Jingxuan Dong

Nanjing University of Aeronautics and Astronautics

Papers

Total Citations

H-Index

About

Jingxuan Dong is a leading researcher at the intersection of computer vision and robotics, with a primary focus on developing intelligent, mapless navigation systems for autonomous agents. Her most influential work, "Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning" (2020), has garnered 45 citations and represents a significant breakthrough in the field. In this study, Dong introduced a novel target-driven navigation system that enables robots to navigate complex indoor environments using only multi-view visual observations and a target image, eliminating the need for traditional odometry or global path planning. By leveraging generative imitation learning, her approach allows robots to learn robust navigation policies directly from expert demonstrations, making them more adaptable to dynamic and unstructured settings. This work has been widely recognized for its practical implications in service robotics and autonomous exploration, where reliable visual navigation without prior maps is critical. Dong’s contributions continue to inspire new research in learning-based control and embodied AI, positioning her as a key innovator in the quest for truly autonomous, vision-guided robots.