Papers
6
Total Citations
60
H-Index
4
About
Dae-Shik Kim is a pioneering researcher at the intersection of neurorobotics, computer vision, and brain-computer interfaces (BCI), whose work bridges the gap between biological intelligence and artificial systems. His primary research areas include multi-object tracking, developmental robotics, predictive coding, and robot-assisted rehabilitation. Kim’s most impactful contribution is a real-time multi-class multi-object tracker using YOLOv2 (23 citations), which addresses critical challenges in surveillance and robot vision by enabling simultaneous detection and tracking of diverse objects. He has also made significant strides in imitation learning, exploring how robots can learn goal-directed actions through the RNNPB model (14 citations), and has advanced theoretical frameworks with predictive coding strategies for developmental neurorobotics (8 citations). His recent work on wearable robot-assisted gait training (7 citations) demonstrates practical applications, showing functional and neuroplastic changes in elderly and patient populations. Kim’s 2025 paper on self-supervised transformers for anomaly detection highlights his continued innovation in machine learning. With a career spanning foundational theory to applied rehabilitation technology, his research has garnered over 60 citations, establishing him as a versatile contributor to both cognitive robotics and clinical neuroengineering.
Research Focus
Key Achievements
Top Papers
- 1A real-time multi-class multi-object tracker using YOLOv223 citations · 2017
- 2
- 3Predictive Coding Strategies for Developmental Neurorobotics8 citations · 2012
- 4
- 5
- 6