Saved in:
Bibliographic Details
Main Authors: Wu, Beining, Ding, Zihao, Ostigaard, Leo, Huang, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.16405
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909998824554496
author Wu, Beining
Ding, Zihao
Ostigaard, Leo
Huang, Jun
author_facet Wu, Beining
Ding, Zihao
Ostigaard, Leo
Huang, Jun
contents Coverage Path Planning (CPP) is a fundamental capability for agricultural robots; however, existing solutions often overlook energy constraints, resulting in incomplete operations in large-scale or resource-limited environments. This paper proposes an energy-aware CPP framework grounded in Soft Actor-Critic (SAC) reinforcement learning, designed for grid-based environments with obstacles and charging stations. To enable robust and adaptive decision-making under energy limitations, the framework integrates Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dynamics. A dedicated reward function is designed to jointly optimize coverage efficiency, energy consumption, and return-to-base constraints. Experimental results demonstrate that the proposed approach consistently achieves over 90% coverage while ensuring energy safety, outperforming traditional heuristic algorithms such as Rapidly-exploring Random Tree (RRT), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) baselines by 13.4-19.5% in coverage and reducing constraint violations by 59.9-88.3%. These findings validate the proposed SAC-based framework as an effective and scalable solution for energy-constrained CPP in agricultural robotics.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reinforcement Learning-Based Energy-Aware Coverage Path Planning for Precision Agriculture
Wu, Beining
Ding, Zihao
Ostigaard, Leo
Huang, Jun
Robotics
Machine Learning
I.2.9; I.2.6; C.4
Coverage Path Planning (CPP) is a fundamental capability for agricultural robots; however, existing solutions often overlook energy constraints, resulting in incomplete operations in large-scale or resource-limited environments. This paper proposes an energy-aware CPP framework grounded in Soft Actor-Critic (SAC) reinforcement learning, designed for grid-based environments with obstacles and charging stations. To enable robust and adaptive decision-making under energy limitations, the framework integrates Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dynamics. A dedicated reward function is designed to jointly optimize coverage efficiency, energy consumption, and return-to-base constraints. Experimental results demonstrate that the proposed approach consistently achieves over 90% coverage while ensuring energy safety, outperforming traditional heuristic algorithms such as Rapidly-exploring Random Tree (RRT), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) baselines by 13.4-19.5% in coverage and reducing constraint violations by 59.9-88.3%. These findings validate the proposed SAC-based framework as an effective and scalable solution for energy-constrained CPP in agricultural robotics.
title Reinforcement Learning-Based Energy-Aware Coverage Path Planning for Precision Agriculture
topic Robotics
Machine Learning
I.2.9; I.2.6; C.4
url https://arxiv.org/abs/2601.16405