Yanqi Liu
Papers
5
Total Citations
46
H-Index
4
About
Yanqi Liu is a researcher at the forefront of secure and robust robotic perception and manipulation, with a focus on integrating generative and discriminative inference to fortify autonomous systems against adversarial threats. Liu’s major contributions center on the GRIP framework (Generative Robust Inference and Perception), which enhances semantic robot manipulation by enabling reliable object detection and grasping even in uncertain or hostile environments—a critical advance for deploying robots in real-world security and industrial applications. This work, alongside complementary studies on robust object estimation and energy-efficient Monte-Carlo sampling hardware acceleration, has garnered over 46 citations, reflecting its growing influence in the robotics and machine learning communities. Notably, Liu’s research addresses the computational bottlenecks of sampling-based algorithms, proposing hardware solutions to enable real-time, low-power operation. While one publication on AI in accounting talent training was later retracted, Liu’s core body of work remains a vital resource for students and engineers seeking to build resilient, perception-driven robotic systems that can operate safely and accurately under duress.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5