Shuangge Wang

Yale University, University of Southern California

Papers

Total Citations

H-Index

About

Shuangge Wang investigates the intersection of human-robot interaction and autonomous agent behavior, with a focus on how robots can better understand and adapt to human feedback. Their research addresses critical challenges in real-world robot deployment, particularly when humans serve as supervisors rather than direct teachers. Wang's work on Learning from Corrections (LfC) challenges traditional assumptions about how people provide feedback to robots, revealing that human correction behaviors are more nuanced than previously understood. Their 2025 paper on robot competency and motion legibility (4 citations) demonstrates how robot design choices directly influence the quality and nature of human corrective feedback. In their 2023 work on active probing and influencing human behaviors (4 citations), Wang tackles the fundamental problem of autonomous agents lacking accurate models of the specific humans they interact with, proposing methods for robots to actively learn and adapt to individual human partners. This research has significant implications for collaborative robotics, autonomous systems, and human-centered AI design. Wang's contributions are particularly valuable for developing robots that can work effectively alongside humans in dynamic, real-world environments.