Addressing key challenges in unstructured environments, including local optimum traps, limited real-time interaction, and convergence difficulties, this research pioneers a hybrid reinforcement learning approach that combines simulated annealing (SA) with proximal policy optimization (PPO) for robotic arm trajectory planning. The framework enables the accurate, collision-free grasping of randomly appearing objects in dynamic obstacles through three key innovations: a probabilistically enhanced simulation environment with a 20% obstacle generation rate; an optimized state-action space featuring 12-dimensional environment coding and 6-DoF joint control; and an SA-PPO algorithm that dynamically adjusts the learning rate to balance exploration and convergence. Experimental results show a 6.52% increase in success rate (98% vs. 92%) and a 7.14% reduction in steps per set compared to the baseline PPO. A real deployment on the AUBO-i5 robotic arm enables real machine grasping, validating a robust transfer from simulation to reality. This work establishes a new paradigm for adaptive robot manipulation in industrial scenarios requiring a real-time response to environmental uncertainty.

The combination of vision and robotic grinding technology provides robots with “visual perception” capabilities that enable them to accurately locate the area to be ground and perform the grinding tasks efficiently. Based on the rough grinding requirements for wheel hub burrs proposed by a casting company, this paper investigates the application of a vision-guided grinding robot in treating burrs on wheel hub castings. First, through vision system calibration, the conversion from pixel coordinate system to robot base coordinate system is implemented, thus ensuring that the subsequently extracted burr point coordinates can be correctly mapped to the robot’s operational coordinate system. Next, the images of the burrs on wheel hub castings are collected and processed. All the burr points are extracted by applying image algorithms. In order to improve grinding accuracy, a height error compensation model is established to adjust the coordinates of the 2D-pixel points; the coordinate error after compensation was reduced by 58.33%. Subsequently, the compensated burr point trajectories are optimized by utilizing an intelligent optimization algorithm to generate the shortest grinding path. Through experimental analysis of the relationship between spindle speed and surface roughness, a grinding trajectory simulation model is constructed, and the simulation results are integrated into the robot system. Finally, actual wheel hub burr grinding experiments are performed to validate the effectiveness and practicality of the proposed solution.

This paper proposes a knowledge graph (KG) construction method for a part machining process in response to the low degree of structuring of historical process data association relationships within the enterprise in the field of part machining, which makes it difficult to reuse effectively. The part types are mainly shafts, gears, boxes and other common parts. First, the schema layer of the process knowledge graph was constructed using a top-down approach. Second, deep learning techniques were employed for entity extraction, while knowledge fusion and ontology relationship establishment methods were combined to build the data layer of the process knowledge graph (PKG) from the bottom up. Third, the mapping between the schema layer and data layer was implemented in the Neo4j graph database. Based on the constructed process KG, process route recommendation and rapid retrieval of process information were thus accomplished. Finally, a shaft part was used as the target part to verify the effectiveness of the proposed method. In over 300 trials, the similarity-based recommendation model achieved a hit rate of 91.7% (the target part’s route appeared in the recommended list in 91.7% of cases). These results indicate that the proposed machining PKG construction is feasible and can assist in process planning, potentially improving the efficiency of retrieving and reusing machining knowledge.

To meet real-time grasping demands in complex environments, this paper proposes a lightweight yet high-performance robotic grasping model. The model integrates large kernel convolution and residual connections to generate grasping information for unknown objects from RGB and depth images, enabling real-time generation of stable grasping plans from the images. The proposed model achieved favorable accuracy on both the Cornell and Jacquard standard grasping datasets. Compared to other methods, the proposed model significantly reduces the number of parameters while achieving comparable performance, making it a lightweight model. Additionally, real-world experiments were conducted using a six-axis collaborative robot on a set of previously unseen household objects with diverse and adversarial shapes, achieving a comprehensive grasping success rate of 93.7%. Experimental results demonstrate that the proposed model not only improves grasping accuracy but also has strong potential for practical applications, particularly in resource-constrained robotic systems.

Based on the analysis of the motion law of 3D five-directional circular transverse braided fibers, this paper obtains the angle calculation formula between fibers and the local polar coordinate system in various cell models by transforming the position coordinates of fiber nodes. The stress transformation matrix between the local coordinate system and the global coordinate system of any fiber in the circular braided single cell is derived without considering the physical force on the single-cell micro-hexahedron unit. The calculation formulas of braided parameters such as the overall stiffness matrix and fiber volume content of the circular braided composite material after considering the matrix are derived by using the volume average method; the length of braided knuckles is 2 mm, the inner diameter of inner cells is 7 mm, the number of radial and axial braided yarns is 80, the height of inner cells is 0.5 mm, and the filling coefficient is 0.61. Comparing the results of the numerical prediction model with the experimental results in reference, it is found that the error of the numerical prediction model deduced in this paper is small. Therefore, this model can be used to fully study the effects of braided parameters such as cell inner diameter, cell height, and node length on the mechanical properties of composites.

Currently, YOLO-based object detection is widely employed in intelligent inspection robots. However, under interference factors present in dimly lit substation environments, YOLO exhibits issues such as excessively low accuracy, missed detections, and false detections for critical targets. To address these problems, this paper proposes HSS-YOLO, a lightweight object detection model based on YOLOv11. Initially, HetConv is introduced. By combining convolutional kernels of different sizes, it reduces the required number of floating-point operations (FLOPs) and enhances computational efficiency. Subsequently, the integration of Inner-SIoU strengthens the recognition capability for small targets within dim environments. Finally, ShuffleAttention is incorporated to mitigate problems like missed or false detections of small targets under low-light conditions. The experimental results demonstrate that on a custom dataset, the model achieves a precision of 90.5% for critical targets (doors and two types of handles). This represents a 4.6% improvement over YOLOv11, while also reducing parameter count by 10.7% and computational load by 9%. Furthermore, evaluations on public datasets confirm that the proposed model surpasses YOLOv11 in assessment metrics. The improved model presented in this study not only achieves lightweight design but also yields more accurate detection results for doors and handles within dimly lit substation environments.