Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Efficient Parking Search using Shared Fleet Data

Niklas Strauß, Lukas Rottkamp, Sebatian Schmoll, Matthias Schubert

TL;DR

The paper addresses how to efficiently locate on-street parking by exploiting data shared within a vehicle fleet to reduce uncertainty about future resource availability. It formalizes fleet-based dynamic resource routing as a multi-agent MDP and augments it with continuous-time Markov models of resource occupancy, extending single-agent solvers with two fleet-oriented approaches: Reservations and Multi-Agent Dynamic Probability Adaption. Through agent-based simulations on real Melbourne data and synthetic scenarios, it demonstrates substantial reductions in search times—up to about 84% in certain settings—and shows that both reservations and probability adaption are practical, scalable strategies for real-world, fleet-guided parking. The work further suggests extensions to partially observable environments and supports deployment in large-scale urban parking guidance systems.

Abstract

Finding an available on-street parking spot is a relevant problem of day-to-day life. In recent years, cities such as Melbourne and San Francisco deployed sensors that provide real-time information about the occupation of parking spots. Finding a free parking spot in such a smart environment can be modeled and solved as a Markov decision process (MDP). The problem has to consider uncertainty as available parking spots might not remain available until arrival due to other vehicles also claiming spots in the meantime. Knowing the parking intention of every vehicle in the environment would eliminate this uncertainty. Unfortunately, it does currently not seem realistic to have such data from all vehicles. In contrast, acquiring data from a subset of vehicles or a vehicle fleet appears feasible and has the potential to reduce uncertainty. In this paper, we examine the question of how useful sharing data within a vehicle fleet might be for the search times of particular drivers. We use fleet data to better estimate the availability of parking spots at arrival. Since optimal solutions for large scenarios are infeasible, we base our method on approximate solutions, which have been shown to perform well in single-agent settings. Our experiments are conducted on a simulation using real-world and synthetic data from the city of Melbourne. The results indicate that fleet data can significantly reduce search times for an available parking spot.

Efficient Parking Search using Shared Fleet Data

TL;DR

The paper addresses how to efficiently locate on-street parking by exploiting data shared within a vehicle fleet to reduce uncertainty about future resource availability. It formalizes fleet-based dynamic resource routing as a multi-agent MDP and augments it with continuous-time Markov models of resource occupancy, extending single-agent solvers with two fleet-oriented approaches: Reservations and Multi-Agent Dynamic Probability Adaption. Through agent-based simulations on real Melbourne data and synthetic scenarios, it demonstrates substantial reductions in search times—up to about 84% in certain settings—and shows that both reservations and probability adaption are practical, scalable strategies for real-world, fleet-guided parking. The work further suggests extensions to partially observable environments and supports deployment in large-scale urban parking guidance systems.

Abstract

Finding an available on-street parking spot is a relevant problem of day-to-day life. In recent years, cities such as Melbourne and San Francisco deployed sensors that provide real-time information about the occupation of parking spots. Finding a free parking spot in such a smart environment can be modeled and solved as a Markov decision process (MDP). The problem has to consider uncertainty as available parking spots might not remain available until arrival due to other vehicles also claiming spots in the meantime. Knowing the parking intention of every vehicle in the environment would eliminate this uncertainty. Unfortunately, it does currently not seem realistic to have such data from all vehicles. In contrast, acquiring data from a subset of vehicles or a vehicle fleet appears feasible and has the potential to reduce uncertainty. In this paper, we examine the question of how useful sharing data within a vehicle fleet might be for the search times of particular drivers. We use fleet data to better estimate the availability of parking spots at arrival. Since optimal solutions for large scenarios are infeasible, we base our method on approximate solutions, which have been shown to perform well in single-agent settings. Our experiments are conducted on a simulation using real-world and synthetic data from the city of Melbourne. The results indicate that fleet data can significantly reduce search times for an available parking spot.
Paper Structure (26 sections, 10 equations, 5 figures, 2 tables, 2 algorithms)

This paper contains 26 sections, 10 equations, 5 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Problem Setting
  5. Continuous-Time Markov Models
  6. Replanning
  7. Hindsight Planning
  8. Reservations
  9. Replanning with Reservations
  10. Hindsight Planner with Reservations
  11. Multi-Agent Dynamic Probability Adaption
  12. Evaluation
  13. Setting
  14. Road Network and Resources
  15. Resource Volatility
  16. ...and 11 more sections

Figures (5)

  • Figure 1: Locations of parking spots present in the simulation visualized as blue dots.
  • Figure 2: A heatmap of the parking occupations in different clusters during one hour on a working day.
  • Figure 3: Destinations of agents chosen from empirical data in two clusters with very high (center right, orange dots) and high demand (center left, dark red dots) for parking.
  • Figure 4: Number of unsuccessful resource claims in a fully observable single destination setting.
  • Figure 5: Computation time in ms on a logarithmic scale in a data-driven destination setting.