Energy-Efficient Ground-Air-Space Vehicular Crowdsensing by Hierarchical Multi-Agent Deep Reinforcement Learning With Diffusion Models
- 12 September 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 42 (12) , 3566-3580
Abstract
The integrated ground-air-space (GAS) communications system can enhance post-disaster rescue and management efforts when traditional networks fail, by navigating unmanned ground vehicles (UGVs) and unmanned arieal vehicles (UAVs) to collaboratively collect sufficient data from point-of-interests (PoIs) in a timely manner. In this paper, we consider the GAS vehicular crowdsensing (VCS) campaign, where UGVs dispatch and callback UAVs periodically across multiple stops in the workzone, to maximize the total collected amount of data, geographic fairness while minimizing the energy consumption simultaneously. Specifically, we propose an energy-efficient, go-directed hierarchical multi-agent deep reinforcement learning (MADRL) method with discrete diffusion models called “ g MADRL-VCS”, to optimize the high-level goal-conditioned navigation policies of UGVs, and the low-level long-term sensing strategies of UAVs. Extensive experimental results on two real-world datasets in Roma, Italy, and Hong Kong SAR, China show that g MADRL-VCS outperforms baselines in terms of energy efficiency, data collection ratio, energy consumption, and UAV-UGV cooperation factor.Keywords
Funding Information
- National Key Research and Development Program of China (2023YFE0209100)
- National Natural Science Foundation of China (U21A20519, U23A20310)
This publication has 35 references indexed in Scilit:
- Air-Ground Spatial Crowdsourcing with UAV Carriers by Geometric Graph Convolutional Multi-Agent Deep Reinforcement Learning2023
- Implementation of Outdoor to Indoor Path Loss Model at 1.8 GHz and 2.1 GHz with a Transmitter Placed on Top of The Building2022
- Distributed Clustering for User Devices Under UAV Coverage Area during Disaster Recovery2021
- Multi-vehicle routing problems with soft time windows: A multi-agent reinforcement learning approachTransportation Research Part C: Emerging Technologies, 2020
- Multi-Task-Oriented Vehicular Crowdsensing: A Deep Learning Approach2020
- Model-free Deep Reinforcement Learning for Urban Autonomous Driving2019
- Propagation Characteristics of Air-to-Air Channels in Urban Environments2018
- What is the best greedy-like heuristic for the weighted set covering problem?Operations Research Letters, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Maximum ratio transmission2003