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

Source: [Safe Aerial 3D Path Planning for Autonomous UAVs using Magnetic Potential Fields](<https://www.sota2.com/research/paper/6a02b4b2dbc836b87d824f98>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-13T05:00:27.562Z

Authors: Haechan Mark Bong, Giovanni Beltrame

Published: 2026-05-11T17:28:26.000Z

## 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).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Path Planning on London White City Offline (held-out scenes)](<https://www.sota2.com/research/sota/path-planning-on-london-white-city-offline-held-out-scenes.md>): Path planning; London White City Offline (held-out scenes); Path Length (m): 59.3.

- [Flight Performance on LA Night City Closed-Loop (held-out scenes)](<https://www.sota2.com/research/sota/flight-performance-on-la-night-city-closed-loop-held-out-scenes.md>): Flight Performance; LA Night City Closed-Loop (held-out scenes); Path Length (m): 109.

- [Flight Performance on London White City Closed-Loop (held-out scenes)](<https://www.sota2.com/research/sota/flight-performance-on-london-white-city-closed-loop-held-out-scenes.md>): Flight Performance; London White City Closed-Loop (held-out scenes); Path Length (m): 74.1.

- [Path Planning on LA Night City held-out scenes (Offline)](<https://www.sota2.com/research/sota/path-planning-on-la-night-city-held-out-scenes-offline.md>): Path planning; LA Night City held-out scenes (Offline); Path Length (m): 58.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.10880>)

[PDF](<https://arxiv.org/pdf/2605.10880.pdf>)