Samuel Looper

Papers

Total Citations

H-Index

About

Samuel Looper’s research lies at the intersection of robotics, computer vision, and long-term scene understanding, with a focus on enabling autonomous systems to operate intelligently in dynamic, human-shared environments. His most cited work, “3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs” (2023, 26 citations), introduces a pioneering framework that models and predicts semantic changes in 3D spaces over extended periods—a critical capability for robots that must adapt to evolving surroundings alongside humans or other agents. This contribution addresses a fundamental gap in robotic perception, moving beyond static mapping to anticipate how scenes transform. In “Temporal Convolutions for Multi-Step Quadrotor Motion Prediction” (2022, 8 citations), Looper adapts Temporal Convolutional Networks to generate accurate, long-horizon predictions of complex nonlinear dynamics for systems like quadrotors and autonomous vehicles, advancing model-based control. His work is notable for bridging semantic reasoning with temporal modeling, offering practical tools for long-term autonomy. With growing citations and a clear trajectory toward impactful, real-world applications, Looper is establishing himself as a rising voice in robotics research, particularly for tasks requiring foresight in shared, changing environments.