Marianne Schaaphok
Papers
1
Total Citations
2
H-Index
1
About
Marianne Schaaphok is a rising researcher at the intersection of computer vision, natural language processing, and cognitive robotics. Her work centers on endowing artificial agents with the ability to perceive and act upon affordances—the actionable properties of objects in an environment—a critical step toward more intuitive human-robot interaction. Her most-cited paper, "Affordance Perception by a Knowledge-Guided Vision-Language Model with Efficient Error Correction" (2025), introduces a novel framework that integrates structured world knowledge with vision-language models to improve both the accuracy and robustness of affordance detection. By incorporating an efficient error-correction mechanism, this approach addresses a key limitation in current models: their tendency to misinterpret ambiguous or novel scenes. Though early in her career, Schaaphok’s work has already garnered attention (2 citations) for its practical elegance and theoretical depth. Her contributions are particularly notable for bridging the gap between high-level semantic understanding and low-level robotic control, offering a pathway toward systems that can reason about how to interact with objects as humans do. Schaaphok’s research promises to shape the next generation of assistive and autonomous robots.
Research Focus
Key Achievements
Top Papers
- 1