Safe Aerial 3D Path Planning for Autonomous UAVs using Magnetic Potential Fields

2026-05-11

AI Summary

This work addresses the challenge of real-time 3D collision-free path planning for autonomous drones in urban environments, where conventional methods often suffer from local minima. The authors extend MaxConvNet—a Maxwell-equation-inspired magnetic potential field approach—into three dimensions for the first time. By employing a convolutional autoencoder to predict obstacle-aware potential fields from 101³ LiDAR-derived voxel grids, the method integrates physics-inspired modeling with deep learning, enabling cross-scenario generalization without retraining and completely eliminating local minima. Experimental results demonstrate 100% planning success in two complex urban scenarios, achieving speedups of 1.7–1.95× over A* and approximately 193–201× over RRT*(3k), while maintaining comparable path quality.

Abstract

Safe autonomous Uncrewed Aerial Vehicle (UAV) navigation in urban environments requires real-time path planning that avoids obstacles. MaxConvNet is a potential-field planner that leverages properties of Maxwell's equations to generate a path to the goal without local minima. We extend the 2D MaxConvNet magnetic field planner to 3D, using a convolutional autoencoder to predict obstacle-aware potential fields from LiDAR-derived 101^3 voxel grids. Evaluation across 100 randomized closed-loop trials in two distinct Cosys-AirSim urban environments, a dense night-time cityscape and a suburban district shows a 100% path planning success rate on both maps without retraining. In offline path planning, 3DMaxConvNet produces path lengths comparable to A* on unseen maps while reducing runtime from 0.155--0.17s to 0.087--0.089s, or about 1.7--1.95 times faster than A*. Against RRT*(3k), 3DMaxConvNet achieves similar path quality while reducing planning runtime from 17.2--17.5s to about 0.09s, which is roughly 193--201 times faster than RRT*(3k).

Problem

• 3D path planning
• autonomous UAVs
• obstacle avoidance
• urban environments
• real-time navigation

Innovation

• 3D path planning
• magnetic potential fields
• convolutional autoencoder
• real-time obstacle avoidance
• UAV navigation