Reinforcement Learning-Based Energy-Aware Coverage Path Planning for Precision Agriculture

2025-11-16

Research in Adaptive and Convergent Systems

AI Summary

This work proposes an energy-aware reinforcement learning framework for coverage path planning in agricultural robotics, addressing the frequent task failures caused by neglecting energy constraints. The approach uniquely integrates Soft Actor-Critic (SAC) with a CNN-LSTM architecture, where the CNN extracts spatial environmental features and the LSTM models temporal dynamics. A multi-objective reward function is designed to jointly optimize coverage rate, energy consumption, and return-to-charging constraints. Evaluated in grid environments with obstacles and charging stations, the method achieves over 90% coverage—outperforming baseline algorithms such as RRT, PSO, and ACO by 13.4–19.5%—while reducing constraint violation rates by 59.9–88.3%. These results demonstrate a significant improvement in both energy-safe coverage efficiency and environmental adaptability.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

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.

Problem

• Coverage Path Planning
• Energy Constraints
• Precision Agriculture
• Agricultural Robotics
• Reinforcement Learning

Innovation

• Soft Actor-Critic
• Energy-aware Coverage Path Planning
• CNN-LSTM integration
• Reinforcement Learning
• Agricultural Robotics