Papers
1
Total Citations
14
H-Index
1
About
Adam Polevoy is a robotics researcher whose work focuses on enabling robots to navigate complex, unstructured environments—particularly deformable terrain where traditional geometric mapping approaches fall short. His most-cited paper, "Complex Terrain Navigation via Model Error Prediction" (2022, 14 citations), introduces a novel paradigm: rather than building an explicit map, robots learn to predict and compensate for model errors in real time, allowing them to traverse surfaces like mud, snow, or leaf litter that would otherwise be mischaracterized as impassable obstacles. This work directly challenges the rigidity assumptions of classical navigation, offering a more adaptive, robust framework for field robotics. Polevoy’s contributions are especially impactful for applications in planetary exploration, disaster response, and off-road autonomous driving. By shifting focus from geometric mapping to predictive error modeling, he provides a scalable solution for robots operating in the wild. His research bridges perception, control, and learning, and his citation record—while still early—reflects growing recognition of this practical, problem-driven approach to real-world robot autonomy.
Research Focus
Key Achievements
Top Papers
- 1Complex Terrain Navigation via Model Error Prediction14 citations · 2022