Search arXiv⌕ Search

arXiv subjects

Roman Engelhardt

Publications and source records attributed to Roman Engelhardt.

14 recordsLinked to original sources
arXiv2025

Semi-on-Demand Transit Feeders with Shared Autonomous Vehicles and Reinforcement-Learning-Based Zonal Dispatching Control

This paper develops a semi-on-demand transit feeder service using shared autonomous vehicles (SAVs) and zonal dispatching control based on reinforcement learning (RL). This service combines the cost-effectiveness of fixed-route transit with the adaptability of demand-responsive transport to improve accessibility in lower-density areas. Departing from the terminus, SAVs first make scheduled fixed stops, then offer on-demand pick-ups and drop-offs in a pre-determined flexible-route area. Our deep RL model dynamically assigns vehicles to subdivided flexible-route zones in response to real-time demand fluctuations and operations, using a policy gradient algorithm - Proximal Policy Optimization. The methodology is demonstrated through agent-based simulations on a real-world bus route in Munich, Germany. Results show that after efficient training of the RL model, the semi-on-demand service with dynamic zonal control serves 16% more passengers at 13% higher generalized costs on average compared to traditional fixed-route service. The efficiency gain brought by RL control brings 2.4% more passengers at 1.4% higher costs. This study not only showcases the potential of integrating SAV feeders and machine learning techniques into public transit, but also sets the groundwork for further innovations in addressing first-mile-last-mile problems in multimodal transit systems.

cs.LG↗
arXiv2025

Machine Learning Surrogates for Optimizing Transportation Policies with Agent-Based Models

Rapid urbanization and growing urban populations worldwide present significant challenges for cities, including increased traffic congestion and air pollution. Effective strategies are needed to manage traffic volumes and reduce emissions. In practice, traditional traffic flow simulations are used to test those strategies. However, high computational intensity usually limits their applicability in investigating a magnitude of different scenarios to evaluate best policies. This paper presents a first approach of using Graph Neural Networks (GNN) as surrogates for large-scale agent-based simulation models. In a case study using the MATSim model of Paris, the GNN effectively learned the impacts of capacity reduction policies on citywide traffic flow. Performance analysis across various road types and scenarios revealed that the GNN could accurately capture policy-induced effects on edge-based traffic volumes, particularly on roads directly affected by the policies and those with higher traffic volumes.

cs.CE↗
arXiv2024

Semi-on-Demand Off-Peak Transit Services with Shared Autonomous Vehicles -- Service Planning, Simulation, and Analysis in Munich, Germany

This study investigates the implementation of semi-on-demand (SoD) hybrid-route services using Shared Autonomous Vehicles (SAVs) on existing transit lines. SoD services combine the cost efficiency of fixed-route buses with the flexibility of on-demand services. SAVs first serve all scheduled fixed-route stops, then drop off and pick up passengers in the pre-determined flexible-route portion, and return to the fixed route. This study addresses four key questions: optimal fleet and vehicle sizes for peak-hour fixed-route services with SAVs and during transition (from drivers to autonomous vehicles), optimal off-peak SoD service planning, and suitable use cases. The methodology combines analytical modeling for service planning with agent-based simulation for operational analysis. We examine ten bus routes in Munich, Germany, considering full SAV and transition scenarios with varying proportions of drivers. Our findings demonstrate that the lower operating costs of SAVs improve service quality through increased frequency and smaller vehicles, even in transition scenarios. The reduced headway lowers waiting time and also favors more flexible-route operation in SoD services. The optimal SoD settings range from fully flexible to hybrid routes, where higher occupancy from the terminus favors shorter flexible routes. During the transition phase, limited fleet size and higher headways constrain the benefits of flexible-route operations. The simulation results corroborate the SoD benefits of door-to-door convenience, attracting more passengers without excessive detours and operator costs at moderate flexible-route lengths, and validate the analytical model.

eess.SY↗
arXiv2024

Graph Neural Network Approach to Predict the Effects of Road Capacity Reduction Policies: A Case Study for Paris, France

Rapid urbanization and growing urban populations worldwide present significant challenges for cities, including increased traffic congestion and air pollution. Effective strategies are needed to manage traffic volumes and reduce emissions. In practice, traditional traffic flow simulations are used to test those strategies. However, high computational intensity usually limits their applicability in investigating a magnitude of different scenarios to evaluate best policies. This paper introduces an innovative approach to assess the effects of traffic policies using Graph Neural Networks (GNN). By incorporating complex transport network structures directly into the neural network, this approach could enable rapid testing of various policies without the delays associated with traditional simulations. We provide a proof of concept that GNNs can learn and predict changes in car volume resulting from capacity reduction policies. We train a GNN model based on a training set generated with a MATSim simulation for Paris, France. We analyze the model's performance across different road types and scenarios, finding that the GNN is generally able to learn the effects on edge-based traffic volume induced by policies. The model is especially successful in predicting changes on major streets. Nevertheless, the evaluation also showed that the current model has problems in predicting impacts of spatially small policies and changes in traffic volume in regions where no policy is applied due to spillovers and/or relocation of traffic.

cs.CE↗
arXiv2023

Predictive Vehicle Repositioning for On-Demand Ride-Pooling Services

On-Demand Ride-Pooling services have the potential to increase traffic efficiency compared to private vehicle trips by decreasing parking space needed and increasing vehicle occupancy due to higher vehicle utilization and shared trips, respectively. Thereby, an operator controls a fleet of vehicles that serve requested trips on-demand while trips can be shared. In this highly dynamic and stochastic setting, asymmetric spatio-temporal request distributions can drive the system towards an imbalance between demand and supply when vehicles end up in regions with low demand. This imbalance would lead to low fleet utilization and high customer waiting times. This study proposes a novel rebalancing algorithm to predictively reposition idle fleet vehicles to reduce this imbalance. The algorithm first samples artificial requests from a predicted demand distribution and simulates future fleet states to identify supply shortages. An assignment problem is formulated that assigns repositioning trips considering multiple samples and forecast horizons. The algorithm is implemented in an agent-based simulation framework and compared to multiple state-of-the-art rebalancing algorithms. A case study for Chicago, Illinois shows the benefits of applying the repositioning strategy by increasing service rate and vehicle revenue hours by roughly 50% compared to a service without repositioning. It additionally outperforms all comparison algorithms by serving more customers, increasing the pooling efficiency and decreasing customer waiting time regardless of the forecasting method applied. As a trade-off, the computational time increases, but with a termination within a couple of seconds it is still applicable for large-scale real world instances.

eess.SY↗
arXiv2023

Effects of Dynamic and Stochastic Travel Times on the Operation of Mobility-on-Demand Services

Mobility-on-Demand (MoD) services have been an active research topic in recent years. Many studies focused on developing control algorithms to supply efficient services. To cope with a large search space to solve the underlying vehicle routing problem, studies usually apply hard time-constraints on pick-up and drop-off while considering static network travel times to reduce computational time. As travel times in real street networks are dynamic and stochastic, assigned routes considered feasible by the control algorithm in one time step might become infeasible in the next. Since once assigned and confirmed, customers should still be part of the solution, damage control is necessary to counteract this effect. In this study, a detailed simulation framework for MoD services is coupled with a microscopic traffic simulation to create dynamic and stochastic travel times, and tested in a case study for Munich, Germany. Results showed that the combination of inaccurate travel time estimation and damage control strategies for infeasible routes deteriorates the performance of MoD services -- hailing and pooling -- significantly. Moreover, customers suffer from unreliable pick-up time and travel time estimations. Allowing re-assignments of initial vehicle schedules according to updated system states helps to restore system efficiency and reliability, but only to a minor extent.

eess.SY↗
arXiv2023

Redesigning Large-Scale Multimodal Transit Networks with Shared Autonomous Mobility Services

This study addresses a large-scale multimodal transit network design problem, with Shared Autonomous Mobility Services (SAMS) as both transit feeders and an origin-to-destination mode. The framework captures spatial demand and modal characteristics, considers intermodal transfers and express services, determines transit infrastructure investment and path flows, and generates transit routes. A system-optimal multimodal transit network is designed with minimum total door-to-door generalized costs of users and operators, satisfying transit origin-destination demand within a pre-set infrastructure budget. Firstly, the geography, demand, and modes in each zone are characterized with continuous approximation. The decisions of network link investment and multimodal path flows in zonal connection optimization are formulated as a minimum-cost multi-commodity network flow (MCNF) problem and solved efficiently with a mixed-integer linear programming (MILP) solver. Subsequently, the route generation problem is solved by expanding the MCNF formulation to minimize intramodal transfers. The model is illustrated through a set of experiments with the Chicago network comprised of 50 zones and seven modes, under three scenarios. The computational results present savings in traveler journey time and operator cost demonstrating the potential benefits of collaboration between multimodal transit systems and SAMS.

eess.SY↗
arXiv2022

Simulating Ride-Pooling Services with Pre-Booking and On-Demand Customers

If private vehicle trips can be replaced, ride-pooling services can decrease parking space needed by higher vehicle utilization and increase traffic efficiency by increasing vehicle occupancy. Nevertheless, substantial benefits can only be achieved if a certain market penetration is passed to find enough shareable rides for pooling to take place. Additionally, because of their highly dynamic and stochastic nature on-demand ride-pooling services cannot always guarantee that a request is served. Allowing customers to pre-book their trip in advance could provide benefits for both aspects. Additional knowledge helps an operator to better plan vehicle schedules to improve service efficiency while an accepted trip or a rejection can be communicated early on to the customer. This study presents a simulation framework where a ride-pooling provider offers a service in mixed operation: Customers can either use the service on-demand or pre-book trips. A graph-based batch optimization formulation is proposed to create offline schedules for pre-booking customers. Using two rolling horizons, this offline solution is forwarded to an online optimization for on-demand and pre-booking customers simultaneously. The framework is tested in a case study for Manhattan, NYC. That the graph-based batch optimization is superior to a basic insertion method in terms of solution quality and run-time. Due to additional knowledge, the ride-pooling operator can improve the solution quality significantly by serving more customers while pooling efficiency can be increased. Additionally, customers have shorter waiting and detour times the more customers book a trip in advance.

eess.SY↗
arXiv2022

FleetPy: A Modular Open-Source Simulation Tool for Mobility On-Demand Services

The market share of mobility on-demand (MoD) services strongly increased in recent years and is expected to rise even higher once vehicle automation is fully available. These services might reduce space consumption in cities as fewer parking spaces are required if private vehicle trips are replaced. If rides are shared additionally, occupancy related traffic efficiency is increased. Simulations help to identify the actual impact of MoD on a traffic system, evaluate new control algorithms for improved service efficiency and develop guidelines for regulatory measures. This paper presents the open-source agent-based simulation framework FleetPy. FleetPy (written in the programming language "Python") is explicitly developed to model MoD services in a high level of detail. It specially focuses on the modeling of interactions of users with operators while its flexibility allows the integration and embedding of multiple operators in the overall transportation system. Its modular structure ensures the transferabillity of previously developed elements and the selection of an appropriate level of modeling detail. This paper compares existing simulation frameworks for MoD services and highlights exclusive features of FleetPy. The upper level simulation flows are presented, followed by required input data for the simulation and the output data FleetPy produces. Additionally, the modules within FleetPy and high-level descriptions of current implementations are provided. Finally, an example showcase for Manhattan, NYC provides insights into the impacts of different modules for simulation flow, fleet optimization, traveler behavior and network representation.

cs.MA↗
arXiv2022

Integrating Parcel Deliveries into a Ride-Pooling Service -- An Agent-Based Simulation Study

This paper examines the integration of freight delivery into the passenger transport of an on-demand ride-pooling service. The goal of this research is to use existing passenger trips for logistics services and thus reduce additional vehicle kilometers for freight delivery and the total number of vehicles on the road network. This is achieved by merging the need for two separate fleets into a single one by combining the services. To evaluate the potential of such a mobility-on-demand service, this paper uses an agent-based simulation framework and integrates three heuristic parcel assignment strategies into a ride-pooling fleet control algorithm. Two integration scenarios (moderate and full) are set up. While in both scenarios passengers and parcels share rides in one vehicle, in the moderate scenario no stops for parcel pick-up and delivery are allowed during a passenger ride to decrease customer inconvenience. Using real-world demand data for a case study of Munich, Germany, the two integration scenarios together with the three assignment strategies are compared to the status quo, which uses two separate vehicle fleets for passenger and logistics transport. The results indicate that the integration of logistics services into a ride-pooling service is possible and can exploit unused system capacities without deteriorating passenger transport. Depending on the assignment strategies nearly all parcels can be served until a parcel to passenger demand ratio of 1:10 while the overall fleet kilometers can be deceased compared to the status quo.

cs.MA↗
arXiv2022

Competition and Cooperation of Autonomous Ridepooling Services: Game-Based Simulation of a Broker Concept

Autonomous mobility on demand services have the potential to disrupt the future mobility system landscape. Ridepooling services in particular can decrease land consumption and increase transportation efficiency by increasing the average vehicle occupancy. Nevertheless, because ridepooling services require a sufficient user base for pooling to take effect, their performance can suffer if multiple operators offer such a service and must split the demand. This study presents a simulation framework for evaluating the impact of competition and cooperation among multiple ridepooling providers. Two different kinds of interaction via a broker platform are compared with the base cases of a single monopolistic operator and two independent operators with divided demand. In the first, the broker presents trip offers from all operators to customers (similar to a mobility-as-a-service platform), who can then freely choose an operator. In the second, a regulated broker platform can manipulate operator offers with the goal of shifting the customer-operator assignment from a user equilibrium towards a system optimum. To model adoptions of the service design depending on the different interaction scenario, a game setting is introduced. Within alternating turns between operators, operators can adapt parameters of their service (fleet size and objective function) to maximize profit. Results for a case study based on Manhattan taxi data, show that operators generate the highest profit in the broker setting while operating the largest fleet. Additionally, pooling efficiency can nearly be maintained compared to a single operator. With the resulting increased service rate, the regulated competition benefits not only operators (profit) and cities (increased pooling efficiency), but also customers. Contrarily, when users can decide freely, the lowest pooling efficiency and operator profit is observed.

cs.MA↗
arXiv2021

On the Dynamism of User Rejections in Mobility-on-Demand Systems

Mobility-on-demand (MoD) systems, especially ride-hailing systems, have seen tremendous growth in recent years. These systems provide user-centric mobility services, whose users expect a high level of convenience. Waiting for a response after an app request and eventually learning after a long period of time that no vehicle is available is hardly acceptable. This study investigates the use-case where users should be served within a certain maximum waiting time. Under certain assumptions, which are reasonable for an attractive MoD business model, it can be shown that an operator using dynamic state optimization can communicate a rejection to users after the first iteration, thereby eliminating unnecessary waiting time before these users would leave the system. Furthermore, early operator rejections reduce the dimension of subsequent customer-vehicle assignment problems, thereby saving computational resources and solving the problems faster. In turn, this allows shorter re-optimization cycles and once again faster responses, i.e. a better user experience.

eess.SY↗
arXiv2021

Regulating Mobility-on-Demand Services: Tri-level Model and Bayesian Optimization Solution Approach

The goal of this paper is to develop a modeling framework that captures the inter-decision dynamics between mobility service providers (MSPs) and travelers that can be used to optimize and analyze policies/regulations related to MSPs. To meet this goal, the paper proposes a tri-level mathematical programming model with a public-sector decision maker (regulator) at the highest level, the MSP in the middle level, and travelers at the lowest level. The regulator aims to maximize social welfare via implementing regulations, policies, plans, transit service designs, etc. The MSP aims to maximize profit by adjusting its service designs. Travelers aim to maximize utility by changing their modes and routes. The travelers' decisions depend on the regulator and MSP's decisions while the MSP decisions themselves depend on the regulator's decisions. To solve the tri-level mathematical program, the study employs Bayesian optimization (BO) within a simulation-optimization solution approach. At the lowest level, the solution approach includes an agent-based transportation system simulation model to capture travelers' behavior subject to specific decisions made by the regulator and MSP. The agent-based transportation simulation model includes a mode choice model, a road network, a transit network, and an MSP providing automated mobility-on-demand (AMOD) service with shared rides. The modeling and solution approaches are applied to Munich, Germany in order to validate the model. The case study investigates the tolls and parking costs the city administration should set, as well as changes in the public transport budget and a limitation of the AMOD fleet size. Best policy settings are derived for two social welfare definitions, in both of which the AMOD fleet size is not regulated as the shared-ride AMOD service provides significant value to travelers in Munich.

eess.SY↗
arXiv2020

Speed-up Heuristic for an On-Demand Ride-Pooling Algorithm

With ongoing developments in digitalization and advances in the field of autonomous driving, on-demand ride pooling is a mobility service with the potential to disrupt the urban mobility market. Nevertheless, to apply this kind of service successfully efficient algorithms have to be implemented for effective fleet management to exploit the benefits associated with this mobility service. Especially real time computation of finding beneficial assignments is a problem not solved for large problem sizes until today. In this study, we show the importance of using advanced algorithms by comparing a fast, but simple insertion heuristic algorithm with a state-of-the-art multi-step matching algorithm. We test the algorithms in various scenarios based on private vehicle trip OD-data for Munich, Germany. Results indicate that in the tested scenarios by using the multi-step algorithm up to 8$\%$ additional requests could be served while also 10$\%$ additional driven distance could be saved. However, computational time for finding optimal assignments in the advanced algorithm exceeds real time rather fast as problem size increases. Therefore, several aspects to reduce the computational time by decreasing redundant checks of the advanced multi step algorithm are introduced. Finally, a refined vehicle selection heuristic based on three rules is presented to furthermore reduce the computational effort. In the tested scenarios this heuristic can speed up the most cost intensive algorithm step by a factor of over 8, while keeping the number of served requests almost constant and maintaining around 70$\%$ of the driven distance saved in the system. Considering all algorithm steps, an overall speed up of 2.5 could be achieved.

eess.SY↗