Online and Adaptive Parking Availability Mapping: An Uncertainty-Aware Active Sensing Approach for Connected Vehicles

TL;DR

This paper introduces an online, adaptive parking mapping method for connected vehicles using active sensing and Gaussian Process Regression, improving convergence speed and resource efficiency in dynamic parking environments.

Contribution

The paper presents a novel active sensing approach combined with Gaussian Process Regression for real-time, adaptive parking availability mapping in connected vehicles.

Findings

Faster convergence in parking mapping compared to baselines

Enhanced adaptivity to changing parking conditions

Low computational overhead of the proposed method

Abstract

Research on connected vehicles represents a continuously evolving technological domain, fostered by the emerging Internet of Things (IoT) paradigm and the recent advances in intelligent transportation systems. Nowadays, vehicles are platforms capable of generating, receiving and automatically act based on large amount of data. In the context of assisted driving, connected vehicle technology provides real-time information about the surrounding traffic conditions. Such information is expected to improve drivers' quality of life, for example, by adopting decision making strategies according to the current parking availability status. In this context, we propose an online and adaptive scheme for parking availability mapping. Specifically, we adopt an information-seeking active sensing approach to select the incoming data, thus preserving the onboard storage and processing resources; then, we estimate the parking availability through Gaussian Process Regression. We compare the proposed algorithm with several baselines, which attain inferior performance in terms of mapping convergence speed and adaptivity capabilities; moreover, the proposed approach comes at the cost of a very small computational demand.