Papers
3
Total Citations
33
H-Index
3
About
Shike Long is a robotics researcher specializing in safe physical human-robot interaction, with a particular focus on sensorless collision detection and torque estimation for collaborative robots. Their major contributions center on developing advanced momentum observers that overcome the traditional trade-off between collision sensitivity and robustness. Long’s most cited work, “A Novel Sliding Mode Momentum Observer for Collaborative Robot Collision Detection” (2022, 18 citations), introduces an innovative approach that eliminates the need for additional sensors, making collision detection both economically feasible and highly responsive. Building on this foundation, Long proposed FOESO-Net (2023, 8 citations), a specialized neural network that enables fast, sensorless torque estimation for robot manipulators, bridging model-based and data-driven methods. Their 2023 work on an improved adaptive super-twisting momentum observer (7 citations) further enhances estimation accuracy under varying operational conditions. Long’s research directly addresses critical safety requirements in human-robot collaboration, offering practical solutions for industrial and service robotics. By systematically advancing observer-based collision detection and torque estimation, Long has established a clear trajectory toward safer, more intuitive physical human-robot interaction without compromising performance or cost efficiency.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3