Artificial Intelligence and Autonomous Agricultural Robots: Path Planning, Task Scheduling, and Intelligent Decision-Making

Agricultural robots have gradually evolved from traditional mechanized equipment into intelligent autonomous systems that integrate perception, positioning, navigation, operation, interaction, and decision-making. Technologies such as machine vision, deep learning, reinforcement learning, sensor fusion, intelligent optimization, multi-robot coordination, and edge computing are increasingly being applied to agricultural scenarios, enabling robots to demonstrate significant potential in tasks such as crop identification, path tracking, precision spraying, fruit harvesting, field transportation, environmental monitoring, and operation management.However, compared to structured environments such as industrial manufacturing and warehousing logistics, agricultural environments are far more complex and unpredictable. Scenarios such as farmlands, orchards, greenhouses, and hilly or mountainous areas typically present challenges including uneven terrain, severe crop obstruction, highly variable lighting conditions, unpredictable obstacle distribution, unstable communication conditions, and biological variability in the objects being handled. These factors significantly increase the difficulty of autonomous operation for agricultural robots and place higher demands on path planning, task scheduling, and intelligent decision-making methods. Therefore, it is necessary to conduct systematic thematic discussions on artificial intelligence and autonomous agricultural robots to promote the deep integration of theoretical innovation, technological breakthroughs, and engineering applications.This research topic aims to bring together the latest research advances in the fields of artificial intelligence and autonomous agricultural robots, with a focus on core scientific issues and key technologies such as path planning, task scheduling, and intelligent decision-making. The research topic seeks to explore how artificial intelligence methods—including machine learning, deep learning, reinforcement learning, swarm intelligence optimization, multi-objective optimization, large-scale models, multi-sensor fusion, digital twins, and cloud-edge-device collaboration—can enhance the autonomy, adaptability, robustness, and operational efficiency of agricultural robots in complex agricultural scenarios.This research topic focuses on the theoretical methods, key technologies, system integration, and agricultural applications of AI-enabled autonomous agricultural robot systems. The scope of submissions includes, but is not limited to:1. Environmental perception, semantic understanding, object recognition, and multi-source information fusion in agricultural robots;2. Localization, navigation, path planning, coverage planning, and motion control for autonomous agricultural robots;3. Agricultural task modeling, task allocation, resource scheduling, operation optimization, and multi-objective decision-making;4. Applications of machine learning, deep learning, reinforcement learning, swarm intelligence optimization, large-scale models, and hybrid intelligence methods in agricultural robots;5. Collaborative operations among multiple agricultural robots, swarm control, human-robot collaboration, and cloud-edge-device cooperative control;6. Digital twins, simulation testing, dataset construction, benchmarking, and system validation for agricultural robots;7. Safety, Reliability, Explainability, Fault Diagnosis, and Risk Assessment of Agricultural Robots;8. System Design, Field Trials, and Engineering Applications for Scenarios Including Tillage, Crop Protection, Harvesting, Transportation, Inspection, Monitoring, Phenotyping, and Precision Management. Topic editors: Liwei Yang, Li Li, KUNDAN KUMAR Source: https://www.frontiersin.org/research-topics/82514/artificial-intelligence-and-autonomous-agricultural-robots-path-planning-task-scheduling-and-intelligent-decision-making