A Learning-Based Optimization Approach for Autonomous Ridesharing Platforms with Service-Level Contracts and On-Demand Hiring of Idle Vehicles

2021 ◽  
Author(s):  
Breno A. Beirigo ◽  
Frederik Schulte ◽  
Rudy R. Negenborn
Keyword(s):  
New York ◽  
Autonomous Vehicles ◽  
Transportation Network ◽  
Supply And Demand ◽  
Service Level ◽  
Third Party ◽  
Optimization Approach ◽  
Marginal Value ◽  
On Demand ◽  
Demand Fluctuations

Current mobility services cannot compete on equal terms with self-owned mobility products concerning service quality. Because of supply and demand imbalances, ridesharing users invariably experience delays, price surges, and rejections. Traditional approaches often fail to respond to demand fluctuations adequately because service levels are, to some extent, bounded by fleet size. With the emergence of autonomous vehicles, however, the characteristics of mobility services change and new opportunities to overcome the prevailing limitations arise. In this paper, we consider an autonomous ridesharing problem in which idle vehicles are hired on-demand in order to meet the service-level requirements of a heterogeneous user base. In the face of uncertain demand and idle vehicle supply, we propose a learning-based optimization approach that uses the dual variables of the underlying assignment problem to iteratively approximate the marginal value of vehicles at each time and location under different availability settings. These approximations are used in the objective function of the optimization problem to dispatch, rebalance, and occasionally hire idle third-party vehicles in a high-resolution transportation network of Manhattan, New York City. The results show that the proposed policy outperforms a reactive optimization approach in a variety of vehicle availability scenarios while hiring fewer vehicles. Moreover, we demonstrate that mobility services can offer strict service-level contracts to different user groups featuring both delay and rejection penalties.

scholarly journals Rebalancing Autonomous Vehicles using Deep Reinforcement Learning

2022 ◽  
Vol 16 ◽  
pp. 646-652
Author(s):  
Jiajie Dai ◽  
Qianyu Zhu ◽  
Nan Jiang ◽  
Wuyang Wang
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Supply And Demand ◽  
Efficient Operation ◽  
Demand And Supply ◽  
On Demand ◽  
Demand Information ◽  
Autonomous Mobility ◽  
Demand Patterns

The shared autonomous mobility-on-demand (AMoD) system is a promising business model in the coming future which provides a more efficient and affordable urban travel mode. However, to maintain the efficient operation of AMoD and address the demand and supply mismatching, a good rebalancing strategy is required. This paper proposes a reinforcement learning-based rebalancing strategy to minimize passengers’ waiting in a shared AMoD system. The state is defined as the nearby supply and demand information of a vehicle. The action is defined as moving to a nearby area with eight different directions or staying idle. A 4.6 4.4 km2 region in Cambridge, Massachusetts, is used as the case study. We trained and tested the rebalancing strategy in two different demand patterns: random and first-mile. Results show the proposed method can reduce passenger’s waiting time by 7% for random demand patterns and 10% for first-mile demand patterns.

Integrating Supply and Demand Perspectives for a Large-Scale Simulation of Shared Autonomous Vehicles

2020 ◽  
Vol 2674 (7) ◽  
pp. 181-192 ◽  
Author(s):  
Krishna Murthy Gurumurthy ◽  
Felipe de Souza ◽  
Annesha Enam ◽  
Joshua Auld
Keyword(s):  
Autonomous Vehicles ◽  
High Performance ◽  
Large Scale ◽  
Choice Model ◽  
Transportation Network ◽  
Supply And Demand ◽  
Transportation Systems ◽  
Point Of View ◽  
Computational Time ◽  
Vehicle Assignment

Transportation Network Companies (TNCs) have been steadily increasing the share of total trips in metropolitan areas across the world. Micro-modeling TNC operation is essential for large-scale transportation systems simulation. In this study, an agent-based approach for analyzing supply and demand aspects of ride-sourcing operation is done using POLARIS, a high-performance simulation tool. On the demand side, a mode-choice model for the agent and a vehicle-ownership model that informs this choice are developed. On the supply side, TNC vehicle-assignment strategies, pick-up and drop-off operations, and vehicle repositioning are modeled with congestion feedback, an outcome of the mesoscopic traffic simulation. Two case studies of Bloomington and Chicago in Illinois are used to study the framework’s computational speed for large-scale operations and the effect of TNC fleets on a region’s congestion patterns. Simulation results show that a zone-based vehicle-assignment strategy scales better than relying on matching closest vehicles to requests. For large regions like Chicago, large fleets are seen to be detrimental to congestion, especially in a future in which more travelers will use TNCs. From an operational point of view, an efficient relocation strategy is critical for large regions with concentrated demand, but not regulating repositioning can worsen empty travel and, consequently, congestion. The TNC simulation framework developed in this study is of special interest to cities and regions, since it can be used to model both demand and supply aspects for large regions at scale, and in reasonably low computational time.

DESIGN OF ROBUST DISTRIBUTION NETWORKS RUN BY THIRD PARTY LOGISTICS SERVICE PROVIDERS

2012 ◽  
Vol 15 (05) ◽  
pp. 1150024 ◽  
Author(s):  
M. P. M. HENDRIKS ◽  
D. ARMBRUSTER ◽  
M. LAUMANNS ◽  
E. LEFEBER ◽  
J. T. UDDING
Keyword(s):  
Network Topology ◽  
Service Providers ◽  
Supply And Demand ◽  
Distribution Networks ◽  
Optimization Method ◽  
Service Level ◽  
Third Party ◽  
Third Party Logistics ◽  
Logistics Service ◽  
Set Up

We consider a third party logistics service provider (LSP), who faces the problem of distributing different products from suppliers to consumers having no control on supply and demand. In a third party set-up, the operations of transport and storage are run as a black box for a fixed price. Thus the incentive for an LSP is to reduce its operational costs. The objective of this paper is to find an efficient network topology on a tactical level, which still satisfies the service level agreements on the operational level. We develop an optimization method, which constructs a tactical network topology based on the operational decisions resulting from a given model predictive control (MPC) policy. Experiments suggest that such a topology typically requires only a small fraction of all possible links. As expected, the found topology is sensitive to changes in supply and demand averages. Interestingly, the found topology appears to be robust to changes in second order moments of supply and demand distributions.

scholarly journals Cybersafety Approach to Cybersecurity Analysis and Mitigation for Mobility-as-a-Service and Internet of Vehicles

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1220
Author(s):  
Chee Wei Lee ◽  
Stuart Madnick
Keyword(s):  
Autonomous Vehicles ◽  
Process Analysis ◽  
Hazard Analysis ◽  
Urban Mobility ◽  
Internet Of Vehicles ◽  
On Demand ◽  
Software Updates ◽  
Levels Of Automation ◽  
New Generation ◽  
Convergence Of Technologies

Urban mobility is in the midst of a revolution, driven by the convergence of technologies such as artificial intelligence, on-demand ride services, and Internet-connected and self-driving vehicles. Technological advancements often lead to new hazards. Coupled with the increased levels of automation and connectivity in the new generation of autonomous vehicles, cybersecurity is emerging as a key threat affecting these vehicles. Traditional hazard analysis methods treat safety and security in isolation and are limited in their ability to account for interactions among organizational, sociotechnical, human, and technical components. In response to these challenges, the cybersafety method, based on System Theoretic Process Analysis (STPA and STPA-Sec), was developed to meet the growing need to holistically analyze complex sociotechnical systems. We applied cybersafety to coanalyze safety and security hazards, as well as identify mitigation requirements. The results were compared with another promising method known as Combined Harm Analysis of Safety and Security for Information Systems (CHASSIS). Both methods were applied to the Mobility-as-a-Service (MaaS) and Internet of Vehicles (IoV) use cases, focusing on over-the-air software updates feature. Overall, cybersafety identified additional hazards and more effective requirements compared to CHASSIS. In particular, cybersafety demonstrated the ability to identify hazards due to unsafe/unsecure interactions among sociotechnical components. This research also suggested using CHASSIS methods for information lifecycle analysis to complement and generate additional considerations for cybersafety. Finally, results from both methods were backtested against a past cyber hack on a vehicular system, and we found that recommendations from cybersafety were likely to mitigate the risks of the incident.

Partnerships with Technology-Enabled Mobility Companies

2017 ◽  
Vol 2649 (1) ◽  
pp. 106-112 ◽  
Author(s):  
Marla Westervelt ◽  
Joshua Schank ◽  
Emma Huang
Keyword(s):  
Service Delivery ◽  
Public Transit ◽  
Transportation Network ◽  
Public Agencies ◽  
On Demand ◽  
Transportation Network Companies

The rise and the proliferation of the on-demand economy are creating a new mobility marketplace. This research explored how these new options could be synergistic with public transit models and detailed the experiences of two transit operators that entered into service delivery partnerships with a transportation network company and a micro-transit operator. Based on a series of interviews and the experiences of these two public agencies, this research provides a set of key takeaways and recommendations for transit operators exploring the potential of partnering with new mobility services such as transportation network companies (e.g., Uber or Lyft) and microtransit (e.g., Bridj or Via).

Coping with Spatial Mismatch: Subsidy Design for Electric Vehicle and Charging Markets

2021 ◽  
Author(s):  
Wei Zhang ◽  
Yifan Dou
Keyword(s):  
Electric Vehicle ◽  
Service Providers ◽  
Supply And Demand ◽  
Problem Definition ◽  
Environmental Benefits ◽  
Third Party ◽  
Theoretic Model ◽  
Spatial Mismatch ◽  
The Government ◽  
Ev Charging

Problem definition: We study how the government should design the subsidy policy to promote electric vehicle (EV) adoptions effectively and efficiently when there might be a spatial mismatch between the supply and demand of charging piles. Academic/practical relevance: EV charging infrastructures are often built by third-party service providers (SPs). However, profit-maximizing SPs might prefer to locate the charging piles in the suburbs versus downtown because of lower costs although most EV drivers prefer to charge their EVs downtown given their commuting patterns and the convenience of charging in downtown areas. This conflict of spatial preferences between SPs and EV drivers results in high overall costs for EV charging and weak EV adoptions. Methodology: We use a stylized game-theoretic model and compare three types of subsidy policies: (i) subsidizing EV purchases, (ii) subsidizing SPs based on pile usage, and (iii) subsidizing SPs based on pile numbers. Results: Subsidizing EV purchases is effective in promoting EV adoptions but not in alleviating the spatial mismatch. In contrast, subsidizing SPs can be more effective in addressing the spatial mismatch and promoting EV adoptions, but uniformly subsidizing pile installation can exacerbate the spatial mismatch and backfire. In different situations, each policy can emerge as the best, and the rule to determine which side (SPs versus EV buyers) to subsidize largely depends on cost factors in the charging market rather than the EV price or the environmental benefits. Managerial implications: A “jigsaw-piece rule” is recommended to guide policy design: subsidizing SPs is preferred if charging is too costly or time consuming, and subsidizing EV purchases is preferred if charging is sufficiently fast and easy. Given charging costs that are neither too low nor too high, subsidizing SPs is preferred only if pile building downtown is moderately more expensive than pile building in the suburbs.

Sign in / Sign up

Export Citation Format

Share Document