Xintao Ding

Anhui Institute of Information Technology, Anhui Normal University

Papers

Total Citations

H-Index

About

Xintao Ding is a leading researcher in robotics and computer vision, with a primary focus on indoor object recognition and mobile robot navigation. His most influential work centers on developing deep learning methods that enable robots to perceive and interact with complex indoor environments. Ding’s seminal 2018 paper, "Prior knowledge-based deep learning method for indoor object recognition and application" (22 citations), pioneered the integration of prior knowledge with convolutional neural networks (CNNs) to significantly improve detection precision for mobile robots. His earlier 2017 work on pre-trained CNNs for indoor object recognition (15 citations) established foundational pipelines that remain widely referenced. Ding has also made critical contributions to dynamic path planning and obstacle avoidance, addressing the limitations of traditional methods in handling dynamic environments. His more recent research explores geometric property-based CNNs (2021, 4 citations), incorporating 2D shape and depth information to enhance detection accuracy. With a growing citation impact, Ding’s work bridges the gap between theoretical deep learning and practical robotic applications, offering robust solutions for autonomous navigation, and his innovative approaches continue to influence both academic research and real-world robotic systems.