Online V2X Scheduling for Raw-Level Cooperative Perception

TL;DR

This paper introduces an online scheduling algorithm for raw-level cooperative perception in connected vehicles, optimizing energy use by selecting the best vehicle to share sensor data amidst dynamic network and traffic conditions.

Contribution

It formulates the scheduling as a Multi-Armed Bandit problem considering vehicle volatility, channel heterogeneity, and traffic, and proposes an online learning algorithm with proven performance.

Findings

The algorithm quickly learns to select the optimal vehicle for cooperation.

It reduces energy consumption compared to baseline methods.

Simulation results validate the effectiveness of the proposed approach.

Abstract

Cooperative perception of connected vehicles comes to the rescue when the field of view restricts stand-alone intelligence. While raw-level cooperative perception preserves most information to guarantee accuracy, it is demanding in communication bandwidth and computation power. Therefore, it is important to schedule the most beneficial vehicle to share its sensor in terms of supplementary view and stable network connection. In this paper, we present a model of raw-level cooperative perception and formulate the energy minimization problem of sensor sharing scheduling as a variant of the Multi-Armed Bandit (MAB) problem. Specifically, volatility of the neighboring vehicles, heterogeneity of V2X channels, and the time-varying traffic context are taken into consideration. Then we propose an online learning-based algorithm with logarithmic performance loss, achieving a decent trade-off between exploration and exploitation. Simulation results under different scenarios indicate that the proposed algorithm quickly learns to schedule the optimal cooperative vehicle and saves more energy as compared to baseline algorithms.