Grasping unstructured and fragile objects such as food and fruits is a great challenge for robots. Being naturally different from the traditional rigid robot, soft robotics provide highly promising choices with their intrinsic flexibility and compliance to objects. Inspired by duck foot and octopus tentacle, a pneumatic webbed soft gripper was proposed, which is consisted of four multi-chambered fingers and four webs. Due to its silicone body and soft web structure, the developed soft gripper can naturally adapt, grasp and hold delicate and unstructured objects. Compressed air inflated into the three chambers of the finger actuates the silicone body and performs inflection and extension. The silicone web follows the motion of four fingers, forming a semi-closed grasping configuration. The fingers were fabricated with silicone rubber and constraint spring by casting process. The web was cast around the fingers. The inflecting motion was modeled via the pneumatic principle and geometrical analysis. The dynamic properties of the finger were tested by step and sinusoidal signals. And the grasping performances for different objects, such as egg, strawberry, candy, and knife, were also demonstrated by experiments. The proposed soft gripper performed stably in response to a 0.4 Hz reference sinusoidal signal. The bionic structure greatly improves the stability and reliability of grasping, particularly for unstructured and fragile objects. Moreover, the webs ensure the grasping for multiple objects in one snatch, especially suitable for agricultural products and food processing. Keywords: soft gripper, biomimetics, grasping, robotic, pneumatic DOI: 10.25165/j.ijabe.20211404.6388 Citation: Cai S B, Tang C E, Pan L F, Bao G J, Bai W Y, Yang Q H. Pneumatic webbed soft gripper for unstructured grasping. Int J Agric & Biol Eng, 2021; 14(4): 145–151.

In order to realize the visual positioning for Hangzhou white chrysanthemums harvesting robot in natural environment, a color image segmentation method for Hangzhou white chrysanthemum based on least squares support vector machine (LS-SVM) was proposed. Firstly, bilateral filter was used to filter the RGB channels image respectively to eliminate noise. Then the pixel-level color feature and texture feature of the image, which was used as input of LS-SVM model (classifier) and SVM model (classifier), were extracted via RGB value of image and gray level co-occurrence matrix. Finally, the color image was segmented with the trained LS-SVM model (classifier) and SVM model (classifier) separately. The experimental results showed that the trained LS-SVM model and SVM model could effectively segment the images of the Hangzhou white chrysanthemums from complicated background taken under three illumination conditions such as front-lighting, back-lighting and overshadow, with the accuracy of above 90%. When segmenting an image, the SVM algorithm required 1.3 s, while the LS-SVM algorithm proposed in this paper just needed 0.7 s, which was better than the SVM algorithm obviously. The picking experiment was carried out and the results showed that the implementation of the proposed segmentation algorithm on the picking robot could achieve 81% picking success rate. Keywords: bilateral filter, least squares support vector machine (LS-SVM), image segmentation, Hangzhou white chrysanthemum, illumination intensity DOI: 10.25165/j.ijabe.20191204.4584 Citation: Yang Q H, Luo S L, Chang C, Xun Y, Bao G J. Segmentation algorithm for Hangzhou white chrysanthemums based on least squares support vector machine. Int J Agric & Biol Eng, 2019; 12(4): 127–134.

Apple fruits on trees tend to swing because of wind or other natural causes, therefore reducing the accuracy of apple picking by robots. To increase the accuracy and to speed up the apple tracking and identifying process, tracking and recognition method combined with an affine transformation was proposed. The method can be divided into three steps. First, the initial image was segmented by Otsu’s thresholding method based on the two times Red minus Green minus Blue (2R-G-B) color feature; after improving the binary image, the apples were recognized with a local parameter adaptive Hough circle transformation method, thus improving the accuracy of recognition and avoiding the long, time-consuming process and excessive fitted circles in traditional Hough circle transformation. The process and results were verified experimentally. Second, the Shi-Tomasi corners detected and extracted from the first frame image were tracked, and the corners with large positive and negative optical flow errors were removed. The affine transformation matrix between the two frames was calculated based on the Random Sampling Consistency algorithm (RANSAC) to correct the scale of the template image and predict the apple positions. Third, the best positions of the target apples within 1.2 times of the prediction area were searched with a de-mean normalized cross-correlation template matching algorithm. The test results showed that the running time of each frame was 25 ms and 130 ms and the tracking error was more than 8% and 20% in the absence of template correction and apple position prediction, respectively. In comparison, the running time of our algorithm was 25 ms, and the tracking error was less than 4%. Therefore, test results indicate that speed and efficiency can be greatly improved by using our method, and this strategy can also provide a reference for tracking and recognizing other oscillatory fruits. Keywords: apple picking robot, tracking and recognition algorithm, oscillating apple, Hough transform, pyramid LK optical flow algorithm, affine transform, template matching DOI: 10.25165/j.ijabe.20201305.5520 Citation: Yang Q H, Chen C, Dai J Y, Xun Y, Bao G J. Tracking and recognition algorithm for a robot harvesting oscillating apples. Int J Agric & Biol Eng, 2020; 13(5): 163–170.

Understanding multiphase flow and gas transport occurring in electrodes is crucial for improving the performance of proton exchange membrane fuel cells. In the present study, a pore-scale model using the lattice Boltzmann method (LBM) was proposed to study the coupled processes of air–water two-phase flow and oxygen reactive transport processes in porous structures of the gas diffusion layer (GDL) and in fractures of the microscopic porous layer (MPL). Three-dimensional pore-scale numerical results show that the liquid water generation rate is gradually reduced as the oxygen consumption reaction proceeds, and the liquid water saturation in the GDL increases, thus the constant velocity inlet or pressure inlet condition cannot be maintained while the results showed that at t = 1,200,000 iterations after 2900 h running time, the local saturation at the GDL/MPL was about 0.7, and the maximum value was about 0.83, while the total saturation was 0.35. The current density reduced from 2.39 to 0.46 A cm⁻². Effects of fracture number were also investigated, and the results showed that for the fracture numbers of 8, 12, 16, and 24, the breakthrough point number was 4, 3, 3, and 2, respectively. As the fracture number increased, the number of the water breakthrough points at the GDL/GC interface decreased, the liquid water saturation inside the GDL increased, the GDL/MPL interface was more seriously covered, and the current density decreased. The pore-scale model for the coupled multiphase reactive transport processes is helpful for understanding the mechanisms inside the porous electrodes of PEMFC.