Skip to content
Open access

Risk-Aware Mixed Prioritized Experience Replay for Cooperative Path Planning of UAV Swarms in Complex Dynamic Airspace

2026 · Computers, Materials & Continua · 0 citations · 26 references

TL;DR

Training results show that MPER-MASAC maintains the highest mean reward in the later stage among Multi-Agent Deep Deterministic Policy Gradient, MASAC, and MPER-MASAC, and the effectiveness of the proposed risk-aware mixed prioritized experience replay mechanism in improving task execution performance in the evaluated complex dynamic airspace.

Abstract

: Cooperative path planning for unmanned aerial vehicle (UAV) swarms is a key technique for achieving safe target reaching, dynamic obstacle avoidance, and stable formation maintenance, particularly in complex dynamic airspace. Existing methods often rely on global environmental information or simplified obstacle models, and they are susceptible to interference from low-value experience samples in partially observable scenarios with coupled multiple obstacles, thereby reducing policy learning efficiency and task execution performance. To address these issues, this paper proposes a Multi-Agent Soft Actor-Critic (MASAC) algorithm based on Mixed Prioritized Experience Replay (MPER), termed MPER-MASAC. First, a complex dynamic airspace containing static obstacles, target-region circular moving obstacles, and obstacles in uniform linear motion is constructed, and the cooperative path planning problem for UAV swarms is formulated as a partially observable Markov decision process. Second, under a centralized training and decentralized execution framework, a leader–follower cooperative structure is adopted, and a mixed reward mechanism is designed to jointly guide target reaching, dynamic obstacle avoidance, and formation maintenance. Furthermore, temporal-difference (TD) error and obstacle-related geometric distance variation are jointly incorporated into sample priority calculation, enabling experiences with larger TD errors or stronger geometric risk trends to be replayed preferentially. This mechanism enhances the learning ability of the algorithm in key decision-making scenarios, such as near-obstacle interaction, cooperative obstacle avoidance, and formation adjustment. Training results show that MPER-MASAC maintains the highest mean reward in the later stage among Multi-Agent Deep Deterministic Policy Gradient (MADDPG), MASAC, and MPER-MASAC. In Monte Carlo testing, MPER-MASAC achieves a task success rate of 73.00%, a formation keeping rate of 70.23%, and a mean flight path length of 159 m; the corresponding values are 56.60%, 47.36%, and 192 m for MADDPG, 60.00%, 51.14%, and 185 m for MASAC, and 66.00%, 62.26%, and 165 m for Prioritized Experience Replay-based MASAC (PERMASAC). These results support the effectiveness of the proposed risk-aware mixed prioritized experience replay mechanism in improving task execution performance in the evaluated complex dynamic airspace.

Read PDF

Similar papers

Sep 2026

A Multi-UAV Cooperative Navigation Method Based on Policy Decomposition Structure

Simulation results demonstrate that, compared to traditional methods, GS-MADDPG improves the navigation success rate, robustness, and generalization performance, and verifies its effectiveness in multi-UAV cooperative navigation for search and rescue tasks.

Li Tan, Hai-Xia Zhao, Jia-Qin Chai et al. · 0 citations
#reinforcement learning Open access Oct 2026

Globally guided multi-agent reinforcement learning with decoupled critics for cooperative UAV path planning

Cooperative path planning for multiple unmanned aerial vehicles (UAVs) requires the simultaneous achievement of target navigation, collision avoidance, and formation coordination in complex obstacle environments. Existing multi-agent reinforcement learning methods often suffer from sparse rewards, local deadlocks,...

Xu Wang, Qi Liu, Hao-Tian Li · 0 citations
Open access Sep 2026

Group-Level Heterogeneous Reinforcement-Learning-Guided Jellyfish Search Optimization for Cooperative Multi-UAV Path Planning Under Dynamic and Adversarial Conditions

Cooperative multi-UAV path planning must produce coupled trajectories that respect inter-UAV separation constraints through environments with moving obstacles, wind, GPS jamming, and communication loss. Population-based metaheuristics handle the resulting nonconvex, dynamic objectives well, and reinforcement-learning (...

Nader Alotaibi, Wojdan Binsaeedan · 0 citations
Conference Open access Sep 2026

Dynamic Resource Scheduling for UAV Systems in Multi-Scenario Tasks Based on MADDPG Algorithm

Unmanned Aerial Vehicle (UAV) systems face critical resource scheduling challenges in multi-scenario tasks such as disaster rescue, logistics delivery, and facility inspection. Traditional static scheduling methods fail to accommodate dynamic resource demands and real-time priority adjustments. This paper proposes a dy...

Ran-Xin Yang, Ying-Wei Xiao, Jin-Hua Sun et al. · 0 citations
Open access Oct 2026

HEA-Planner: A Hierarchical Environment-Aware Trajectory Planning Framework for Autonomous UAV Landing on Moving Platforms in Confined Dynamic Warehouse Environments

Autonomous quadrotor landing on moving ground platforms is essential for cooperative air–ground operations in confined warehouse environments. However, existing trajectory planners often compromise corridor clearance in narrow aisles or fail to track maneuvering platforms under dynamic intrusions. To address these chal...

Xing Wu, Feng-Yang Qiu, Jun-Zhe Chen et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.