Yiting Kang
Papers
4
Total Citations
37
H-Index
4
About
Yiting Kang is a robotics researcher specializing in motion planning, terrain identification, and adaptive control for mobile robots. His work addresses fundamental challenges in autonomous robot navigation, particularly in unstructured and demanding real-world environments. Kang's most influential contribution, "Smooth-RRT*" (2021, 12 citations), introduced a novel reconnection method that extends the widely used RRT* algorithm to generate smooth, curved trajectories while satisfying kinodynamic constraints — a significant advancement for practical robot deployment. Complementing this, his self-adaptive path tracking framework (2021, 7 citations) leverages radial basis function neural networks to counteract slippage disturbances, addressing a critical limitation of wheeled robots in field conditions. His terrain identification research further demonstrates his breadth of expertise. Through both an integrated multi-sensor framework (2020, 10 citations) and a learning-based proprioceptive approach (2020, 8 citations), Kang developed methods that combine inertial and current signals to robustly classify terrain and predict driving torque with high accuracy — capabilities essential for intelligent autonomous control of tracked platforms. Collectively, Kang's body of work, accumulating nearly 40 citations across recent publications, reflects a cohesive research vision: enabling mobile robots to navigate complex environments safely, smoothly, and intelligently.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4