Two Tales of Platoon Intelligence for Autonomous Mobility Control: Enabling Deep Learning Recipes

TL;DR

This paper reviews recent deep learning approaches, specifically multi-agent reinforcement learning and neural Myerson auctions, to improve autonomous mobility control and resource management in vehicles and UAVs, highlighting their integration for better efficiency and trust.

Contribution

It surveys recent advances in MARL and neural Myerson auctions for autonomous mobility, emphasizing their integration as a novel approach for improved control and resource management.

Findings

Communication network (CommNet) enables distributed multi-agent actions.

Neural Myerson auction ensures trustfulness and optimal revenue.

Integration of MARL and neural auctions is promising for autonomous systems.

Abstract

This paper presents the deep learning-based recent achievements to resolve the problem of autonomous mobility control and efficient resource management of autonomous vehicles and UAVs, i.e., (i) multi-agent reinforcement learning (MARL), and (ii) neural Myerson auction. Representatively, communication network (CommNet), which is one of the most popular MARL algorithms, is introduced to enable multiple agents to take actions in a distributed manner for their shared goals by training all agents' states and actions in a single neural network. Moreover, the neural Myerson auction guarantees trustfulness among multiple agents as well as achieves the optimal revenue of highly dynamic systems. Therefore, we survey the recent studies on autonomous mobility control based on MARL and neural Myerson auction. Furthermore, we emphasize that integration of MARL and neural Myerson auction is expected to be critical for efficient and trustful autonomous mobility services.