Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controller

2026-07-28

AI Summary

This work addresses the challenge of cooperative navigation and collision avoidance for multiple unmanned aerial vehicles (UAVs) in complex indoor environments under GNSS-denied conditions. The proposed framework, termed “world-coordinate fusion, ego-coordinate execution,” employs a shared voxel map to unify spatial representation across agents, fuses 360° LiDAR observations from multiple UAVs into local bird’s-eye-view maps, and leverages a multi-agent Soft Actor-Critic algorithm for decentralized continuous control. Operating within a centralized training and decentralized execution paradigm, the system enables scalable and consistent collaborative navigation, further enhanced by offline imitation fine-tuning to improve policy robustness. In simulations, the approach achieves a 90.3% success rate in corridor navigation, significantly outperforming A* and potential field methods; real-world experiments demonstrate successful stable traversal of complex obstacle layouts by two UAVs.

Abstract

This paper presents a cooperative indoor UAV guidance framework that combines a shared voxel-map world model with a multi-agent Soft Actor-Critic (MASAC) controller. Multiple drones fuse 360 LiDAR observations into a common world-frame occupancy map, which is converted into a compact bird's-eye-view (BEV) representation and provided to each agent as an ego-aligned local crop. This integrate-in-world, act-in- ego design enables consistent multi-UAV spatial fusion whilst retaining decentralised continuous control. The policy combines BEV map features, near-field obstacle observations, and compact goal and peer-state information within a centralised-training, decentralised-execution framework. In simulation, the learned controller achieves a 90.3% success rate in corridor navigation, outperforming Astar planning, an artificial potential field controller, and a prior guidance method. To address residual sim-to-real mismatch, the simulation-trained policy is further adapted using offline imitation fine-tuning from real-world data. Real-world experiments in GNSS-denied indoor environments demonstrate stable two-UAV cooperative operation across increasingly chal- lenging obstacle layouts. The results show that shared voxel-map representations provide an effective and scalable spatial substrate for learned cooperative indoor UAV guidance.

Problem

• cooperative UAV guidance
• indoor navigation
• multi-agent coordination
• GNSS-denied environment
• obstacle avoidance

Innovation

• shared voxel-map
• multi-agent Soft Actor-Critic
• bird's-eye-view representation
• integrate-in-world act-in-ego
• offline imitation fine-tuning