Continuous World Coverage Path Planning for Fixed-Wing UAVs using Deep Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Theile, Mirco, Rodriguez, Andres R. Zapata, Caccamo, Marco, Sangiovanni-Vincentelli, Alberto L.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913834489348096
author Theile, Mirco
Rodriguez, Andres R. Zapata
Caccamo, Marco
Sangiovanni-Vincentelli, Alberto L.
author_facet Theile, Mirco
Rodriguez, Andres R. Zapata
Caccamo, Marco
Sangiovanni-Vincentelli, Alberto L.
contents Unmanned Aerial Vehicle (UAV) Coverage Path Planning (CPP) is critical for applications such as precision agriculture and search and rescue. While traditional methods rely on discrete grid-based representations, real-world UAV operations require power-efficient continuous motion planning. We formulate the UAV CPP problem in a continuous environment, minimizing power consumption while ensuring complete coverage. Our approach models the environment with variable-size axis-aligned rectangles and UAV motion with curvature-constrained Bézier curves. We train a reinforcement learning agent using an action-mapping-based Soft Actor-Critic (AM-SAC) algorithm employing a self-adaptive curriculum. Experiments on both procedurally generated and hand-crafted scenarios demonstrate the effectiveness of our method in learning energy-efficient coverage strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous World Coverage Path Planning for Fixed-Wing UAVs using Deep Reinforcement Learning
Theile, Mirco
Rodriguez, Andres R. Zapata
Caccamo, Marco
Sangiovanni-Vincentelli, Alberto L.
Robotics
Machine Learning
Systems and Control
Unmanned Aerial Vehicle (UAV) Coverage Path Planning (CPP) is critical for applications such as precision agriculture and search and rescue. While traditional methods rely on discrete grid-based representations, real-world UAV operations require power-efficient continuous motion planning. We formulate the UAV CPP problem in a continuous environment, minimizing power consumption while ensuring complete coverage. Our approach models the environment with variable-size axis-aligned rectangles and UAV motion with curvature-constrained Bézier curves. We train a reinforcement learning agent using an action-mapping-based Soft Actor-Critic (AM-SAC) algorithm employing a self-adaptive curriculum. Experiments on both procedurally generated and hand-crafted scenarios demonstrate the effectiveness of our method in learning energy-efficient coverage strategies.
title Continuous World Coverage Path Planning for Fixed-Wing UAVs using Deep Reinforcement Learning
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2505.08382