Sam Prentice

Papers

Total Citations

175

H-Index

About

Sam Prentice is a robotics researcher whose work sits at the intersection of machine learning, probabilistic modeling, and legged robot locomotion. He is best known for his pioneering contributions to terrain modeling for legged robots, developing sophisticated Gaussian process-based techniques that allow autonomous systems to learn and update representations of complex environments from sparse, noisy sensor data. His 2008 paper, "Learning Predictive Terrain Models for Legged Robot Locomotion," has garnered 81 citations and remains a foundational reference in the field, demonstrating how sparse approximation methods can make probabilistic terrain modeling computationally tractable. Complementing this, his Bayesian regression approach to terrain mapping further refined these ideas by introducing nonstationary Gaussian processes capable of capturing the irregular, heterogeneous nature of real-world surfaces. Alongside his terrain modeling work, Prentice made significant contributions to motion planning for quadruped robots, developing kinodynamic planning methodologies that enable high-impedance robotic systems to reliably navigate diverse and challenging terrains — from dynamic lunging maneuvers to careful deliberate stepping. With over 175 cumulative citations across his key publications, his research has meaningfully advanced the field of autonomous legged locomotion and continues to inform both academic and applied robotics research.