Michael S. Gashler
Papers
3
Total Citations
325
H-Index
3
About
Michael S. Gashler is a researcher whose work sits at the intersection of machine learning, deep neural networks, and robotics. He is perhaps best known for his widely read 2017 review paper, "Deep Learning in Robotics: A Review of Recent Research," which has accumulated over 317 citations and has become an important reference for those entering the field. In it, Gashler and his collaborators systematically surveyed more than 30 papers examining how deep artificial neural networks can be applied to robotic systems, carefully outlining both the promising capabilities and the practical limitations of these approaches. This contribution helped consolidate a rapidly expanding body of literature into an accessible framework for students and practitioners alike. Complementing this broad survey, his 2016 work on using neural networks to estimate robot state from digital camera images demonstrates a hands-on, applied dimension to his research — tackling the real-world challenge of enabling robots to understand their environment through visual input. Together, these works reflect Gashler's commitment to bridging theoretical advances in deep learning with tangible robotic applications, making him a valuable voice in the ongoing conversation about intelligent autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Deep learning in robotics: a review of recent research317 citations · 2017
- 2Deep Learning in Robotics: A Review of Recent Research5 citations · 2017
- 3