Kai Cheng
Papers
1
Total Citations
5
H-Index
1
About
Kai Cheng is a rising researcher in robotics and computer vision, whose work centers on enabling robots to perceive and manipulate 3D articulated objects—such as doors, drawers, and cabinets—in complex, real-world environments. His key contributions lie in developing learning-based methods that integrate environment-aware affordance reasoning, allowing robots to handle occlusions and cluttered settings that challenge traditional approaches. In his highly cited 2023 paper, "Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions," Cheng introduced a novel framework that moves beyond single-object scenarios to consider the surrounding context, significantly improving robotic dexterity and autonomy. This work has garnered early attention with 5 citations, reflecting its timely impact on the growing field of home-assistant robotics. Cheng’s research bridges the gap between perception and action, offering actionable priors for downstream manipulation tasks. His achievements are particularly notable for advancing point-level affordance learning in practical, occlusion-heavy environments, marking him as a promising contributor to embodied AI and human-robot interaction.
Research Focus
Key Achievements
Top Papers
- 1