Batbold Myagmarjav

About

Batbold Myagmarjav is a researcher focused on advancing human-robot collaboration through intelligent knowledge acquisition systems. His work centers on enabling robots to learn from non-expert humans in real-world settings, addressing the critical challenge of handling unforeseen situations without requiring extensive pre-labeled data. Myagmarjav’s major contributions include developing an architecture for incremental knowledge acquisition that uses selective active learning, where robots generate and rank candidate questions based on contextual information, information gain, ambiguity, and human confusion. This approach maximizes the utility of human responses, allowing robots to efficiently expand their domain knowledge during interaction. His most cited paper, "Incremental knowledge acquisition for human-robot collaboration" (2015), has garnered 5 citations, with two additional papers from the same year each receiving 2 citations. While his citation counts reflect a niche but growing field, Myagmarjav’s work is notable for its practical focus on making robots adaptable and accessible for collaboration with non-experts, a key step toward deploying autonomous systems in dynamic, everyday environments. His research bridges machine learning and robotics, offering a foundation for more intuitive human-robot partnerships.

Research Focus

Key Achievements

Top Papers

1. 1
   Incremental knowledge acquisition for human-robot collaboration

   5 citations · 2015
2. 2
   Incremental Knowledge Acquisition with Selective Active Learning

   2 citations · 2015
3. 3
   Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction

   2 citations · 2015

Key Collaborators

Contact & Links