John G. Rogers
Papers
1
Total Citations
56
H-Index
1
About
John G. Rogers is a robotics researcher specializing in autonomous navigation, off-road vehicle traversability, and self-supervised learning for robotic systems. His work addresses one of the fundamental challenges in field robotics: enabling robots to intelligently reason about complex terrain interactions without requiring extensive manual labeling efforts. His most notable contribution, "How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversability" (2023), has garnered 56 citations and represents a significant advance in how autonomous ground vehicles perceive and assess unstructured environments. By leveraging self-supervised learning techniques, Rogers and his collaborators developed methods that allow robots to generate their own informative training signals from physical interaction data, dramatically reducing the burden of human annotation while improving the richness of terrain assessment. This research has meaningful implications for autonomous vehicles operating in challenging real-world conditions such as military, agricultural, and search-and-rescue contexts. Rogers' work sits at the intersection of machine learning and field robotics, contributing practical solutions that push the boundaries of what autonomous systems can accomplish in unstructured, off-road settings.
Research Focus
Key Achievements
Top Papers
- 1