Home // SIMUL 2025, The Seventeenth International Conference on Advances in System Modeling and Simulation // View article

Advanced Simulation Framework for UAV Path Planning Integrating Monte Carlo Prediction and MAPPO

Authors:
Yingying Gao
Qingqing Yang
Jing Xu
Pengcheng Yang

Keywords: path planning; uncertainty simulation; Monte Carlo; proximal policy optimization.

Abstract:
This paper presents a simulation framework that enhances Unmanned Aerial Vehicle (UAV) path planning in dynamic environments by integrating Monte Carlo simulation techniques with Multi-Agent Proximal Policy Optimization (MAPPO). Our framework addresses three key challenges in UAV operations: (1) uncertainty in target movement due to complex environmental factors, (2) the computational complexity of navigating large operational spaces, and (3) coordination for multi-UAV systems in constrained environments. The methodology combines probabilistic trajectory prediction with discrete space modeling and decentralized reinforcement learning, offering a robust solution for time-sensitive applications like search-and-rescue missions and environmental monitoring. Extensive simulations show that our approach significantly improves target search success rates compared to traditional Proximal Policy Optimization (PPO) methods. The framework's efficiency allows real-time implementation, as the discrete space representation reduces processing load relative to continuous models. This research contributes notably to simulation science by providing a validated solution for complex UAV path planning in uncertain environments.

Pages: 67 to 68

Copyright: Copyright (c) IARIA, 2025

Publication date: September 28, 2025

Published in: conference

ISSN: 2308-4537

ISBN: 978-1-68558-300-2

Location: Lisbon, Portugal

Dates: from September 28, 2025 to October 2, 2025