Papers
2
Total Citations
5
H-Index
2
About
Cong He’s research lies at the intersection of haptic perception, robotic manipulation, and intelligent navigation, with a focus on enabling robots to interact with their environments more naturally and autonomously. In one of their key contributions, He developed a perceptual model for compliance that quantifies the relationship between physical stimuli and human subjective perception when interacting with compliant objects featuring rigid surfaces. This work, though early in its citation trajectory, addresses a foundational challenge in haptic rendering and sensorimotor control, offering a framework for designing robotic systems that can “feel” compliance as humans do. In parallel, He proposed a novel Multi-Task Decomposition Architecture based on Deep Reinforcement Learning for obstacle avoidance in mobile robots. By decomposing complex navigation tasks into subtasks and leveraging collision-related rewards, this approach enables more efficient and robust learning in cluttered environments. While still building momentum—with papers accumulating 3 and 2 citations respectively—He’s work demonstrates a thoughtful integration of perceptual modeling and learning-based control. Their contributions are particularly relevant for advancing human-robot interaction and autonomous navigation, laying groundwork for more adaptive and perceptually aware robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2