Alper Canberk

Papers

Total Citations

H-Index

About

Alper Canberk is a researcher at the forefront of human-robot interaction, with a focus on enabling robots to learn from intuitive, physical human feedback. His work addresses a fundamental challenge: how can robots understand and adapt to human objectives when people naturally correct them through touch and manipulation, rather than programming or explicit commands. Canberk’s most cited paper (2021, 23 citations) introduces a framework for learning human objectives from sequences of physical corrections—an approach that recognizes that a single correction may be insufficient when working with multiple robots or in complex tasks. This contribution is critical for developing personal, assistive, and interactive robots that can gracefully recover from mistakes and align with user intent over time. By modeling how humans physically guide robots, Canberk’s research bridges the gap between robotic autonomy and seamless human collaboration. His work has significant implications for assistive technology, manufacturing, and everyday robotics, where natural, non-verbal communication is essential. With a growing citation footprint, Canberk is establishing himself as a key voice in making robots more responsive and intuitive partners for humans.