Qinyang Qu

Papers

Total Citations

H-Index

About

Qinyang Qu is a researcher focused on advancing scene understanding for autonomous systems, particularly indoor robots equipped with 2D LiDAR. Their key research area lies in applying deep learning, specifically convolutional neural networks (CNNs), to improve environmental perception and classification. Qu’s most notable contribution is a novel scene classification method that transforms raw 2D LiDAR data into a polar coordinate representation, enabling a one-dimensional CNN to accurately recognize indoor scenes—a critical challenge for robot navigation and localization. This work directly addresses the limitations of traditional 2D LiDAR in complex indoor environments, offering a computationally efficient solution that enhances robotic autonomy. While early in its citation impact, with 1 citation to date, the paper represents a foundational step in bridging sensor data and deep learning for real-time scene recognition. Qu’s research holds promise for advancing affordable, LiDAR-based robotic systems in applications like service robots, warehouse automation, and smart home assistants, demonstrating a practical approach to integrating neural networks with spatial data for robust environmental understanding.