Rachel Gardner

Michigan State University, Nvidia (United States), Stanford University

Papers

Total Citations

H-Index

About

Rachel Gardner’s research bridges the foundational economics of automation with cutting-edge advances in robotic learning and perception. Her early work, “Economics of robot application” (1997, 55 citations), established a framework for analyzing the cost-benefit dynamics of industrial robotics, providing a lasting reference for scholars studying technology adoption. Two decades later, Gardner pivoted to reinforcement learning (RL) for contact-rich manipulation, where her 2019 paper (29 citations) introduced variable impedance control in end-effector space as a novel action space—a critical insight that addressed a gap in RL research, which had largely overlooked how action representation impacts task success. Most recently, her 2022 work (11 citations) on vision-only robot navigation within Neural Radiance Fields (NeRFs) demonstrates her ability to integrate emerging 3D scene representations into autonomous systems, enabling robots to navigate complex, natural environments using only visual input. Gardner’s career trajectory—from economic modeling to state-of-the-art robotics—reflects a rare interdisciplinary depth, and her contributions continue to influence both the theoretical underpinnings and practical deployment of intelligent robotic systems.