Papers
9
Total Citations
188
H-Index
5
About
Yuying Chen is a leading researcher in the field of autonomous navigation and human-robot interaction, with a focus on developing intelligent systems that can safely and efficiently operate in crowded, dynamic environments. Her work centers on integrating deep reinforcement learning with graph-based representations to address key challenges in robot crowd navigation and pedestrian trajectory prediction. Chen’s most impactful contribution is her 2020 paper on "Robot Navigation in Crowds by Graph Convolutional Networks With Attention Learned From Human Gaze," which has garnered 139 citations. This work pioneered the use of gaze-informed attention mechanisms to improve navigation policies in dense crowds, overcoming limitations of prior methods that deteriorated with increasing crowd size. She further advanced the field with her development of the Hierarchical Graph Convolutional Network with Groupwise Joint Sampling (HGCN-GJS) and Coherent Motion Aware Trajectory Prediction (CoMoGCN) models, which capture complex social interactions and group dynamics for more accurate trajectory forecasting. Chen’s research, which also includes early work on policy learning from human reinforcement and emotion-based reward shaping, has been widely recognized for its practical implications in autonomous driving and mobile robotics, establishing her as a key innovator in socially-aware navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Policy Learning with Human Reinforcement4 citations · 2016
- 7
- 8
- 9Reward shaping for reinforcement learning by emotion expressions2 citations · 2014