Accurate target recognition and localization remain significant challenges for robotic fruit harvesting in unstructured orchard environments characterized by branch occlusion and leaf clutter. To address the difficulty in identifying and locating apples under such visually complex conditions, this paper proposes an improved YOLOv5-based visual recognition algorithm incorporating an efficient channel attention (ECA) module. The ECA module is strategically integrated into specific C3 layers (C3-3, C3-6, C3-9) of the YOLOv5 network architecture to enhance feature representation for occluded targets. During operation, the system simultaneously acquires apple pose information and achieves precise spatial localization through coordinate transformation matrices. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed system. The custom-designed six-degree-of-freedom (6-DOF) robotic arm exhibits a wide operational range with a maximum working angle of 120°. The ECA-enhanced YOLOv5 model achieves a confidence level of 90% and an impressive in-range apple recognition rate of 98%, representing a 2.5% improvement in the mean Average Precision (mAP) compared to the baseline YOLOv5s algorithm. The end-effector positioning error is consistently controlled within 1.5 mm. The motion planning success rate reaches 92%, with the picking completed within 23 s per apple. This work provides a novel and effective vision recognition solution for future development of harvesting robots.

Stable mobility of rail-climbing robots in complex aerial worksites remains a significant challenge for industrial inspection and maintenance. Existing designs often struggle with reliable adhesion, efficient locomotion, and adaptability to omnidirectional movement on rails with varying curvature and orientation. This study proposes OmniClimb, a novel omnidirectional rail-climbing robot integrating a gravity-actuated locking mechanism and a variable-posture passive adaptation mechanism. The front locomotion unit employs gravity-actuated locking mechanism to ensure consistent contact stress and friction while self-adjusting to rail inclination. A variable-posture passive adaptation mechanism dynamically adjusts the pitch between front and rear frames, enhancing the gravity-actuated locking effect on the rear unit during curved-rail climbing. A multistage compound transmission system combined with an five-wheel-drive configuration improve power transmission efficiency and disturbance rejection in complex rail environments. Dynamic models were established, and structural parameters were optimized using ADAMS multi-body dynamics simulations. Experiments on a 3D-printed physical prototype demonstrated stable mobility and locking capability on multi-curvature rails under loaded conditions, achieving a maximum speed of 0.053 m/s with controlled motor torque fluctuation (mean 1.25 N·m). OmniClimb’s validated adaptability, stability, and efficient climbing performance provide a promising novel solution for deploying rail robots in complex scenarios such as transmission towers and utility tunnels.

Xue-Chen Qiao, Meng-Yun Yan, Zhen-Gang Zhao; Recurrent strokes in a 64-year-old woman caused by left ventricular diverticulum, European Heart Journal - Cardiova