Affan Jilani
Papers
1
Total Citations
9
H-Index
1
About
Affan Jilani is a roboticist whose research lies at the intersection of tactile sensing, imitation learning, and dexterous manipulation. His work addresses one of the field’s most stubborn challenges: enabling robots to perform contact-rich tasks that involve relative motion, such as slipping and sliding. In his highly cited 2024 paper, Jilani introduced a novel approach that leverages a see-through visuotactile sensor within an imitation learning framework, achieving force-matched, multimodal control for tasks that require nuanced physical interaction. This work, which has already garnered 9 citations, demonstrates how combining visual and tactile feedback can bridge the gap between rigid, position-controlled manipulation and the adaptive, force-sensitive behaviors needed for real-world tasks. Jilani’s contributions are particularly notable for their focus on “force-matching” — ensuring that learned policies not only replicate trajectories but also faithfully reproduce the contact forces essential for success. His research is paving the way for more capable, sensor-rich robotic systems that can handle the subtle dynamics of assembly, insertion, and other industrial tasks. For students and researchers, Jilani’s work offers a compelling blueprint for integrating multimodal sensing into learning-based control.
Research Focus
Key Achievements
Top Papers
- 1