Gi Hyun Lim

About

Gi Hyun Lim is a leading researcher in cognitive robotics, whose work bridges the gap between artificial intelligence and autonomous service robots. His primary research areas encompass robot knowledge representation, lifelong learning, and semantic perception for intelligent systems. Lim’s foundational contributions include the development of the Ontology-Based Unified Robot Knowledge framework (cited over 164 times), which enables service robots to reason about complex indoor environments by structuring perceptual, model, activity, and context knowledge. He further advanced the field with the Ontology-based Multi-layered Robot Knowledge Framework (OMRKF, 77 citations), providing a layered architecture for robot intelligence. Notably, his work on “Towards Lifelong Assistive Robotics” (56 citations) demonstrates a tight coupling between object perception and manipulation, allowing robots to continuously adapt and learn from interaction. Lim has also pioneered interactive, open-ended learning for 3D object recognition (42 citations) and perceptual memory systems for grounding semantic representations (32 citations). Through projects like RACE and innovations in Bayesian robot localization using spatial object contexts, Lim has established himself as a key figure in creating robots that can learn, reason, and operate autonomously in dynamic human environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Ontology-Based Unified Robot Knowledge for Service Robots in Indoor Environments

   164 citations · 2010
2. 2
   Ontology-based multi-layered robot knowledge framework (OMRKF) for robot intelligence

   77 citations · 2007
3. 3
   Towards lifelong assistive robotics: A tight coupling between object perception and manipulation

   56 citations · 2018
4. 4
   Interactive Open-Ended Learning for 3D Object Recognition: An Approach and Experiments

   42 citations · 2015
5. 5
   A perceptual memory system for grounding semantic representations in intelligent service robots

   32 citations · 2014
6. 6
   The RACE Project

   25 citations · 2014
7. 7
   Bayesian robot localization using spatial object contexts

   23 citations · 2009
8. 8
   Interactive teaching and experience extraction for learning about objects and robot activities

   22 citations · 2014
9. 9
   Concurrent learning of visual codebooks and object categories in open-ended domains

   20 citations · 2015
10. 10
    Active-semantic localization with a single consumer-grade camera

    20 citations · 2009

Key Collaborators

Contact & Links