The digital orchard is an important trend for the future development of orchards towards intelligentization. The current wide variety of orchard gripping objects with different sizes and material characteristics brings challenges for gripping operations. In order to improve the versatility and dexterity of the orchard end-effector, a humanoid 14-degree-of-freedom orchard dexterous hand is designed for agronomic operations. An optimal design scheme of the orchard dexterous hand combining orchard gesture analysis and human hand structure is proposed, and the design of the modular fingers, palm, and overall structure of the orchard dexterous hand is completed. The orthogonal and inverse kinematics model of the dexterous hand is established to analyze the motion space of the fingertips, and the dexterity of the orchard dexterous hand is verified by combining with the Kapandji test. The equivalent distribution model of the contact force is solved according to the Hertz theory, and the grasping matrix is established based on the friction surface contact model to realize force-closure, which describes the relationship between the finger and the object being grasped in the configuration. The experimental platform of dexterous hand in the orchard is built, and the experiments of gesture formation, grasping, and contact force testing are carried out. The results show that the dexterous hand can form all kinds of gestures commonly used in the orchard and can grasp spherical fruit with diameters of 26-90 mm, masses of 11-238 g, and all kinds of orchard-specific working tools; for navel oranges with masses of 234 g, the dexterous hand can realize stable grasping under different gestures. This provides a theoretical basis and technical support for the realization of complex agronomy in orchards.

Human-robot collaboration is a promising means to promote orchard intelligence and reduce the over-reliance on manual work for complex agronomic practices such as fruit tree pruning, flower and fruit thinning, and harvesting. Accurate target detection and recognition of robots on humans are the basis and prerequisite for subsequent autonomous human-robot collaboration. In this study, detection and recognition of following robots for human torso were carried out in a standardized hilly orchard. A LiDAR-based human torso detection method was proposed based on the actual orchard environment. Breakpoint detection was used to cluster and segment the point clouds, and the segmentation thresholds were determined based on experimental results. The geometric attributes of the human torso were trained in the classification detection model, resulting in the extraction of six geometric attributes of the human torso. The classification model was then trained with various combinations to obtain the optimal feature combination [girth-depth-average curvature (G-D-k)] for human torso recognition in an orchard environment. Practical experiments were carried out to validate the feasibility and accuracy of the G-D-k feature combination. The experimental results demonstrate that the G-D-k feature combination can accurately recognize human bodies in orchards. The LiDAR-based detection method can achieve relatively accurate human detection and recognition in complex orchard environments, providing a reference for target detection in human-robot collaboration in orchards.