Asset Yskak
Papers
3
Total Citations
19
H-Index
2
About
Asset Yskak is a robotics researcher whose work focuses on the dynamic control and identification of lightweight bipedal robots, bridging the gap between theoretical models and real-world hardware. Their most significant contribution is a computationally efficient balance control algorithm (2018, 10 citations), which integrates a Linear Inverted Pendulum (LIP) model with sensor-based Zero Moment Point (ZMP) estimation to derive joint-space PD control actions, enabling stable locomotion on resource-constrained platforms. Yskak has also pioneered real-time system identification using reservoir-based Recurrent Neural Networks (2023, 7 citations), demonstrating online adaptation of a nonlinear inverted pendulum model under repeated disturbances—a critical step toward robust, learning-based control. Additionally, they developed a teach pendant for humanoid robotics (2019, 2 citations), featuring a touch-based GUI for both joint-space and Cartesian control. This practical tool underscores Yskak’s commitment to accessible human-robot interaction. With a growing citation record and a focus on computationally light, sensor-driven solutions, Yskak’s work is shaping the future of agile, low-cost bipedal robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3