YZYangbin Zheng

Yangbin Zheng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yangbin Zheng has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • ICP registration with SHOT descriptor for arresters point clouds

    by Senjian Lu, Wen Zhu, Beiping Hou, Jianwei Dong, Yangbin Zheng, Xiaoxin Qi, Yuzhen Zhu, Aihua Yu

    Arresters are one of the critical components of the power system. However, due to the arrester’s regular and uniform umbrella skirt, both traditional manual detection methods and existing computer vision approaches exhibit limitations in accuracy and efficiency. This paper proposes an automatic, robust, efficient arrester point cloud registration method to address this problem. First, a robotic arm maneuvers a depth camera to capture point cloud data from various perspectives. Then, the fast global registration point cloud coarse registration method based on the signature of histograms of orientations descriptor to produce preliminary registration results. This result is ultimately used as the initial value of the improved iterative closest point algorithm to refine the registration further. Experimental results on various data sets collected from arrester and public data sets show that the algorithm’s root mean square error is less than 0.1 mm, meeting the requirements of the engineering application of arrester detection.


  • Pixel-Level Collision-Free Grasp Prediction Network for Medical Test Tube Sorting on Cluttered Trays

    by Shihao Ge, Beiping Hou, Wen Zhu, Yuzhen Zhu, Senjian Lu, Yangbin Zheng

    Robotic sorting shows a promising aspect for future developments in medical field. However, vision-based grasp detection of medical devices is usually in unstructured or cluttered environments, which raises major challenges for the development of robotic sorting systems. In this work, a pixel-level grasp detection method is proposed to predict the optimal collision-free grasp configuration on RGB images. First, an Adaptive Grasp Flex Classify (AGFC) model is introduced to add category attributes to distinguish test tube arrangements in complex scenarios. Then, we propose an end-to-end trainable CNN-based architecture, which delivers high quality results for grasp detection and avoids the confusion in neural network learning, to generate the AGFC-model. Utilizing this, we design a Residual Efficient Atrous Spatial Pyramid (REASP) block to further increase the accuracy of grasp detection. Finally, a collision-free manipulation policy is designed to guide the robot to grasp. Experiments on various scenarios are implemented to illustrate the robustness and the effectiveness of our approach, and a robotic grasping platform is constructed to evaluate its application performance. Overall, the developed robotic sorting system achieves a success rate of 95% on test tube sorting.