative influences on traffic hazard estimated. The traffic hazard score for 25,000 streets in the City of Montreal, Canada were estimated. The tool’s accuracy was found to be over >90 % when validated with ***: Many factors influence the hazard created by vehicular traffic directly or in combination. An MCDA approach allowed for in-depth consideration of each criterion and for a tool to be developed that consistently estimates traffic hazard for city streets in Montreal. This information can help inform planning to address the hazard imposed on residents. © 2025, The Authors. All rights reserved.

关键词：

Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms: Challenges and a Roadmap

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xu, Jianye Alrifaee, Bassam Betz, Johannes Mokhtarian, Armin Mittal, Archak Cai, Mengchi Mangharam, Rahul Shehata, Omar M. Elias, Catherine M. Zaech, Jan-Nico Scheffe, Patrick Jahncke, Felix Ulhas, Sangeet Sankaramangalam Arfvidsson, Kaj Munhoz Department of Computer Science RWTH Aachen University Germany Department of Aerospace Engineering University of the Bundeswehr Munich Germany Professorship of Autonomous Vehicle Systems Technical University of Munich Germany Department of Civil Engineering Indian Institute of Technology Bombay India School of Vehicle and Mobility Tsinghua University China Department of Electrical and Systems Engineering University of Pennsylvania United States Mechatronics Engineering Department Faculty of Engineering and Materials Science The German University in Cairo Egypt Department of Computer Science Engineering The German University in Cairo Egypt INSAIT Sofia University "St. Kliment Ohridski" Bulgaria School for Engineering of Matter Transport and Energy Arizona State University United States Division of Decision and Control Systems KTH Royal Institute of Technology Sweden

This article proposes a roadmap to address the current challenges in small-scale testbeds for Connected and Automated Vehicles (CAVs) and robot swarms. The roadmap is a joint effort of participants in the workshop "1st Workshop on Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms," held on June 2 at the IEEE Intelligent Vehicles Symposium (IV) 2024 in Jeju, South Korea. The roadmap contains three parts: 1) enhancing accessibility and diversity, especially for underrepresented communities, 2) sharing best practices for the development and maintenance of testbeds, and 3) connecting testbeds through an abstraction layer to support collaboration. The workshop features eight invited speakers, four contributed papers [1]–[4], and a presentation of a survey paper on testbeds [5]. The survey paper provides an online comparative table of more than 25 testbeds, available at https://***/testbeds-survey. The workshop’s own website is available at https://***/iv24-workshop. Copyright © 2025, The Authors. All rights reserved.

关键词： Testbeds

FURTHER RESULTS ON ITERATIVE APPROACHES TO THE DETERMINATION OF THE RESPONSE OF NONCLASSICALLY DAMPED systems

学校读者我要写书评

暂无评论

JOURNAL OF APPLIED MECHANICS-TRANSACTIONS OF THE ASME 1993年第1期60卷 235-239页

作者： UDWADIA, FE Civil Engineering and Decision Systems University of Southern California Los Angeles CA 90089-1453

Iterative schemes for obtaining the response of nonclassically damped dynamic systems have been shown to converge when the damping matrix possesses certain specific characteristics. This paper extends those previous results which pertain to symmetric, positive-definite damping matrices. The paper considers a more general decomposition of the damping matrix, and extends the applicability of these iterative methods to all positive definite, symmetric damping matrices. This decomposition is governed by a parameter alpha. Conditions on alpha under which convergence is guaranteed are provided. Estimates of alpha which yield the fastest asymptotic convergence as well as estimates of the value of this asymptotic rate of convergence are also provided.

关键词： Iterative methods Damping Dynamic systems

A Cooperative Compliance Control Framework for Socially Optimal Mixed Traffic Routing

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Anni Bai, Ting Chen, Yingqing Cassandras, Christos G. Malikopoulos, Andreas A. Division of Systems Engineering Center for Information and Systems Engineering Boston University BrooklineMA02446 United States Information and Decision Science Lab School of Civil & Environmental Engineering Cornell University IthacaNY United States

In mixed traffic environments, where Connected and Autonomed Vehicles (CAVs) coexist with potentially non-cooperative Human-Driven Vehicles (HDVs), the self-centered behavior of human drivers may compromise the efficiency, optimality, and safety of the overall traffic network. In this paper, we propose a Cooperative Compliance Control (CCC) framework for mixed traffic routing, where a Social Planner (SP) optimizes vehicle routes for system-wide optimality while a compliance controller incentivizes human drivers to align their behavior with route guidance from the SP through a "refundable toll" scheme. A key challenge arises from the heterogeneous and unknown response models of different human driver types to these tolls, making it difficult to design a proper controller and achieve desired compliance probabilities over the traffic network. To address this challenge, we employ Control Lyapunov Functions (CLFs) to adaptively correct (learn) crucial components of our compliance probability model online, construct data-driven feedback controllers, and demonstrate that we can achieve the desired compliance probability for HDVs, thereby contributing to the social optimality of the traffic network. Copyright © 2025, The Authors. All rights reserved.

关键词： Transportation routes

Cost-effective planning of decarbonized power-gas infrastructure to meet the challenges of heating electrification

学校读者我要写书评

暂无评论

Cell Reports Sustainability 2025年第2期2卷

作者： Khorramfar, Rahman Santoni-Colvin, Morgan Amin, Saurabh Norford, Leslie K. Botterud, Audun Mallapragada, Dharik MIT Energy Initiative (MITEI) Massachusetts Institute of Technology Cambridge 02139 MA United States Laboratory for Information & Decision Systems (LIDS) Massachusetts Institute of Technology Cambridge 02139 MA United States Civil and Environmental Engineering (CEE) Massachusetts Institute of Technology Cambridge 02139 MA United States Department of Architecture Massachusetts Institute of Technology Cambridge 02139 MA United States Department of Chemical and Biomolecular Engineering Tandon School of Engineering New York University Brooklyn 11201 NY United States

Building heat electrification is central to economy-wide decarbonization efforts and directly affects energy infrastructure planning through increasing electricity and reducing gas demand. Here, we develop a modeling framework to quantify end-use demand for electricity and gas in the buildings sector across various electrification pathways and to evaluate their impact on co-optimized bulk power-gas infrastructure investments and operations under deep decarbonization scenarios. Applying the framework to the US New England region in 2050 across 20 weather scenarios, we find that high electrification of the residential sector can increase sectoral peak and total electricity demands by up to 56%–158% and 41%–59%, respectively, relative to business-as-usual projections. Employing demand-side measures, such as building envelope improvements under high electrification, can reduce the combined residential sector power-gas demand by 28%–30% and yield 21%–29% lower bulk power-gas system cost outcomes. Similarly, we find that demand flexibility programs can reduce the total system cost by up to 6.3%. © 2025 The Authors

关键词： decarbonization heating electrification inter-annual weather variation joint power-gas planning