Xiaoxi Gong

Nanjing University of Aeronautics and Astronautics

Papers

Total Citations

H-Index

About

Xiaoxi Gong is a leading researcher in embodied AI and robotic perception, specializing in visual navigation and 6D pose estimation. Her work bridges the gap between high-level reasoning and low-level control in autonomous systems. Her most influential contribution, "Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning" (45 citations), introduces a groundbreaking approach that enables robots to navigate to a target using only visual inputs, eliminating the need for odometry or GPS. This work has been pivotal in advancing mapless navigation for real-world robotics. Gong further extended this line of research with "Image-Goal Navigation in Complex Environments via Modular Learning" (11 citations), which decouples navigation planning, collision avoidance, and goal prediction for robust performance in cluttered spaces. In the domain of robotic manipulation, her paper "EANet: Edge-Attention 6D Pose Estimation Network for Texture-Less Objects" (37 citations) tackles the challenging problem of pose estimation under poor lighting and occlusion, introducing an edge-attention mechanism that significantly improves accuracy for texture-less industrial objects. With over 90 total citations, Gong’s work is essential reading for researchers in autonomous navigation and vision-based robotics.