S. Maharlevan
Papers
1
Total Citations
16
H-Index
1
About
S. Maharlevan is a researcher in robotics and artificial intelligence, with a primary focus on probabilistic modeling and autonomous navigation in complex, partially observable environments. Their most notable contribution is the development of hierarchical observable Markov decision process (HOMDP) models, as detailed in their 2002 paper "Learning hierarchical observable Markov decision process models for robot navigation." This work introduced a general framework using hierarchical hidden Markov models (HHMMs) to efficiently represent and learn the structure of environments like office buildings, enabling robots to navigate more effectively under uncertainty. By exploring hierarchical modeling, Maharlevan laid the groundwork for more scalable and computationally efficient methods in model construction for robotics, addressing key challenges in real-world deployment. Their research has garnered 16 citations, reflecting its foundational impact on the field. Maharlevan's work continues to influence advancements in robot navigation and hierarchical reinforcement learning, offering valuable insights for students and researchers seeking to build intelligent systems that operate in dynamic, partially known spaces.
Research Focus
Key Achievements
Top Papers
- 1