Ping Yang

Accurate segmentation of densely stacked and weakly textured objects remains a core challenge in robotic depalletizing for industrial applications. To address this, we propose MaskNet, an instance segmentation network tailored for RGB-D input, designed to enhance recognition performance under occlusion and low-texture conditions. Built upon a Vision Transformer backbone, MaskNet adopts a dual-branch architecture for RGB and depth modalities and integrates multi-modal features using an attention-based fusion module. Further, spatial and channel attention mechanisms are employed to refine feature representation and improve instance-level discrimination. The segmentation outputs are used in conjunction with regional depth to optimize the grasping sequence. Experimental evaluations on camshaft depalletizing tasks demonstrate that MaskNet achieves a precision of 0.980, a recall of 0.971, and an F1-score of 0.975, outperforming a YOLO11-based baseline. In an actual scenario, with a self-designed flexible magnetic gripper, the system maintains a maximum grasping error of 9.85 mm and a 98% task success rate across multiple camshaft types. These results validate the effectiveness of MaskNet in enabling fine-grained perception for robotic manipulation in cluttered, real-world scenarios.

Spatial error obtained is a crucial process for industrial robot accuracy calibration. However, the existing spatial error sensor systems are often limited by inflexibility, poor adaptability to varying conditions, or substantial cost. This study proposes a multi-sensor system for calibrating tool center point of the robot, comprising a novel non-contact sensor system based on R-test, and an automated rotary device equipped with several standard spheres across different ranges. The geometric accuracy of the proposed system was validated by coordinate measuring machine. Spatial error measurement was established based on the geometric modelling and error vector mapping, followed by a novel error identification and compensation algorithm incorporating the Least Squares Method, Cartesian stiffness identification and Ridge Estimation. A simulation was conducted to demonstrate the capability of the proposed model to identify and correct spatial errors down to the micrometer level. The calibration experiment was conducted on EPSON C4-A901 industrial robot. The results showed that the proposed method reduced the average error modulus by 36.94% to 43.86%, and the maximum error modulus by 35.90% to 20.34% as the rotation radius increased from 50 mm to 100 mm. Additionally, a laser tracker was employed for validation, and the spatial errors measured by both systems exhibited a similar trend and deviation. The calibration results obtained using the laser tracker showed a 49 % reduction in average error. This result substantiates the reliability of the proposed calibration algorithm and verifies the accuracy of the measurement system.

In the application of vision measurement, the black light-absorbing object is difficult to reflect the structured light from infrared emitter of the RGB-D camera. Therefore, an image recognition algorithm based on reference environment information is proposed to acquire the spatial positioning information of black volutes in the depalletizing system. The hardware system of the depalletizing system is mainly constructed of an upper computer, a six-axis industrial robot, an RGB-D camera and an end adsorption device. Firstly, the horizontal position information of each volute placed on the cardboard is obtained by the depth differences between the cardboard and the volute. Then, the depth information of the volute is obtained by the upper cardboard depth through collecting the position of the end vacuum suction cup triggered by feedback signal from vacuum generator. Secondly, a regional planar hand-eye calibration method is developed to improve the calibration accuracy in two-dimensional coordinates. The regional calibration method divides the robot working area into four regions: upper left, lower left, upper right, and lower right. The transformation matrix of each region is calculated separately. Finally, the depalletizing experiment is conducted on the three types of volutes. It is concluded that the average positioning error of the grasping center point of each volute obtained by our method is 3.795 mm, and its standard deviation is 1.769 mm. The average value of regional planar hand-eye calibration error is 4.044 mm, and its standard deviation is 1.501 mm. Under a stack of materials with dimensions of 1350 mm × 1350 mm × 1500 mm, the maximum error is controlled within 15 mm. Additionally, when combined with the end feedback compensation mechanism, the success rate for grasping all three volutes reaches 100%.

Fiber Reinforced Plastics (FRP) are extensively employed in the fabrication of mannequins. However, the manual polishing process of FRP is characterized by a deficiency in efficiency and poses detrimental effects on the workforce. An industrial robot combined with an online measurement method is proposed for polishing the surface of the mannequin arm made of FPR material. In this paper, the factors affecting the removal depth of FRP materials are discussed by establishing a mathematical model. Based on the simulation analysis, the removal depth and the range of machining parameters are derived. The online measuring device manufactured by Keyence model LJ-X8200 is mounted on the flange of an ABB IRB6700 industrial robot, which obtains the 3D digital data from arm surface before and after the polishing process. A sub-regional hand-eye calibration is applied to establish the spatial transformation matrix from the sensor coordinate to the workpiece coordinate to refine the calibration range and accuracy. Then, the processing data points are extracted by equal interval and coplanar method. In addition, the robot processing posture is obtained from the surface fitting curve based on the least square method. Finally, the polishing processing experiments are performed to analyze robot intelligent location recognition and verify the surface removal effect based on the optimum polishing parameters. Comparing the 3D measuring data before and after the polishing process, it is shown that the average value of workpiece surface roughness has been reduced to 2.518µm.

The sphericity error is one of the most important tolerances to evaluate the dimensional accuracy of bearing balls. A continuous dynamic measurement system based on an industrial camera and a Z-shaped transparent track is developed to measure the sphericity error of bearing balls. The Z-shaped track, which is considered for the parameter setting of length, width and inclination, is designed to achieve a pure rolling of the ball around three perpendicular axes. During the whole measurement process, 15 images are dynamically captured by an industrial camera and divided into three groups according to the three mutually perpendicular directions. Then, a sub-pixel edge contour of the bearing ball from each image is extracted by an image-processing step, such as image de-noising, contrast enhancement, region-of-interest extraction and edge detection. Finally, the roundness error and sphericity error, as defined by ISO 12181-1 and ISO 3290-1, are acquired from the extracted contour of each image. Three different diameter bearing balls with a precision grade of G1000, representing a sphericity error of approximately 25 μm, are applied as experimental objects. The two times standard deviation roundness error obtained from the contour of each image are all less than 7 μm after six repeated measurements. In addition, the two measurement results respectively acquired from the proposed method and a commercial projection measuring instrument have good consistency.