Ainur Begalinova

University of Manchester, Nazarbayev University

Papers

Total Citations

H-Index

About

Ainur Begalinova is a researcher at the intersection of robotics, embedded systems, and machine learning. Her primary research areas focus on enhancing robotic manipulation through intelligent sensing and control, with a particular emphasis on tactile perception and gesture-based interfaces. Begalinova’s most significant contribution is her pioneering work on self-supervised learning for object slippage detection. In her 2020 study, she developed an LSTM model trained on data from low-cost tactile sensors to predict slippage events by analyzing temporal features of micro-slippages at the hand-object contact point. This approach, which has garnered 12 citations, offers a practical and cost-effective solution for improving robotic grasping stability. Earlier in her career, Begalinova contributed to the design of embedded gesture recognition systems for robotic applications (2014), leveraging system-on-chip technologies to enable mobile robots with advanced onboard computation for complex data processing and control. Her work demonstrates a commitment to bridging the gap between sophisticated algorithms and real-world, resource-constrained robotic platforms, making her a notable figure in the advancement of intelligent robotic systems.