EdgeMap: CrowdSourcing High Definition Map in Automotive Edge Computing

TL;DR

EdgeMap is a novel crowdsourcing framework that efficiently updates high-definition maps in automotive edge computing by minimizing network resource usage through adaptive data offloading and resource reservation.

Contribution

This paper introduces EdgeMap, a new crowdsourcing HD map system utilizing deep reinforcement learning and Gaussian process regression for resource-efficient map updates.

Findings

Reduces resource usage by over 30% compared to existing solutions.

Effectively maintains map freshness under constrained network conditions.

Demonstrates scalability and robustness in extensive simulations.

Abstract

High definition (HD) map needs to be updated frequently to capture road changes, which is constrained by limited specialized collection vehicles. To maintain an up-to-date map, we explore crowdsourcing data from connected vehicles. Updating the map collaboratively is, however, challenging under constrained transmission and computation resources in dynamic networks. In this paper, we propose EdgeMap, a crowdsourcing HD map to minimize the usage of network resources while maintaining the latency requirements. We design a DATE algorithm to adaptively offload vehicular data on a small time scale and reserve network resources on a large time scale, by leveraging the multi-agent deep reinforcement learning and Gaussian process regression. We evaluate the performance of EdgeMap with extensive network simulations in a time-driven end-to-end simulator. The results show that EdgeMap reduces more than 30% resource usage as compared to state-of-the-art solutions.