Large-Scale Bandwidth and Power Optimization for Multi-Modal Edge Intelligence Autonomous Driving

TL;DR

This paper introduces an efficient algorithm for optimizing bandwidth and power in multi-modal edge autonomous driving, significantly improving training quality and reducing computation time in high-mobility scenarios.

Contribution

It presents a novel, low-complexity optimization algorithm that maximizes training quality by considering data modality priorities and wireless channel variations.

Findings

Reduces perception error by 3% in simulations

Decreases computation time by 98%

Effectively manages large-scale multi-modal data transmission

Abstract

Edge intelligence autonomous driving (EIAD) offers computing resources in autonomous vehicles for training deep neural networks. However, wireless channels between the edge server and the autonomous vehicles are time-varying due to the high-mobility of vehicles. Moreover, the required number of training samples for different data modalities, e.g., images, point-clouds, is diverse. Consequently, when collecting these datasets from vehicles to the edge server, the associated bandwidth and power allocation across all data frames is a large-scale multi-modal optimization problem. This article proposes a highly computationally efficient algorithm that directly maximizes the quality of training (QoT). The key ingredients include a data-driven model for quantifying the priority of data modality and two first-order methods termed accelerated gradient projection and dual decomposition for low-complexity resource allocation. Finally, high-fidelity simulations in Car Learning to Act (CARLA) show that the proposed algorithm reduces the perception error by $3\%$ and the computation time by $98\%$.