Sovannara Hak

About

Sovannara Hak is a leading researcher in humanoid robotics, specializing in dynamic motion control, task recognition, and human-robot interaction. His most significant contribution is the systematic use of operational-space inverse dynamics (OSID) to enable humanoid robots to perform complex, dynamically consistent movements. This breakthrough was spectacularly demonstrated in October 2012, when his team’s humanoid robot HRP-2 performed a live, fine-balanced dance with a human performer in front of over 1,000 people—a landmark achievement in the field. His work on "Dancing Humanoid Robots" (37 citations) remains a cornerstone reference. Hak also pioneered methods for motion recognition and task identification, allowing robots to interpret human actions by comparing observed motion to candidate controllers. His research on "Reverse Control for Humanoid Robot Task Recognition" (23 citations) and "Dynamic motion capture and edition using a stack of tasks" (22 citations) has been widely cited for its practical impact. Additionally, his development of a generalized projector for task priority transitions during hierarchical control (14 citations) provides a flexible framework for managing complex, multi-priority tasks in redundant robots. Hak’s work bridges the gap between human motion and robotic execution, advancing the frontier of autonomous, interactive humanoid robots.

Research Focus

Key Achievements

Top Papers

1. 1
   Dancing Humanoid Robots: Systematic Use of OSID to Compute Dynamically Consistent Movements Following a Motion Capture Pattern

   37 citations · 2015
2. 2
   Reverse Control for Humanoid Robot Task Recognition

   23 citations · 2012
3. 3
   Dynamic motion capture and edition using a stack of tasks

   22 citations · 2011
4. 4
   Generalized projector for task priority transitions during hierarchical control

   14 citations · 2015
5. 5
   Humanoid robot task recognition from movement analysis

   4 citations · 2010

Key Collaborators

Contact & Links