A Physics-Informed Neural Network Approach for UAV Path Planning in Dynamic Environments

TL;DR

This paper introduces a physics-informed neural network framework for UAV path planning in dynamic environments, enabling the generation of safe, smooth, and energy-efficient trajectories that incorporate physical and environmental constraints without supervised data.

Contribution

It presents a novel PINN-based approach that embeds UAV dynamics and environmental factors directly into the learning process, outperforming traditional planning methods in key metrics.

Findings

Outperforms A* and Kino-RRT* in energy and safety margins

Produces smoother and more physically feasible trajectories

Maintains similar flight efficiency to traditional methods

Abstract

Unmanned aerial vehicles (UAVs) operating in dynamic wind fields must generate safe and energy-efficient trajectories under physical and environmental constraints. Traditional planners, such as A* and kinodynamic RRT*, often yield suboptimal or non-smooth paths due to discretization and sampling limitations. This paper presents a physics-informed neural network (PINN) framework that embeds UAV dynamics, wind disturbances, and obstacle avoidance directly into the learning process. Without requiring supervised data, the PINN learns dynamically feasible and collision-free trajectories by minimizing physical residuals and risk-aware objectives. Comparative simulations show that the proposed method outperforms A* and Kino-RRT* in control energy, smoothness, and safety margin, while maintaining similar flight efficiency. The results highlight the potential of physics-informed learning to unify model-based and data-driven planning, providing a scalable and physically consistent framework for UAV trajectory optimization.