WONDER: A Radio World Model-based Negotiation Framework for Multi-Agent UAV Coverage Optimization

Jiahao Huang; Rongpeng Li; Zhifeng Zhao; Guoru Ding; Honggang Zhang

cs.MAAug 16, 2026

WONDER: A Radio World Model-based Negotiation Framework for Multi-Agent UAV Coverage Optimization

Authors: Jiahao Huang, Rongpeng Li, Zhifeng Zhao, Guoru Ding, Honggang Zhang

Organizations: Zhejiang University, Hangzhou 310027, China · Zhejiang Lab, Hangzhou 310012, China · College of Communications and Engineering, Army Engineering University of PLA, Nanjing 210007, China · Macau University of Science and Technology, Macau, China

Abstract

Post-disaster damage to terrestrial infrastructure can disrupt wireless coverage,while Uncrewed Aerial Vehicle (UAV) swarms provide a promising solution for rapid restoration.However, due to the limitations in local geometry observations hidden radio impact,and inter-UAV communication,there exists a significant gap between locally visible movement choices and swarm-level coverage outcomes.To combat this gap,we propose a raido World-model-based Optimized Negotiation framework for Distributed UAV covERage (WONDER).Particularly, to tackle the unavailability of the future radio field from onboard observations, WONDER uses a Joint-Embedding Predictive Architecture (JEPA)-based radio world model to learn and predict the incremental radio effect of each candidate trajectory from deployment-available information.Multi-round negotiation in WONDER then coordinates ranked proposals by committing one trajectory at a time and re-evaluating the remaining proposals under the updated context. Our theoretical analyses further validate the effectiveness of such a world model-based framework. WONDER also adopts a Proximal Policy Optimization (PPO)-style Actor and alternates between updating the world model and the actor. Furthermore,we build RadioDynamics,a comprehensive simulation environment that integrates UAV mobility,radio propagation, inter-UAV communication modeling,and digital-twin geometry with ray-traced fields in $62$ metropolitan scenes.Experiments on $11$ testing scenes in RadioDynamics show that WONDER achieves the highest balanced score among seven evaluated methods,reaching $0.870$ with a $0.162$ coverage advantage over STACCA, while maintaining $100\%$ connectivity between UAVs.

Figures & tables

Representative Studies	UAV Swarm Coverage	Radio-Aware Evaluation	Predictive World Model	Sparse Communication	Long-Range Coordination	Trajectory Negotiation
UAV access and emergency relay [ 3 , 2 , 4 , 10 , 11 , 5 ]
Multi-UAV coverage control [ 12 , 9 , 13 , 14 ]
Radio-aware deployment and radio maps [ 6 , 15 , 16 ]
World models and action-sufficient representations [ 17 , 18 , 19 , 20 , 21 , 22 ]
Networked MARL and long-range critics [ 23 , 24 , 25 , 26 ]
Learned communication [ 27 , 28 , 29 , 30 , 31 ]

TABLE I: A key summary of the key differences between WONDER and the literature.

Fig. 1: RadioDynamics setting for deployable UAV-swarm coverage. The upper flow constructs the radio environment from digital-twin geometry, UAV mobility, and ray-traced Reference Signal Received Power (RSRP) fields. The lower flow contrasts deployment-visible local geometry and constrained multi-hop communication with a full-information reference view. The marked asymmetries highlight the gaps between visible geometry and hidden radio impact, and between sparse local communication and swarm-level coverage objectives.

Symbol	Meaning
System and deployment information
$\mathbb{N},N$	UAV set and number of UAVs.
$\mathbf{p}_{i,t}$	Position of UAV $i$ at deployment step $t$ .
$\mathbb{H}_{t},\mathbb{N}_{l}$	A2A communication graph and one subgraph.
$\mathbb{N}^{\mathrm{nbr}}_{i}$	One-hop neighbor set of UAV $i$ .
$o^{\mathrm{loc}}_{i}$	Deployment-visible local observation of UAV $i$ .

TABLE II: Main notations used in the methodology.

Fig. 2: Visualization of flocking warm-up prefix, with $N_{\mathrm{warm}}=15$ . In each panel, blue markers denote UAV positions, orange segments denote feasible inter-UAV communication links, and the red circle in the upper left denotes the terminal backhaul range; UAVs outside this range depend on multi-hop UAV relaying for backhaul connectivity. dark-gray regions indicate building footprints, and the red – green heat map encodes RSRP strength.

Fig. 3: Loss curve and return curve of STACCA in RadioDynamics.

Fig. 4: Empirical evidence for counterfactual composition gap and sequential-plan gains in RadioDynamics. Both experiments are implemented across $51$ train and validation scenes. Left: pairwise $\mathcal{G}^{\mathrm{CF}}(\mathbb{N};\mathbb{T}^{\mathrm{base}})$ measured from $3,726$ active UAV pairs, comparing synchronized two-UAV counterfactual estimates with the impact of parallel execution. Right: the incremental balanced score of $\mathbb{T}^{\mathrm{seq}}_{r}$ over $\mathbb{T}^{\parallel}$ increases with the negotiation round $r$ ; the shaded region denotes the $95\%$ confidence interval.

Fig. 5: Architecture of WONDER. The upper panel shows the deployment-time inference pipeline at a synchronization time step, including candidate trajectory generation, one-hop aggregation, subgraph reduction, multi-hop relay, global election, and trajectory commitment. The lower panel shows the three-stage training pipeline for the JEPA world model and election actor. Orange blocks denote modules used at deployment, and yellow blocks denote modules used only during training.

Fig. 6: Visualization of RadioDynamics closed-loop rollouts. Panels are recorded every five timesteps; the red time axis aligns the panels with rollout time, and the bottom curve reports the corresponding balanced score. The first to third rows show rollouts controlled by Flocking, STACCA, and WONDER, respectively.

Description	Notation	Value
Ground service area	$\diagup$	$700\times 700$ m 2
Ground grid	$\diagup$	$350\times 350$
Cell resolution	$\diagup$	$2$ m
A2G bandwidth	$B$	$100$ MHz [ 41 ]
A2A carrier frequency	$f_{c}$	$3.5$ GHz [ 36 ]
A2A transmit power	$P_{i}^{\mathrm{A2A}}$	$23$ dBm

TABLE III: Simulation and benchmark parameters.

Description	Notation	Value
Candidate proposal per reduction	$K_{\text{c}}$	$3$
Relay-depth bound	$\mathcal{K}_{\text{dep}}$	$2$ hops
Negotiation-round limit	$R$	$3$
JEPA continuity constants	$\tau_{\mathrm{coh}},\varepsilon_{\mathrm{z}}$	$(0.25,10^{-8})$
Connectivity penalty	$\lambda_{\mathrm{c}}$	$1.0$
PPO constants	$\begin{gathered}\epsilon_{\mathrm{clip}},c_{\mathrm{v}},c_{\mathrm{e}}\end{gathered}$	$(0.2,0.5,0.01)$

TABLE IV: Training parameters.

Fig. 7: Closed-loop performance under the shared RadioDynamics evaluation. Fair baselines are shown in blue , WONDER in red , and Exhausted references in gray . The balanced score summarizes the normalized metric vector.

Fig. 8: Representative cases where our method outperforms Sequential Exhausted. Sequential Exhausted visits UAVs in a fixed order and greedily commits each visited UAV’s locally best action. The gray actions yield marginal gain, while the yellow actions would produce higher global gain if committed earlier. Our method prioritizes the yellow actions through proposal-level negotiation, avoiding the local optimum induced by fixed-order greedy selection.

Entry	Scope	No. of Messages	Payload (kbit)
STACCA [ 26 ]	Local vectors	$120$	$122.88$
MAGI [ 28 ]	Neighborhood Message	$120$	$245.76$
WONDER	Local + proposal	$264$	$270.336$
Full Connection	Full Radio Map (raw)	$120$	$470400$

TABLE V: Payload upper bounds for message exchange.

Fig. 9: Training curves for JEPA and DR local proposal models.

Fig. 10: Offline recall of retained proposals for JEPA and DR.

Fig. 11: Training curve of the election policy.

Method	Coverage Area (%)	Mean Rate (Mbps)	5% Edge Rate (Mbps)	SINR Coverage (%)	Mean Interference (%)	Jain Fairness (%)	Connectivity (%)	Balanced Score
w/o JEPA Encoder	43.1	300.8	0.00357	38.5	0.98	29.8	66.5	0.659
w/o Election Module	44.5	322.2	0.00381	41.0	0.94	31.7	68.4	0.708
w/o Alternating update	49.4	353.2	0.00420	45.0	0.85	35.0	75.7	0.808
w/o Multi-Round Negotiation	48.3	343.3	0.00408	44.5	0.87	34.1	74.0	0.784
Our full method	52.2	362.5	0.00400	47.5	0.89	33.4	100.0	0.870

TABLE VI: Ablation analysis of the main WONDER components under the shared evaluation setting.

Coverage Path Planning

Coverage path planning designs robot routes that systematically survey or act across an area or surface while limiting missed regions, overlap, and travel cost.

See all 21 papers

Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment
Mar 17, 2026Enguang Fan, Yifan Chen, Zihan Shan +3Cooperative MARL Decentralized MARL
University of Illinois at Urbana-Champaign · Boeing Research and Technology
Predictive Lightweight MARL for Resilient Coverage in Sparse-Signaling Aerial Networks
Jul 24, 2026Chuan-Chi Lai, Ang-Hsun TsaiSequential MARL Multi-Agent Control
Department of Communications Engineering, National Chung Cheng University, Minxiong Township, Chiayi County 621301, Taiwan · Advanced Institute of Manufacturing with High-tech Innovations (AIM-HI), National Chung Cheng University, Minxiong Township, Chiayi County 621301, Taiwan · Department of Communications Engineering, Feng Chia University, Taichung 407102, Taiwan
LAEI: Layered Autonomous Edge Intelligence Framework for Robust UAV Swarm Operations
Jun 8, 2026Changmin Park, Wooyong Jung, Hwangnam KimAerial Robotics Swarm Robotics
School of Electrical Engineering Korea University Seoul 02841, Korea

Mar 17, 2026J/K move · Enter open · S save

Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment

Enguang Fan, Yifan Chen, Zihan Shan, Klara Nahrstedt+2

University of Illinois at Urbana-Champaign · Boeing Research and Technology

Cooperative MARL Decentralized MARL Multi-Agent Communication Partially Observable RL

Open paper AskPDF arXiv

Autonomous Unmanned Aerial Vehicle (UAV) swarms are increasingly used as rapidly deployable aerial relays and sensing platforms, yet practical deployments must operate under partial observability and intermittent peer-to-peer connectivity. We present a graph-based multi-agent reinforcement learning framework trained under centralized training with decentralized execution (CTDE): a centralized critic and global state are available only during training, while each UAV executes a shared policy using local observations and messages from nearby neighbors. Under restricted communication, neighbor relations are induced by an SNR-threshold connectivity graph. Our architecture encodes local agent state and nearby entities with an agent-entity attention module and aggregates inter-UAV messages with neighbor self-attention over a signal-quality-limited communication graph defined by a channel model. We evaluate the framework on a cooperative relay-deployment task, DroneConnect. Experimental results show that the proposed method achieves an approximately 12% increase in target coverage over MAPPO under restricted communication and partial observability, while remaining competitive with a mixed-integer linear programming (MILP)-based offline upper bound with full node observability.

Abstract

Coverage Path Planning

Explore similar work

Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment

Predictive Lightweight MARL for Resilient Coverage in Sparse-Signaling Aerial Networks

LAEI: Layered Autonomous Edge Intelligence Framework for Robust UAV Swarm Operations