Xian-Shi Zhang

University of Electronic Science and Technology of China

Papers

Total Citations

H-Index

About

Xian-Shi Zhang is a leading researcher in embodied AI and autonomous robot navigation, with a focus on bridging the gap between simulation and real-world deployment. His primary research areas include visual odometry, goal-conditioned navigation, and unsupervised learning for robotic perception. Zhang’s most notable contribution is his work on PointGoal navigation in indoor environments, where he developed unsupervised methods that integrate visual odometry with action planning to enable robots to navigate to specified points without relying on noisy or costly sensor calibration. His 2023 paper on this topic, which has garnered 11 citations, addresses a critical challenge in robotics: achieving near-perfect navigation success rates in photorealistic simulations while accounting for real-world actuation noise. This work is pivotal for advancing personal robotics, as it reduces the gap between simulated training and physical deployment. Zhang’s research is widely recognized for its practical impact, offering scalable solutions for indoor robot navigation that require minimal supervision. His contributions continue to inspire new approaches in embodied AI, making him a key figure in the quest for truly autonomous, real-world robotic systems.