The apple target recognition algorithm is one of the core technologies of the apple picking robot. However, most of the existing apple detection algorithms cannot distinguish between the apples that are occluded by tree branches and occluded by other apples. The apples, grasping end-effector and mechanical picking arm of the robot are very likely to be damaged if the algorithm is directly applied to the picking robot. Based on this practical problem, in order to automatically recognize the graspable and ungraspable apples in an apple tree image, a light-weight apple targets detection method was proposed for picking robot using improved YOLOv5s. Firstly, BottleneckCSP module was improved designed to BottleneckCSP-2 module which was used to replace the BottleneckCSP module in backbone architecture of original YOLOv5s network. Secondly, SE module, which belonged to the visual attention mechanism network, was inserted to the proposed improved backbone network. Thirdly, the bonding fusion mode of feature maps, which were inputs to the target detection layer of medium size in the original YOLOv5s network, were improved. Finally, the initial anchor box size of the original network was improved. The experimental results indicated that the graspable apples, which were unoccluded or only occluded by tree leaves, and the ungraspable apples, which were occluded by tree branches or occluded by other fruits, could be identified effectively using the proposed improved network model in this study. Specifically, the recognition recall, precision, mAP and F1 were 91.48%, 83.83%, 86.75% and 87.49%, respectively. The average recognition time was 0.015 s per image. Contrasted with original YOLOv5s, YOLOv3, YOLOv4 and EfficientDet-D0 model, the mAP of the proposed improved YOLOv5s model increased by 5.05%, 14.95%, 4.74% and 6.75% respectively, the size of the model compressed by 9.29%, 94.6%, 94.8% and 15.3% respectively. The average recognition speeds per image of the proposed improved YOLOv5s model were 2.53, 1.13 and 3.53 times of EfficientDet-D0, YOLOv4 and YOLOv3 and model, respectively. The proposed method can provide technical support for the real-time accurate detection of multiple fruit targets for the apple picking robot.

Canopy shaking system is one of the research hotspots for large-scale mechanized fruits harvesting. Shaking rods considered as one of the essential components of canopy shaker are responsible for transferring mechanical energy from shaking mechanism to different regions of tree canopy. This transfer depends on the characteristics of the shaking rods that directly strike the tree canopy. In order to evaluate the effects of the shaking rods on tree damage level and fruit removal percentage, three kinds of shaking rods with different materials or shapes were selected. Based on the results of bending deformation tests, it was proven that the rigid shaking rod (R 1 ) with the material of Polyvinyl Chloride (PVC) did more resistance against producing bending deformation in comparison with the other two types of shaking rods with the material of Polyamide Nylon 12 (PA). By contrast, the position close to the free end of the flexible shaking rod was easier to be deformed by less external force. In addition, dynamic analysis and vibration performance tests indicated that the rigid shaking rod could produce stronger vibration with higher shaking frequency of 4.8 Hz and maximum acceleration of 31.4 m/s 2 . Finally, the results of field trials indicated that the flexible bow-shaped shaking rod (R 3 ) has a better widespread performance to achieve comparative higher fruit removal percentage up to 82.6% while producing lower tree damage rate of 5.36%. This study demonstrates that the materials or shapes of the shaking rod could significantly influence the fruit detachment rate and tree damage level. This study would provide an essential reference for the application of shaking rods for canopy shaker.

No abstract