Steve Grehl
Papers
7
Total Citations
162
H-Index
6
About
Steve Grehl is a robotics researcher whose work spans human-robot interaction, autonomous mobile robotics, and machine learning-based force estimation. His most influential contribution, "A system for learning continuous human-robot interactions from human-human demonstrations" (2017, 69 citations), introduced a data-driven imitation learning framework that enables robots to replicate natural interaction dynamics observed between humans — a significant step toward more intuitive collaborative robotics. Complementing this, his work on torque and force estimation using neural networks and proprioceptive models addresses the practical challenge of endowing robots with force awareness without costly dedicated sensors, accumulating over 20 citations across multiple publications. Grehl has also made a notable mark in the specialized domain of underground mining robotics. His 2018 paper designing an autonomous robot for mapping, navigation, and manipulation in mines (47 citations) tackled the uniquely harsh subterranean environment, where conventional sensors and systems routinely fail. This work, extended in subsequent research on IoT-integrated safety systems, positions him as a leading voice in applying autonomous robotics to dangerous industrial settings. Across his career, Grehl's research consistently bridges machine learning and real-world robotic deployment, emphasizing safety, adaptability, and human-centered design.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Increased safety in deep mining with IoT and autonomous robots16 citations · 2019
- 4Experience-based torque estimation for an industrial robot13 citations · 2016
- 5
- 6Research perspective - mobile robots in underground mining7 citations · 2017
- 7Deep Learning of Proprioceptive Models for Robotic Force Estimation2 citations · 2019