Approximate dynamic programming for planning a ride-hailing system using autonomous fleets of electric vehicles
From MaRDI portal
Publication:2178143
DOI10.1016/J.EJOR.2020.01.033zbMATH Open1441.90014arXiv1810.08124OpenAlexW3002585184WikidataQ126304798 ScholiaQ126304798MaRDI QIDQ2178143FDOQ2178143
Authors: Lina Al-Kanj, Juliana Nascimento, Warren Powell 
Publication date: 7 May 2020
Published in: European Journal of Operational Research (Search for Journal in Brave)
Abstract: Within a decade, almost every major auto company, along with fleet operators such as Uber, have announced plans to put autonomous vehicles on the road. At the same time, electric vehicles are quickly emerging as a next-generation technology that is cost effective, in addition to offering the benefits of reducing the carbon footprint. The combination of a centrally managed fleet of driverless vehicles, along with the operating characteristics of electric vehicles, is creating a transformative new technology that offers significant cost savings with high service levels. This problem involves a dispatch problem for assigning riders to cars, a surge pricing problem for deciding on the price per trip and a planning problem for deciding on the fleet size. We use approximate dynamic programming to develop high-quality operational dispatch strategies to determine which car is best for a particular trip, when a car should be recharged, and when it should be re-positioned to a different zone which offers a higher density of trips. We prove that the value functions are monotone in the battery and time dimensions and use hierarchical aggregation to get better estimates of the value functions with a small number of observations. Then, surge pricing is discussed using an adaptive learning approach to decide on the price for each trip. Finally, we discuss the fleet size problem which depends on the previous two problems.
Full work available at URL: https://arxiv.org/abs/1810.08124
Recommendations
- An Adaptive Dynamic Programming Algorithm for Dynamic Fleet Management, I: Single Period Travel Times
- Dynamic matching for real-time ride sharing
- Approximate dynamic programming for ambulance redeployment
- Empty-car routing in ridesharing systems
- Pricing and optimization in shared vehicle systems: an approximation framework
Learning and adaptive systems in artificial intelligence (68T05) Dynamic programming (90C39) Transportation, logistics and supply chain management (90B06)
Cites Work
- Bagging predictors
- Approximate dynamic programming. Solving the curses of dimensionality
- Optimization for dynamic ride-sharing: a review
- Dynamic-programming approximations for stochastic time-staged integer multicommodity-flow problems
- The share-a-ride problem: people and parcels sharing taxis
- An optimization framework for the development of efficient one-way car-sharing systems
- An Adaptive Dynamic Programming Algorithm for Dynamic Fleet Management, I: Single Period Travel Times
- A representational paradigm for dynamic resource transformation problems
- Value function approximation using multiple aggregation for multiattribute resource management
- Hierarchical knowledge gradient for sequential sampling
- Optimal pricing for ride-sourcing platforms
- Optimal learning in experimental design using the knowledge gradient policy with application to characterizing nanoemulsion stability
- Optimal battery purchasing and charging strategy at electric vehicle battery swap stations
- Empty-car routing in ridesharing systems
Cited In (18)
- Accelerating value function approximations for dynamic dial-a-ride problems via dimensionality reductions
- Recent advances in integrating demand management and vehicle routing: a methodological review
- An online reinforcement learning approach to charging and order-dispatching optimization for an e-hailing electric vehicle fleet
- Fleet management for autonomous vehicles: online PDP under special constraints
- Dynamic scheduling with uncertain job types
- Models and algorithms for reliability-oriented dial-a-ride with autonomous electric vehicles
- A Queueing Model of Dynamic Pricing and Dispatch Control for Ride-Hailing Systems Incorporating Travel Times
- Heterogeneous fleet management for one-way electric carsharing system with optional orders, vehicle relocation and on-demand recharging
- Optimized ensemble value function approximation for dynamic programming
- A reinforcement learning approach to the stochastic cutting stock problem
- Approximate dynamic programming for an energy-efficient parallel machine scheduling problem
- Opportunities for reinforcement learning in stochastic dynamic vehicle routing
- Stochastic dynamic vehicle routing in the light of prescriptive analytics: a review
- Dynamic priority rules for combining on-demand passenger transportation and transportation of goods
- Ride solo or pool: designing price-service menus for a ride-sharing platform
- Heuristics for electric taxi fleet management at Teo Taxi
- An approximated dynamic programming model for the supply vessel fleet sizing problem
- The stochastic share-a-ride problem with electric vehicles and customer priorities
Uses Software
This page was built for publication: Approximate dynamic programming for planning a ride-hailing system using autonomous fleets of electric vehicles
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2178143)
