Ki-Sung Kim

About

Ki-Sung Kim is a robotics researcher whose work focuses on terrain classification and adaptive locomotion for legged robots, particularly quadruped platforms. His key research areas include machine learning for robotics, gait transition strategies, and field robotics. Kim’s major contributions lie in developing robust terrain classification methods that enable legged robots to dynamically adjust their gait and movement patterns based on surface conditions—a critical capability for autonomous operation in unstructured outdoor environments. His most cited work, "Performance comparison between neural network and SVM for terrain classification of legged robot" (2010, 13 citations), systematically evaluated machine learning approaches for identifying terrain types, establishing foundational benchmarks for the field. In his subsequent study, "Terrain Classification Strategy of a Quadruped Robot for Gait Transition and Adaptation in a Field Terrain" (2012), Kim proposed a practical framework for integrating terrain sensing with real-time gait modulation, directly addressing the challenge of maintaining stability and efficiency across diverse surfaces. While his citation counts reflect the specialized nature of his research, Kim’s contributions have influenced the design of more adaptive and resilient legged robots, supporting advancements in search-and-rescue, exploration, and agricultural robotics.

Research Focus

Key Achievements

Top Papers

1. 1
   Performance comparison between neural network and SVM for terrain classification of legged robot

   13 citations · 2010
2. 2
   Terrain Classification Strategy of a Quadruped Robot for Gait Transition and Adaptation in a Field Terrain

   2 citations · 2012

Key Collaborators

Contact & Links