Technical pathways and prospects of digital twin empowerment for agricultural robots

Agricultural robots have been increasingly recognized as the key intelligent equipment for high productivity and quality in sustainable farming. It is often required to integrate environmental perception, autonomous decision-making, and precise execution in a complex field. However, spatiotemporal variations in soil conditions, crop morphology, terrain landscapes, loading, and meteorological factors have introduced substantial uncertainty into robotic perception, decision-making, and control systems, particularly for the open, dynamic, and unstructured scenarios. Agricultural robots can be extended into the crop-robot-environment coupling system. As a result, their intelligent operation is still restricted by incomplete sensing information, insufficient model accuracy, limited adaptability of control strategies, low repeatability of field validation, and weak coordination among robots, tasks, and environments. Digital twin can be expected to provide a promising potential approach for the dynamic connection between physical entities and virtual models, according to real-time data interaction, model updating, and predictive simulation. Virtual representations can be constructed to integrate agricultural robots, operating environments, and task processes. Therefore, digital twins can support state monitoring, process prediction, strategy evaluation, and control optimization, thereby reducing the dependence on costly and time-consuming field trials. In this study, a systematic review was presented on the technical pathways and prospects of digital twins in agricultural robots. Agricultural machinery evolved from conventional equipment to intelligent robotic systems. Agricultural robots were summarized from the perspectives of perception, decision-making, and control systems. Furthermore, the concept, system elements, and functional value of digital twins were analyzed to clarify their applicability to agricultural robotic systems under complex field conditions. Empowerment pathways of digital twins were summarized within a perception-decision-control framework. In perception enhancement, dynamic virtual mapping was realized to integrate digital twins with the robot state data, environmental information, historical data, and mechanisms. Multi-source data fusion, virtual sensing, state reconstruction, and anomaly correction were used to improve the reliability and interpretability of sensing information. In decision optimization, controllable and evaluable virtual environments were provided for process simulation, multi-strategy comparison, intelligent algorithm training, and policy iteration. Path planning, task allocation, parameter matching, and risk avoidance were shifted from experience-based decision-making into prediction and optimization. In control improvement, digital twins were used to connect decision outputs, execution, external disturbances, and control constraints using online updating, disturbance prediction, and adaptive parameter tuning, thereby supporting control compensation, parameter adaptation, and closed-loop optimization. Representative scenarios were then analyzed, including fault and health prediction, autonomous operation, as well as scheduling and coordination. In fault and health prediction, real sensing was integrated with virtual simulation data for the key component and anomaly detection, degradation prediction, and maintenance. In autonomous operation, virtual testing and optimization of motion and operation-control algorithms were adjusted to trajectories, parameters, and execution strategies in agricultural robots, according to field conditions. In scheduling and coordination, field environments, robot fleets, tasks, and environmental constraints were simulated to evaluate scheduling and then optimize task allocation, path coordination, and resource deployment. Digital twins enhanced the role of agricultural robots as information hubs in the production chain. Transition conductions were accelerated from mechanical into data-driven intelligent systems. Finally, the challenges were summarized from the current application of the digital twin. Their future directions were also proposed in agricultural robotics. This finding can contribute to the theoretical and practical guidance of digital twins in agricultural robots.