Imperial College London

Panagiotis Angeloudis

Faculty of EngineeringDepartment of Civil and Environmental Engineering

Reader in Transport Systems and Logistics
 
 
 
//

Contact

 

+44 (0)20 7594 5986p.angeloudis Website

 
 
//

Location

 

337Skempton BuildingSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

107 results found

Hu S, Ye Y, Hu Q, Liu X, Cao S, Yang HH, Shen Y, Angeloudis P, Parada L, Wu Cet al., 2023, A Federated Learning-Based Framework for Ride-Sourcing Traffic Demand Prediction, IEEE Transactions on Vehicular Technology, Vol: 72, Pages: 14002-14015, ISSN: 0018-9545

Accurate short-Term ride-sourcing demand prediction is vital for transportation operations, planning, and policy-making. With the models developed from data based on individual ride-sourcing companies to the joint models with data from multiple ride-sourcing companies, the prediction performance of the proposed models is enhanced significantly. However, the privacy issues of these models become a problem. Raw data collected from individual companies could cause business concerns and data privacy issues. In this article, we propose a Federated Learning (FL) based framework for traffic demand prediction (FedTDP), to solve this problem without sacrificing the prediction performance. In our framework, the model can encapsulate the spatial and temporal correlation of traffic demand data via LSTM and GCN respectively. Moreover, by associating FL with the spatio-Temporal model, no raw data is uploaded to the centralized server, and only model parameters are required. Furthermore, a Shapley value-based reward mechanism is proposed to evaluate the contribution of ride-sourcing companies and can be used as a means to distribute rewards accordingly. Finally, a real-world case study of Hangzhou City, China, is conducted. More than 16 million real-world ride-sourcing requests collected from 8 ride-sourcing companies are used, covering most of the ride-sourcing travel demand across the city. The case study shows that the FL-based spatio-Temporal model outperforms several well-established prediction models while preserving data privacy. It demonstrates the effectiveness and potential of our proposed framework. Some discussions related to the real-world implementations of the Shapley value-based reward mechanism are also given in the article.

Journal article

Cheong H-I, Macias JJE, Karamanis R, Stettler M, Majumdar A, Angeloudis Pet al., 2023, Policy and strategy evaluation of ridesharing autonomous vehicle operation: a london case study, Transportation Research Record: Journal of the Transportation Research Board, Vol: 2677, Pages: 22-52, ISSN: 0361-1981

To understand the dynamics of an autonomous ridesharing transport mode from the perspectives of different stakeholders, a single model of such a system is essential, because this will enable policymakers and companies involved in the manufacture and operation of shared autonomous vehicles (SAVs) to develop user-centered strategies. The model needs to be based on real data, network, and traffic information and applied to real cities and situations, particularly those with complex public transportation systems. In this paper, we propose a new agent-based model for SAV deployment that enables the parametric assessment of key performance indicators from the perspective of potential SAV users, vehicle manufacturers, operators, and local authorities. This has been applied to a case study of three regions in London: central, inner, and outer. The results show there is no linear correlation between an increased ridesharing acceptance level and average trip duration. Without a fleet rebalancing algorithm, over 80% of SAVs’ energy expenditure is on picking up customers. By reducing pickup distance, SAVs could be a contender for a nonpersonal transportation system based on trip energy comparisons. The results provide a picture of future SAV systems for potential users and offer suggestions as to how operators can devise an optimal transportation strategy beyond the question of fleet size and how policymakers can improve the overall transport network and reduce its environmental impact based on energy consumption. As a result of its flexibility and parametric capability, the model can be utilized to inform any local authority how SAV services could be deployed in any city.

Journal article

Parada L, Candela E, Marques L, Angeloudis Pet al., 2023, Safe and efficient manoeuvring for emergency vehicles in autonomous traffic using multi-agent proximal policy optimisation, TRANSPORTMETRICA A-TRANSPORT SCIENCE, ISSN: 2324-9935

Journal article

Xia Y, Geng M, Chen Y, Sun S, Liao C, Zhu Z, Li Z, Ochieng WY, Angeloudis P, Elhajj M, Zhang L, Zeng Z, Zhang B, Gao Z, Chen XMet al., 2023, Understanding common human driving semantics for autonomous vehicles, PATTERNS, Vol: 4, ISSN: 2666-3899

Journal article

Xia Y, Liao C, Chen XM, Zhu Z, Chen X, Wang L, Jiang R, Stettler MEJ, Angeloudis P, Gao Zet al., 2023, Future reductions of China's transport emissions impacted by changing driving behaviour, NATURE SUSTAINABILITY, ISSN: 2398-9629

Journal article

Candela E, Doustaly O, Parada L, Feng F, Demiris Y, Angeloudis Pet al., 2023, Risk-aware controller for autonomous vehicles using model-based collision prediction and reinforcement learning, ARTIFICIAL INTELLIGENCE, Vol: 320, ISSN: 0004-3702

Journal article

Zhang X, Angeloudis P, Demiris Y, 2023, Dual-branch Spatio-Temporal Graph Neural Networks for Pedestrian Trajectory Prediction, Pattern Recognition, ISSN: 0031-3203

Journal article

Ye Q, Feng Y, Macias JJE, Stettler M, Angeloudis Pet al., 2023, Adaptive road configurations for improved autonomous vehicle-pedestrian interactions using reinforcement learning, IEEE Transactions on Intelligent Transportation Systems, Vol: 24, Pages: 2024-2034, ISSN: 1524-9050

The deployment of Autonomous Vehicles (AVs) poses considerable challenges and unique opportunities for the design and management of future urban road infrastructure. In light of this disruptive transformation, the Right-Of-Way (ROW) composition of road space has the potential to be renewed. Design approaches and intelligent control models have been proposed to address this problem, but we lack an operational framework that can dynamically generate ROW plans for AVs and pedestrians in response to real-time demand. Based on microscopic traffic simulation, this study explores Reinforcement Learning (RL) methods for evolving ROW compositions. We implement a centralised paradigm and a distributive learning paradigm to separately perform the dynamic control on several road network configurations. Experimental results indicate that the algorithms have the potential to improve traffic flow efficiency and allocate more space for pedestrians. Furthermore, the distributive learning algorithm outperforms its centralised counterpart regarding computational cost (49.55%), benchmark rewards (25.35%), best cumulative rewards (24.58%), optimal actions (13.49%) and rate of convergence. This novel road management technique could potentially contribute to the flow-adaptive and active mobility-friendly streets in the AVs era.

Journal article

Chow AHF, Kuo Y-H, Angeloudis P, Bell MGHet al., 2022, Dynamic modelling and optimisation of transportation systems in the connected era, TRANSPORTMETRICA B-TRANSPORT DYNAMICS, Vol: 10, Pages: 801-802, ISSN: 2168-0566

Journal article

Zhang X, Angeloudis P, Demiris Y, 2022, ST CrossingPose: a spatial-temporal graph convolutional network for skeleton-based pedestrian crossing intention prediction, IEEE Transactions on Intelligent Transportation Systems, Vol: 23, Pages: 20773-20782, ISSN: 1524-9050

Pedestrian crossing intention prediction is crucial for the safety of pedestrians in the context of both autonomous and conventional vehicles and has attracted widespread interest recently. Various methods have been proposed to perform pedestrian crossing intention prediction, among which the skeleton-based methods have been very popular in recent years. However, most existing studies utilize manually designed features to handle skeleton data, limiting the performance of these methods. To solve this issue, we propose to predict pedestrian crossing intention based on spatial-temporal graph convolutional networks using skeleton data (ST CrossingPose). The proposed method can learn both spatial and temporal patterns from skeleton data, thus having a good feature representation ability. Extensive experiments on a public dataset demonstrate that the proposed method achieves very competitive performance in predicting crossing intention while maintaining a fast inference speed. We also analyze the effect of several factors, e.g., size of pedestrians, time to event, and occlusion, on the proposed method.

Journal article

Ngu E, Parada L, Macias JJE, Angeloudis Pet al., 2022, Decentralised Multi-Agent Reinforcement Learning Approach for the Same-Day Delivery Problem, Transportation Research Record, Pages: 385-395

Same-day delivery (SDD) services have become increasingly popular in recent years. These have been usually modeled by previous studies as a certain class of dynamic vehicle routing problem (DVRP) where goods must be delivered from a depot to a set of customers in the same day that the orders were placed. Adaptive exact solution methods for DVRPs can become intractable even for small problem instances. In this paper, the same-day delivery problem (SDDP) is formulated as a Markov decision process (MDP) and it is solved using a parameter-sharing Deep Q-Network, which corresponds to a decentralised multi-agent reinforcement learning (MARL) approach. For this, a multi-agent grid-based SDD environment is created, consisting of multiple vehicles, a central depot, and dynamic order generation. In addition, zone-specific order generation and reward probabilities are introduced. The performance of the proposed MARL approach is compared against a mixed-integer programming (MIP) solution. Results show that the proposed MARL framework performs on par with MIP-based policy when the number of orders is relatively low. For problem instances with higher order arrival rates, computational results show that the MARL approach underperforms MIP by up to 30%. The performance gap between both methods becomes smaller when zone-specific parameters are employed. The gap is reduced from 30% to 3% for a 5 3 5 grid scenario with 30 orders. Execution time results indicate that the MARL approach is, on average, 65 times faster than the MIP-based policy, and therefore may be more advantageous for real-time control, at least for small-sized instances.

Book chapter

Ngu E, Parada L, Macias JJE, Angeloudis Pet al., 2022, Decentralised Multi-Agent Reinforcement Learning Approach for the Same-Day Delivery Problem, TRANSPORTATION RESEARCH RECORD, Vol: 2676, Pages: 385-395, ISSN: 0361-1981

Journal article

Ye Q, Feng Y, Qiu J, Stettler M, Angeloudis Pet al., 2022, Approximate optimum curbside utilisation for pick-up and drop-off (PUDO) and parking demands using reinforcement learning, 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), Publisher: IEEE, Pages: 2628-2633

With the uptake of automated transport, especially Pick-Up and Drop-Off (PUDO) operations of Shared Autonomous Vehicles (SAVs), the valet parking of passenger vehicles and delivery vans are envisaged to saturate our future streets. These emerging behaviours would join conventional on-street parking activities in an intensive competition for scarce curb resources. Existing curbside management approaches principally focus on those long-term parking demands, neglecting those short-term PUDO or docking events. Feasible solutions that coordinate diverse parking requests given limited curb space are still absent. We propose a Reinforcement Learning (RL) method to dynamically dispatch parking areas to accommodate a hybrid stream of parking behaviours. A partially-learning Deep Deterministic Policy Gradient (DDPG) algorithm is trained to approximate optimum dispatching strategies. Modelling results reveal satisfying convergence guarantees and robust learning patterns. Namely, the proposed model successfully discriminates parking demands of distinctive sorts and prioritises PUDOs and docking requests. Results also identify that when the demand-supply ratio situates at 2:1 to 4:1, the service rate approximates an optimal (83\%), and curbside occupancy surges to 80%. This work provides a novel intelligent dispatching model for diverse and fine-grained parking demands. Furthermore, it sheds light on deploying distinctive administrative strategies to the curbside in different contexts.

Conference paper

Zhang X, Feng Y, Angeloudis P, Demiris Yet al., 2022, Monocular visual traffic surveillance: a review, IEEE Transactions on Intelligent Transportation Systems, Vol: 23, Pages: 14148-14165, ISSN: 1524-9050

To facilitate the monitoring and management of modern transportation systems, monocular visual traffic surveillance systems have been widely adopted for speed measurement, accident detection, and accident prediction. Thanks to the recent innovations in computer vision and deep learning research, the performance of visual traffic surveillance systems has been significantly improved. However, despite this success, there is a lack of survey papers that systematically review these new methods. Therefore, we conduct a systematic review of relevant studies to fill this gap and provide guidance to future studies. This paper is structured along the visual information processing pipeline that includes object detection, object tracking, and camera calibration. Moreover, we also include important applications of visual traffic surveillance systems, such as speed measurement, behavior learning, accident detection and prediction. Finally, future research directions of visual traffic surveillance systems are outlined.

Journal article

Zhang K, Macias JJE, Paccagnan D, Angeloudis Pet al., 2022, The Competition and Inefficiency in Urban Road Last-Mile Delivery, Pages: 1473-1481, ISSN: 1548-8403

The last-mile delivery market is highly competitive and is saturated with numerous small operators. In this context, the fierce competition between operators, joint with the rapid increase in the demand for home-delivery, resulted in a significant increase in urban freight traffic further worsening congestion and pollution. To tackle these issues, previous research has studied the implementation of collaborative last-mile operations, with organisations sharing resources in the form of inventory space or transportation capacity. However, a common limitation of the proposed models is ignoring time windows and the effects of externalities such as network congestion. In this work, we propose a framework to quantify the efficiency loss in urban last-mile delivery system by comparing the solutions of a fully-decentralised and fully-centralised last-mile delivery problem. In doing so, we develop a Multi-depot Vehicle Routing Problem with Time Windows and Congestible Network that is solved using a bespoke Parallel Hybrid Genetic Algorithm that accounts for the non-linearities arising from modelling endogenous network congestion. The model is evaluated on a case study based on central London to assess the efficiency gaps of realistic last-mile delivery operations. When time window constraints are not included, our results show that the efficiency loss fluctuates the most with a small number of customers, while it stabilises to less than 15% for instances with over 100 customers. However, time windows could significantly exacerbate this issue, resulting in an additional 25% of efficiency loss.

Conference paper

Ye Q, Feng Y, Candela E, Escribano Macias J, Stettler M, Angeloudis Pet al., 2022, Spatial-temporal flows-adaptive street layout control using reinforcement learning, Sustainability, Vol: 14, ISSN: 2071-1050

Complete streets scheme makes seminal contributions to securing the basic public right-of-way (ROW), improving road safety, and maintaining high traffic efficiency for all modes of commute. However, such a popular street design paradigm also faces endogenous pressures like the appeal to a more balanced ROW for non-vehicular users. In addition, the deployment of Autonomous Vehicle (AV) mobility is likely to challenge the conventional use of the street space as well as this scheme. Previous studies have invented automated control techniques for specific road management issues, such as traffic light control and lane management. Whereas models and algorithms that dynamically calibrate the ROW of road space corresponding to travel demands and place-making requirements still represent a research gap. This study proposes a novel optimal control method that decides the ROW of road space assigned to driveways and sidewalks in real-time. To solve this optimal control task, a reinforcement learning method is introduced that employs a microscopic traffic simulator, namely SUMO, as its environment. The model was trained for 150 episodes using a four-legged intersection and joint AVs-pedestrian travel demands of a day. Results evidenced the effectiveness of the model in both symmetric and asymmetric road settings. After being trained by 150 episodes, our proposed model significantly increased its comprehensive reward of both pedestrians and vehicular traffic efficiency and sidewalk ratio by 10.39%. Decisions on the balanced ROW are optimised as 90.16% of the edges decrease the driveways supply and raise sidewalk shares by approximately 9%. Moreover, during 18.22% of the tested time slots, a lane-width equivalent space is shifted from driveways to sidewalks, minimising the travel costs for both an AV fleet and pedestrians. Our study primarily contributes to the modelling architecture and algorithms concerning centralised and real-time ROW management. Prospective applications out o

Journal article

Shipman A, Mead D, Feng Y, Escribano J, Angeloudis P, Demiris Yet al., 2022, Novel trajectory prediction algorithm using a full dataset: comparison and ablation studies, IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), Publisher: IEEE, Pages: 2401-2406, ISSN: 2153-0009

Conference paper

Candela E, Parada L, Marques L, Georgescu T-A, Demiris Y, Angeloudis Pet al., 2022, Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 8814-8820, ISSN: 2153-0858

Conference paper

Escribano J, Chang H, Angeloudis P, 2022, Integrated Path Planning and Task Assignment Model for On-Demand Last-Mile UAV-Based Delivery, Editors: DeArmas, Ramalhinho, Voss, Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 198-213, ISBN: 978-3-031-16578-8

Book chapter

Ye Q, Feng Y, Han J, Stettler M, Angeloudis Pet al., 2021, A reinforcement learning-based adaptive control model for future street planning an algorithm and a case study, Doha, Qatar, 57th ISOCARP World Planning Congress, Publisher: ISOCARP, Pages: 1-13

With the emerging technologies in Intelligent Transportation System (ITS), the adaptive operation of road space is likely to be realised within decades. An intelligent street can learn and improve its decision-making on the right-of-way (ROW) for road users, liberating more active pedestrian space while maintaining traffic safety and efficiency. However, there is a lack of effective controlling techniques for these adaptive street infrastructures. To fill this gap in existing studies, we formulate this control problem as a Markov Game and develop a solution based on the multi-agent Deep Deterministic Policy Gradient (MADDPG) algorithm. The proposed model can dynamically assign ROW for sidewalks, autonomous vehicles (AVs) driving lanes and on-street parking areas in real-time. Integrated with the SUMO traffic simulator, this model was evaluated using the road network of the South Kensington District against three cases of divergent traffic conditions: pedestrian flow rates, AVs traffic flow rates and parking demands. Results reveal that our model can achieve an average reduction of 3.87% and 6.26% in street space assigned for on-street parking and vehicular operations. Combined with space gained by limiting the number of driving lanes, the average proportion of sidewalks to total widths of streets can significantly increase by 10.13%.

Conference paper

Mijic A, Whyte J, Myers R, Angeloudis P, Cardin M-A, Stettler M, Ochieng Wet al., 2021, Reply to a discussion of 'a research agenda on systems approaches to infrastructure' by david elms, Civil Engineering and Environmental Systems: decision making and problem solving, Vol: 38, Pages: 295-297, ISSN: 0263-0257

Journal article

Liu Q, Hu S, Angeloudis P, Wang Y, Zhang L, Yang Q, Li Yet al., 2021, Dynamic wireless power transfer system for electric-powered connected and autonomous vehicle on urban road network, IET INTELLIGENT TRANSPORT SYSTEMS, Vol: 15, Pages: 1153-1166, ISSN: 1751-956X

Journal article

Mijic A, Whyte J, Fisk D, Angeloudis P, Ochieng W, Cardin M-A, Mosca L, Simpson C, McCann J, Stoianov I, Myers R, Stettler Met al., 2021, The Centre for Systems Engineering and Innovation – 2030 vision and 10-year celebration

The 2030 vision of the Centre is to bring Systems Engineering and Innovation to Civil Infrastructure by changing how cross-sector infrastructure challenges are addressedin an integrated way using principles of systems engineering to maximise resilience, safety and sustainability in an increasingly complex world.We want to better understand the environmental and societal impacts of infrastructure interventions under uncertainty. This requires a change in current approaches to infrastructure systems engineering: starting from the natural environmentand its resources, encompassing societaluse of infrastructure and the supporting infrastructure assets and services.We argue for modelling that brings natural as well as built environments within the system boundaries to better understand infrastructure and to better assess sustainability. We seethe work as relevant to both the academic community and to a wide range of industry and policy applications that are working on infrastructure transition pathways towards fair, safe and sustainable society.This vision was developed through discussions between academics in preparation for the Centre for Systems Engineering and Innovation (CSEI) 10 years celebration. These rich discussions about the future of the Centre were inspired by developing themes for a celebration event, through which we have summarised the first 10 years of the Centre’s work and our vision for the future and identified six emerging research areas.

Report

Anastasiadis E, Angeloudis P, Ainalis D, Ye Q, Hsu P-Y, Karamanis R, Escribano Macias J, Stettler Met al., 2021, On the selection of charging facility locations for EV-based ride-hailing services: a computational case study, Sustainability, Vol: 13, ISSN: 2071-1050

The uptake of Electric Vehicles (EVs) is rapidly changing the landscape of urban mobility services. Transportation Network Companies (TNCs) have been following this trend by increasing the number of EVs in their fleets. Recently, major TNCs have explored the prospect of establishing privately owned charging facilities that will enable faster and more economic charging. Given the scale and complexity of TNC operations, such decisions need to consider both the requirements of TNCs and local planning regulations. Therefore, an optimisation approach is presented to model the placement of CSs with the objective of minimising the empty time travelled to the nearest CS for recharging as well as the installation cost. An agent based simulation model has been set in the area of Chicago to derive the recharging spots of the TNC vehicles, and in turn derive the charging demand. A mathematical formulation for the resulting optimisation problem is provided alongside a genetic algorithm that can produce solutions for large problem instances. Our results refer to a representative set of the total data for Chicago and indicate that nearly 180 CSs need to be installed to handle the demand of a TNC fleet of 3000 vehicles.

Journal article

Li J, Zhang K, Shen L, Wang Z, Guo F, Angeloudis P, Chen XM, Hu Set al., 2021, A Domain Adaptation Framework for Short-term Traffic Prediction, IEEE Intelligent Transportation Systems Conference (ITSC), Publisher: IEEE, Pages: 3564-3569, ISSN: 2153-0009

Conference paper

Candela E, Feng Y, Mead D, Demiris Y, Angeloudis Pet al., 2021, Fast Collision Prediction for Autonomous Vehicles using a Stochastic Dynamics Model, IEEE Intelligent Transportation Systems Conference (ITSC), Publisher: IEEE, Pages: 211-216, ISSN: 2153-0009

Conference paper

Ye Q, Stebbins SM, Feng Y, Candela E, Stettler M, Angeloudis Pet al., 2020, Intelligent management of on-street parking provision for the autonomous vehicles era, 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC), Publisher: IEEE, Pages: 1-7, ISSN: 2153-0009

The increasing degree of connectivity between vehicles and infrastructure, and the impending deployment of autonomous vehicles (AV) in urban streets, presents unique opportunities and challenges regarding the on-street parking provision for AVs. This study develops a novel simulation-optimisation approach for intelligent curbside management, based on a metaheuristic technique. The hybrid method balances curb lanes for driving or parking, aiming to minimise the average traffic delay. The model is tested using an idealised grid layout with a range of flow rates and parking policies. Results demonstrate delay decreased by 9%-27% from the benchmark case. Additionally, the traffic delay distribution shows the trade-offs between expanding road capacity and minimising traffic demand through curb management, indicating the interplay between curb parking and traffic management in the AV era.

Conference paper

Whyte J, Mijic A, Myers RJ, Angeloudis P, Cardin M, Stettler M, Ochieng Wet al., 2020, A research agenda on systems approaches to infrastructure, Journal of Civil Engineering and Environmental Systems, Vol: 37, Pages: 214-233, ISSN: 1029-0249

At a time of system shocks, significant underlying challenges are revealed in current approaches to delivering infrastructure, including that infrastructure users in many societies feel distant from nature. We set out a research agenda on systems approaches to infrastructure, drawing on ten years of interdisciplinary work on operating infrastructure, infrastructure interventions and lifecycles. Research insights and directions on complexity, systems integration, data-driven systems engineering, infrastructure life-cycles, and the transition towards zero pollution are summarised. This work identifies a need to better understand the natural and societal impacts of infrastructure interventions under uncertainty. We argue for a change in current approaches to infrastructure: starting from the natural environment and its resources, encompassing societal use of infrastructure and the supporting infrastructure assets and services. To support such proposed new systems approaches to infrastructure, researchers need to develop novel modelling methods, forms of model integration, and multi-criteria indicators.

Journal article

Escribano Macias J, Goldbeck N, Hsu P-Y, Angeloudis P, Ochieng Wet al., 2020, Endogenous stochastic optimisation for relief distribution assisted with unmanned aerial vehicles, OR SPECTRUM, Vol: 42, Pages: 1089-1125, ISSN: 0171-6468

Unmanned aerial vehicles (UAVs) have been increasingly viewed as useful tools to assist humanitarian response in recent years. While organisations already employ UAVs for damage assessment during relief delivery, there is a lack of research into formalising a problem that considers both aspects simultaneously. This paper presents a novel endogenous stochastic vehicle routing problem that coordinates UAV and relief vehicle deployments to minimise overall mission cost. The algorithm considers stochastic damage levels in a transport network, with UAVs surveying the network to determine the actual network damages. Ground vehicles are simultaneously routed based on the information gathered by the UAVs. A case study based on the Haiti road network is solved using a greedy solution approach and an adapted genetic algorithm. Both methods provide a significant improvement in vehicle travel time compared to a deterministic approach and a non-assisted relief delivery operation, demonstrating the benefits of UAV-assisted response.

Journal article

Karamanis R, Anastasiadis E, Stettler M, Angeloudis Pet al., 2020, Vehicle redistribution in ride-sourcing markets using convex minimum cost flows

Ride-sourcing platforms often face imbalances in the demand and supply ofrides across areas in their operating road-networks. As such, dynamic pricingmethods have been used to mediate these demand asymmetries through surge pricemultipliers, thus incentivising higher driver participation in the market.However, the anticipated commercialisation of autonomous vehicles couldtransform the current ride-sourcing platforms to fleet operators. The absenceof human drivers fosters the need for empty vehicle management to address anyvehicle supply deficiencies. Proactive redistribution using integer programmingand demand predictive models have been proposed in research to address thisproblem. A shortcoming of existing models, however, is that they ignore themarket structure and underlying customer choice behaviour. As such, currentmodels do not capture the real value of redistribution. To resolve this, weformulate the vehicle redistribution problem as a non-linear minimum cost flowproblem which accounts for the relationship of supply and demand of rides, byassuming a customer discrete choice model and a market structure. Wedemonstrate that this model can have a convex domain, and we introduce an edgesplitting algorithm to solve a transformed convex minimum cost flow problem forvehicle redistribution. By testing our model using simulation, we show that ourredistribution algorithm can decrease wait times up to 50% and increase vehicleutilization up to 8%. Our findings outline that the value of redistribution iscontingent on localised market structure and customer behaviour.

Journal article

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: respub-action=search.html&id=00337165&limit=30&person=true