The spread of infections and rot are crucial factors in the decrease in tomato production. Accurately segmenting the affected tomatoes in real-time can prevent the spread of illnesses. However, environmental factors and surface features can affect tomato segmentation accuracy. This study suggests an improved YOLOv8s-Seg network to perform real-time and effective segmentation of tomato fruit, surface color, and surface features. The feature fusion capability of the algorithm was improved by replacing the C2f module with the RepBlock module (stacked by RepConv), adding SimConv convolution (using the ReLU function instead of the SiLU function as the activation function) before two upsampling in the feature fusion network, and replacing the remaining conventional convolution with SimConv. The F1 score was 88.7%, which was 1.0%, 2.8%, 0.8%, and 1.1% higher than that of the YOLOv8s-Seg algorithm, YOLOv5s-Seg algorithm, YOLOv7-Seg algorithm, and Mask RCNN algorithm, respectively. Meanwhile, the segment mean average precision (segment mAP_@0.5) was 92.2%, which was 2.4%, 3.2%, 1.8%, and 0.7% higher than that of the YOLOv8s-Seg algorithm, YOLOv5s-Seg algorithm, YOLOv7-Seg algorithm, and Mask RCNN algorithm. The algorithm can perform real-time instance segmentation of tomatoes with an inference time of 3.5 ms. This approach provides technical support for tomato health monitoring and intelligent harvesting.

Accurate obstacle detection and proper behavior planning are key factors in the success of transmission line inspection robots. To achieve the autonomous location and identification of line obstacles in the operation of transmission line inspection robots, we propose a method in which information from various sensors is used to control a robot such that it can reliably and stably approach, locate, and identify obstacles. The accuracy and real-time requirements of obstacle information in the autonomous operation of the inspection robot are analyzed, a multi-sensor integrated structure for line obstacle location and identification is proposed, and an obstacle location and identification algorithm is designed for each stage. The principle of monocular vision ranging is used to control the robot such that it approaches obstacles and enters the short-range location stage, where the reliable location of obstacles is achieved via collision-encoder-current sensor data fusion. Obstacles are identified and the identification results are combined with those of the approaching rolling phase. The robot state vector is constructed according to the obstacle detection information and information measured by the robot sensors. Based on the current state vector, combined with the robot obstacle surmounting process, an obstacle surmounting behavior planning method based on multi-sensor fusion is implemented. Experiments were conducted using laboratory-simulated lines to verify the effectiveness of the proposed method for obstacle detection and behavior planning during transmission line inspection.

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.

To inspect the 110kV power transmission line, the inspection robot should be able to cross the jumper lines of the live lines. In this paper, a novel inspection robot is designed, equipped with a centroid adjustment mechanism to make it capable of crossing the jumper line smoothly. The various obstacle crossing modes of the robot and the proper planning of the obstacle crossing of the jumper line are designed. Also, the rigid-flexible coupling dynamic modeling method of the robot in the flexible cable environment is studied, which helps understand the influence of the robot on the transmission line in the flexible cable environment. Moreover, a simulation is carried out to analyze the deformation of the jumper line when the robot is on the jumper line. Simulation results can be utilized to plan the motion when the robot crosses the jumper line, improving the robot’s efficiency and stability.

The distribution law of residual stress in multi-channel scanned plasma cladding of Co-based alloy under different process parameters was studied by means of simulation and tests, and the optimum process parameters were optimized. The simulation model of the plasma cladding stress field was established by ABAQUS software, and the influence law of the working current, scanning speed, and scanning mode on the residual stress of the Co-based alloy multi-channel scanning was studied. A set of optimal cladding process parameters were obtained. The residual stress of the cladding layer was measured by the blind hole method and compared with the stress value in the finite element model. The results show that there is residual tensile stress on the surface of the cladding layer. The residual stress along the direction of the scanning path is greater than that along the direction of the scan sequence. The residual stress increases with the increase of the working current. The scanning speed is greater, and the residual stress is smaller. The residual stress of the short-edge scanning is greater than that of the long-edge scanning. The residual stress of the successive scanning is greater than that of the reciprocating scanning. The long-edge reciprocating scanning is the best scanning mode. The best combination of process parameters is the working current of 90 A, the scanning speed of 100 mm/min, and the long-edge reciprocating scanning mode.