China’s Guizhou is a typical karst landscape province with high production of chili pepper, but it is mostly planted in mountainous areas, while manual harvesting of chili pepper has the deficiencies of high labor intensity, low efficiency, and high labor cost; in addition, there is no harvesting machinery applicable to the dense planting pattern of the chili pepper in mountainous areas in China. The fully hydraulic mountain track-based self-propelled pepper harvester 4JZ-1.0A is designed to solve the above problems. The pepper harvester spiral comb picking head is an important part of the whole machine design, the design of the hydraulic system of the working circuit of the picking head is the key to realizing the hydraulic control part of the whole system. In this paper, the working principle diagram of the improved load-sensitive hydraulic system is designed and analyzed for the study of whether the working circuit of the pepper picking head of the pepper machine can meet the requirements of mountain operation, taking the working circuit of the mountain pepper harvester as the research object. In addition, the load-sensitive pump model and the simulation model of the whole working circuit are established by the AMESim platform 2019.2 (Siemens simcenter amesim). The operating performance of the system under variable flow conditions, variable load conditions, and an improved sensitive system is analyzed. The simulation results show that the improved load-sensitive system can effectively reduce the oscillation and cavitation during cylinder operation and improve the system efficiency and the performance and service life of the components. The performance of the hydraulic system of the working circuit of the mountain pepper harvester was verified in the test, meeting the requirements of working use. This provides a theoretical basis for the improvement and optimal design of a mountain pepper harvester hydraulic system.

To address the problem of system instability during vehicle low-speed driving, we propose improving the visual odometer using ORB (Oriented FAST and Rotated BRIEF) features. The homogeneity of ORB features leads to poor corner point properties of some feature points. When the environmental texture lacks richness, it leads to poor matching performance and low matching accuracy of the feature points. We solve the problem of the corner point properties of feature points using weight calculation for regions with different textures. When the vehicle speed is too low, the continuous frames captured by the camera will overlap significantly, causing large fluctuations in the system error. We use motion model estimation to solve this problem. Meanwhile, experimental validation using the KITTI dataset achieves good results.

ORB (Oriented FAST and Rotated Brief) features are the most commonly used features in visual SLAM and visual odometry that have high computational speed, and rotation scale invariance. However, due to the homogenization of ORB features, the corner properties of specific features are poor in some artificial environments, and it can lead to poor matching performance when the environmental texture is not rich. The underlying reason is that the pixel grayscale changes in the less-richly textured regions on the image are not obvious, leading to a certain degree of mis-matching in the matching process. At the same time, when the camera motion speed is low, there is much overlap between adjacent frames. This results in minimal or almost no changes in the projection of feature points, and the system is highly sensitive to errors, In this case, even small errors can cause significant fluctuations in the calculation results. In response to the above issues, an improved feature point method for stereo vision mileage calculation is proposed to solve the problem of system stability deterioration when cameras move at low speeds in artificial envi-ronments. Firstly, weight calculation based on different texture regions is used to solve the problem of low corner properties of feature points caused by environmental texture differences. Then, keyframes are used for motion model estimation to improve the system's stability under low-speed motion. The experimental results of the dataset showed that the key frame rate was optimal between 10% and 12%, and the positioning accuracy was higher than these open-source systems compared with three common open-source VO systems.