The application of intelligent mobile robots in agriculture has emerged as a new research frontier, with the integration of autonomous navigation technology and intelligent agricultural robots being the key to the widespread adoption of smart agricultural machinery. This paper investigates comprehensive coverage path planning for tracked lawnmowers within orchard environments and addresses challenges related to task allocation and battery life. Firstly, in this study, the motion model of the tracked lawnmower was initially simplified based on assumptions about the orchard environment. Force analyses were conducted on each of its motion mechanisms. For the known orchard environment, a grid-based mapping technique was employed to model the orchard environment. Then, in order to improve the algorithm speed and reduce the number of turns during the lawnmower’s traversal, the A* search algorithm was enhanced by combining the method of robot cluster traversal in the orchard environment. Finally, the improved method was simulated and verified in the MATLAB platform to investigate the influence of the number of lawnmower clusters on the path planning in the connected and non-connected orchards. Furthermore, two sets of on-site field trials were meticulously designed to validate the reliability, practicality, and efficacy of the simulation experiments.

In order to meet the needs of intensive mechanized picking in trellised pear orchards, this paper designed a pick-place integrated end-picker based on the analysis of agronomic characteristics of trellised pear gardens and fruit. In order to realize the accurate positioning of pears in picking, based on the kinematic analysis of robot arms and the construction of a private dataset, the YOLOv5s object detection algorithm was used in conjunction with a depth camera to achieve fruit positioning. The hand–eye system calibration was carried out. Aiming at solving the problems of redundancy, inefficiency, and uneven distribution of task volume in the conventional multiple robot arms algorithm, a simulated annealing algorithm was introduced to optimize the picking sequence, and a task allocation method was proposed. On the basis of studying several key parameters affecting the performance of the algorithm, the picking efficiency was greatly optimized. And the effectiveness of the proposed multi-robot collaborative picking method in a trellised pear orchard environment was demonstrated through experiments and simulation verification. The experiments showed that the picking efficiency of the integrated end-picker was increased by about 30%, and the success rate was significantly higher than that of the flexible grippers. The results of this study can be utilized to advance robotic pear-picking research and development.

The torque load spectrum is an important basis for the strength design and durability test verification of tractor power take-off (PTO), and the performance and reliability of tractor PTO directly affect the quality and efficiency of agricultural operations. In this paper, taking the PTO torque load as the object, a PTO loading method based on the dynamic load spectrum acquired in the actual field work was proposed in this paper. Based on the Peak Over Threshold model, the extrapolation of the PTO load spectrum was realized, and the load spectrum throughout the whole life cycle was obtained. On the basis of this, the mobile tractor PTO loading test bench and Fuzzy-Proportional-Integral-Derivative (Fuzzy-PID) controller were developed to achieve the dynamic loading of the PTO load spectrum, and the dynamic characteristics were analyzed and verified by the simulation and laboratory test. The results showed that with the time domain extrapolation method, the load extreme value was expanded from (63.24, 469.50) to (60.88, 475.18), and the coverage was expanded by 1.98%. By comparing with the fitting results, statistical characteristics and rain flow counting results, the load spectrum extrapolation method was effective. In addition, the response time of simulation and laboratory test were 0.05s and 0.75s, respectively; the maximum error was 1.77% and 4.03%, respectively; and the goodness of fit was 16.78 N·m, which indicated that the PTO loading test bench, can accurately restore the dynamic loading of the tractor and the Fuzzy-PID controller had better accuracy and stability. It would provide a reference for the practical application of PTO load spectrum of the tractors.

The accurate recognition of maize growth stages is crucial for effective farmland management strategies. In order to overcome the difficulty of quickly obtaining precise information about maize growth stage in complex farmland scenarios, this study proposes a Maize Hybrid Vision Transformer (MaizeHT) that combines a convolutional algorithmic structure with self-attention for maize growth stage recognition. The MaizeHT model utilizes a ResNet34 convolutional neural network to extract image features to self-attention, which are then transformed into sequence vectors (tokens) using Patch Embedding. It simultaneously inserts category information and location information as a token. A Transformer architecture with multi-head self-attention is employed to extract token features and predict maize growth stage categories using a linear layer. In addition, the MaizeHT model is standardized and encapsulated, and a prototype platform for intelligent maize growth stage recognition is developed for deployment on a website. Finally, the performance validation test of MaizeHT was carried out. To be specific, MaizeHT has an accuracy of 97.71% when the input image resolution is 224 × 224 and 98.71% when the input image resolution is 512 × 512 on the self-built dataset, the number of parameters is 15.446 M, and the floating-point operations are 4.148 G. The proposed maize growth stage recognition method could provide computational support for maize farm intelligence.

The overall safety of a building can be effectively evaluated through regular inspection of the indoor walls by unmanned ground vehicles (UGVs). However, when the UGV performs line patrol inspections according to the specified path, it is easy to be affected by obstacles. This paper presents an obstacle avoidance strategy for unmanned ground vehicles in indoor environments. The proposed method is based on monocular vision. Through the obtained environmental information in front of the unmanned vehicle, the obstacle orientation is determined, and the moving direction and speed of the mobile robot are determined based on the neural network output and confidence. This paper also innovatively adopts the method of collecting indoor environment images based on camera array and realizes the automatic classification of data sets by arranging cameras with different directions and focal lengths. In the training of a transfer neural network, aiming at the problem that it is difficult to set the learning rate factor of the new layer, the improved bat algorithm is used to find the optimal learning rate factor on a small sample data set. The simulation results show that the accuracy can reach 94.84%. Single-frame evaluation and continuous obstacle avoidance evaluation are used to verify the effectiveness of the obstacle avoidance algorithm. The experimental results show that an unmanned wheeled robot with a bionic transfer-convolution neural network as the control command output can realize autonomous obstacle avoidance in complex indoor scenes.

Steering control is vital for hillside tractors, and four-wheel-steering technology significantly enhances stability and flexibility. However, existing methods often overlook the slope–stability relationship. In order to address this issue, considering the impact of tractor wheels on the steering characteristics, a nonlinear three-degree-of-freedom dynamic model based on the basic requirements within a 15° range of slope angles was derived. Subsequently, a four-wheel steering control strategy for hillside tractors was designed based on this model, incorporating a fuzzy PID control algorithm. The dynamics model was validated on the high-fidelity Carsim/Simulink co-simulation platform, and relevant experiments were conducted in Matlab/Simulink. Results showed that fuzzy PID control reduced the yaw rate’s average settling time from 0.36 s to 0.1 s and the response value from 0.28 rad/s to 0.038 rad/s. In addition, the lateral velocity and sideslip angle responses closely matched ideal values. Thus, the tractor with four-wheel steering under fuzzy PID control exhibited improved wheel angle flexibility and higher tracking accuracy. Finally, hardware-in-the-loop-experiments were conducted, confirming the algorithm’s effectiveness in ensuring stability and meeting the requirements of semi-physical simulation scenarios. This research provides a foundation for potential applications in tractor manufacturing to improve control performance on hilly terrains.