Papers
37
Total Citations
1,709
H-Index
17
About
Sungho Jo is a versatile robotics and human-machine interface researcher whose work spans soft robotics, brain-computer interfaces (BCIs), wearable sensing, and machine learning-driven control systems. His research has made significant strides in enabling intuitive, intelligent interactions between humans and robotic systems across multiple fronts. Jo's early contributions focused on EEG-based BCIs for humanoid robot navigation, with his asynchronous direct-control system (209 citations) and hybrid BCI combining P300, SSVEP, and ERD signals (129 citations) establishing foundational frameworks for brain-actuated robotics. He extended this work to quadcopter control using hybrid eye-tracking and EEG interfaces, demonstrating broad applicability across robotic platforms. In soft robotics and wearable technology, Jo pioneered the use of deep learning for characterizing nonlinear soft sensors (129 citations) and developed a skin-mounted sensor system capable of decoding complex human body motions through machine learning (287 citations). His comprehensive review of machine learning in soft robotics (249 citations) has become an essential reference in the field. Jo's work on bio-inspired locomotion, egocentric intention detection for wearable robots, and autonomous 3D environmental modeling further illustrates the remarkable breadth of his contributions, making him an influential figure at the intersection of robotics, neurotechnology, and artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1A deep-learned skin sensor decoding the epicentral human motions287 citations · 2020
- 2Review of machine learning methods in soft robotics249 citations · 2021
- 3
- 4
- 5Use of Deep Learning for Characterization of Microfluidic Soft Sensors129 citations · 2018
- 6
- 7
- 8Shape memory alloy-based small crawling robots inspired by <i>C. elegans</i>81 citations · 2011
- 9Surface-Based Exploration for Autonomous 3D Modeling67 citations · 2018
- 10