Xiantong Tao
Papers
1
Total Citations
45
H-Index
1
About
Xiantong Tao is a leading researcher in robotic perception and manipulation, with a primary focus on enabling robots to reliably interact with unstructured environments. His most impactful work centers on deep learning-driven grasp detection, particularly for cluttered and unpredictable settings. Tao’s landmark 2021 paper, “Robotic Objects Detection and Grasping in Clutter Based on Cascaded Deep Convolutional Neural Network,” has garnered 45 citations, establishing a foundational method for grasping unknown, irregular objects. In this work, he introduced a cascaded convolutional neural network architecture that dramatically improves grasp pose detection accuracy, addressing the persistent challenge of low success rates in complex, changeable operating environments. This contribution is critical for advancing autonomous robotics in applications like warehouse automation and domestic assistance. Beyond this, Tao’s research spans object detection, sensor fusion, and real-time robotic control, consistently pushing the boundaries of how machines perceive and act upon their surroundings. His work is widely recognized for bridging the gap between theoretical deep learning models and practical, robust robotic systems, making him a key figure in modern robotic manipulation.
Research Focus
Key Achievements
Top Papers
- 1