Aleksandr Semochkin

• PhD
• Group Leader at Sberbank

Object pose estimation is a prerequisite for many robotic applications. Preparing dataset for network training is a challenging part of the pose estimation approaches, and in most of them, the network can detect just the trained objects. Synthetic data are used to train deep neural networks in robotic manipulation as a promising method for obtainin...

Given the laborious difficulty of moving heavy bags of physical currency in the cash center of the bank, there is a large demand for training and deploying safe autonomous systems capable of conducting such tasks in a collaborative workspace. However, the deformable properties of the bag along with the large quantity of rigid-body coins contained w...

This paper presents an approach for grasping objects by the robotic manipulator at predefined points by userdefined grasping methods for cases of arbitrary position and orientation of objects. The key idea is to implement a detection algorithm for user-defined key-points on the reference object image. As these points can be detected and localized o...

This paper presents an approach for grasping objects by the robotic manipulator at predefined points by userdefined grasping methods for cases of arbitrary position and orientation of objects. The key idea is to implement a detection algorithm for user-defined key-points on the reference object image. As these points can be detected and localized o...

The paper introduces a device “Artificial Muscle Twister” (AMT) used for producing artificial muscles from nylon fishing line with a heater wire. AMT is assembled from common electronic and mechanical components, while the case is printed on the 3D printer. The device is used for winding wire onto a nylon monofilament and twisting followed by coili...