Papers
10
Total Citations
240
H-Index
5
About
Shuijing Liu is a robotics researcher whose work sits at the intersection of autonomous navigation, human-robot interaction, and multimodal learning. Her research is primarily focused on enabling mobile robots to navigate safely and intelligently through complex, crowded environments — a challenge that demands both technical sophistication and deep consideration of human behavior. Liu's most influential contribution, "Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning" (118 citations), introduced a framework for handling partially observable, dynamic crowd scenarios — a significant advance over prior methods that assumed fully known agent dynamics. Her follow-up work on intention-aware navigation with attention-based interaction graphs (76 citations) further refined how robots model diverse social interactions and anticipate human intent. More recently, she has tackled occlusion-aware navigation and constrained environments through heterogeneous graph transformers, pushing the boundaries of spatial-temporal reasoning in robotics. Beyond navigation, Liu has broadened her scope to include assistive technologies — notably DRAGON, a dialogue-based robot for visually impaired users — as well as voice-controlled robots and bimanual manipulation using diffusion models. Her cumulative citation record reflects a growing influence in the field, establishing her as an emerging and versatile voice in intelligent, socially aware robotics research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Occlusion-Aware Crowd Navigation Using People as Sensors12 citations · 2023
- 5
- 6Learning Visual-Audio Representations for Voice-Controlled Robots2 citations · 2023
- 7
- 8
- 9
- 10