Papers
2
Total Citations
30
H-Index
2
About
Shi Chang is pioneering the integration of transformer-based deep learning into robot-assisted surgery (RAS), with a focused mission to make surgical robots more intelligent, predictive, and responsive to human intent. His core research spans surgical activity recognition, trajectory prediction, and haptic guidance—areas critical for advancing autonomous assistance in the operating room. In his highly cited 2022 work, Chang introduced transformer models to recognize and predict surgical gestures and trajectories in RAS, achieving 23 citations and establishing a new paradigm for long-horizon surgical context inference. Building on this, his 2023 study proposed a transformer-based surgeon-side trajectory prediction algorithm that enables haptic guidance during surgical training, a breakthrough for real-time, intent-aware robotic assistance. By enabling robots to anticipate a surgeon’s next move and provide corrective haptic feedback, Chang’s work directly addresses the challenge of long-horizon inference in teleoperation. His contributions are shaping the future of surgical skill evaluation, shared control, and autonomous training systems, positioning him as a rising leader at the intersection of machine learning and surgical robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2