Yaxin Ren

Introduction: Autonomous navigation of crawler tractors is essential for precision agriculture; however, existing systems often face a trade-off between path-tracking accuracy and steering stability, particularly under complex field conditions. To address this limitation, this study aimed to develop an autonomous driving system for single-HST (Hydrostatic Transmission) crawler tractors that enhances both control resolution and operational reliability. Methods: A kinematic model of the single-HST crawler chassis was established, and a state-feedback path-tracking controller integrating lateral and heading deviations was proposed. A pulse-width modulation (PWM)-based multi-modal steering control strategy was designed to enable intelligent switching and smooth transition between differential steering and unilateral braking steering by dynamically adjusting the steering hydraulic cylinder stroke. A three-layer hardware and software architecture—comprising perception, decision-making, and execution layers—was constructed, and an embedded vehicle controller integrating path planning and real-time control was developed. Field tests were conducted at the China National Precision Agriculture Research Demonstration Base, including fixed-curvature path tracking and reciprocating autonomous operation trials. Results: Under curve path-tracking conditions, the proposed multi-modal steering control achieved an average lateral deviation of 4.25 cm, with a standard deviation below 5.0 cm, representing a 34.4% reduction compared with unilateral braking steering. In reciprocating operations, the average inter-row spacing error was 6.04 cm, satisfying the precision requirements for agricultural machinery under both field soil and cement pavement conditions. Discussion: The results demonstrate that the proposed system effectively balances tracking accuracy and steering stability in autonomous crawler tractor navigation. The multi-modal steering strategy offers a practical solution for agricultural machinery operating on varied surfaces and shows strong potential for broader application in precision farming systems with similar terrain conditions.

Accurate heading estimation is crucial for the autonomous navigation of small-to-medium tractors. While dual-antenna GNSS systems offer precision, they face installation and safety challenges. Single-antenna GNSS integrated with a low-cost Strapdown Inertial Navigation System (SINS) presents a more adaptable solution but suffers from slow convergence and low accuracy of heading estimation in low-speed farmland operations. This study proposes an adaptive trajectory-constrained heading estimation method. A sliding-window adaptive extended Kalman filter (SWAEKF) was developed, incorporating a heading constraint model that utilizes the GNSS-derived trajectory angle. An enhanced Sage–Husa algorithm was employed for the adaptive estimation of the trajectory angle measurement variance. Furthermore, a covariance initialization strategy based on the variance of trajectory angle increments was implemented to accelerate convergence. Field tests demonstrated that the proposed method achieved rapid heading convergence (less than 10 s for straight lines and 14 s for curves) and high accuracy (RMS heading error below 0.15° for straight-line tracking and 0.25° for curved paths). Compared to a conventional adaptive EKF, the SWAEKF improved accuracy by 23% and reduced convergence time by 62%. The proposed algorithm effectively enhances the performance of GNSS/SINS integrated navigation for tractors in low-dynamic environments, meeting the requirements for autonomous navigation systems.

Accurate panicle identification is a key step in rice-field phenotyping. Deep learning methods based on high-spatial-resolution images provide a high-throughput and accurate solution of panicle segmentation. Panicle segmentation tasks require costly annotations to train an accurate and robust deep learning model. However, few public datasets are available for rice-panicle phenotyping. We present a semi-supervised deep learning model training process, which greatly assists the annotation and refinement of training datasets. The model learns the panicle features with limited annotations and localizes more positive samples in the datasets, without further interaction. After the dataset refinement, the number of annotations increased by 40.6%. In addition, we trained and tested modern deep learning models to show how the dataset is beneficial to both detection and segmentation tasks. Results of our comparison experiments can inspire others in dataset preparation and model selection.

This paper presents a farm management information system targeting improvements in the ease of use and sustainability of robot farming systems. The system integrates the functionalities of field survey, path planning, monitoring, and controlling agricultural vehicles in real time. Firstly, a Grabcut-based semi-supervised field registration method is proposed for arable field detection from the orthoimage taken by the drone with an RGB camera. It partitions a complex field into simple geometric entities with simple user interaction. The average Mean Intersection over Union is about 0.95 when the field size ranges from 2.74 ha to 5.06 ha. In addition, a desktop software and a web application are developed as the entity of an FMIS. Compared to existing FMISs, this system provides more advanced features in robot farming, while providing simpler user interaction and better results. It allows clients to invoke web services and receive responses independent of programming language and platforms. Moreover, the system is compatible with other services, users, and devices following the open-source access protocol. We have evaluated the system by controlling 5 robot tractors with a 2 Hz communication frequency. The communication protocols will be publicly available to protentional users.