Shuangda Duan
Papers
7
Total Citations
41
H-Index
5
About
Shuangda Duan is a robotics researcher whose work centers on autonomous manipulation, anomaly detection, and robot resilience in unstructured environments. His research addresses one of the fundamental challenges in modern robotics: enabling robots to recognize, classify, and recover from unexpected disturbances — such as accidental human or tool collisions — without human intervention. Duan's most significant contributions lie in developing recovery policies that allow robots to respond intelligently to external disturbances during manipulation tasks. His work on state-dependent revertive recovery policies and grounded anomaly classification frameworks provides robots with the capacity to not only detect failures but actively restore task execution, extending their operational autonomy. Complementing this, his research on Hidden Markov Model (HMM)-based event detection offers fast and robust methods for identifying nominal and anomalous behavior from multimodal sensor data, a critical capability for data-driven robotic systems. With papers accumulating citations across multiple publication years — including works cited up to nine times — Duan's research has gained consistent recognition within the robotics and autonomous systems community. His contributions to multimodal sparse representation for anomaly classification further demonstrate a commitment to building introspective robots capable of self-assessment in complex, real-world scenarios, making his work highly relevant to the future of human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7