Samuel J. Hudson
Papers
2
Total Citations
9
H-Index
2
About
Samuel J. Hudson is a robotics researcher specializing in bipedal locomotion and humanoid safety systems. His primary contributions lie in energy-efficient walking pattern generation and fall mitigation strategies for humanoid robots. Hudson’s most influential work, "Normalized Neural Network for Energy Efficient Bipedal Walking Using Nonlinear Inverted Pendulum Model" (2019, 7 citations), introduces a novel approach that leverages a deep neural network to bypass the computational burden of solving nonlinear dynamics online. By optimizing control variables for a 2D inverted pendulum model, his method achieves significantly more energy-efficient gait generation, a critical advancement for autonomous robots with limited power resources. In his subsequent work, "An Upper Limb Fall Impediment Strategy for Humanoid Robots" (2020, 2 citations), Hudson explores proactive upper-limb movements to reduce impact forces during falls, addressing a key safety challenge in humanoid deployment. Though early in his career, his integration of neural networks with classical biomechanical models marks a notable step toward practical, low-power humanoid locomotion. Hudson’s research bridges theoretical control theory and applied machine learning, offering a foundation for safer, more efficient bipedal robots in real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2An Upper Limb Fall Impediment Strategy for Humanoid Robots2 citations · 2020