Robotics@SNU

Research
- Design and Development of
   FLEA

- Omegabot: Inchworm inspired
   robot

- Large deformable morphing
   structure:Flytrap-inspired
   robot

- Wearable robotic hand
- Hands on surgical robot:
   Shared control system
- Situation Understanding for
   Smart Devices

- Wireless Camera Sensor
   Networks Technology

- Mobile Sensor Networks:
   Algorithms and Applications
- Whole-Body Control Framework
    for Humanoid Robot

- Walking Pattern Generation for
   Humanoid Robot

- Robot Hand Control
- Quadruped Robot Control with
   Whole-Body Control Framework

- Human Gait Analysis using
   3D Motion Capture
- Coordination of multiple robots
- Flocking and consensus
- Vision-based guidance and
   navigation

- Online collision avoidance for
   mobile robots

- Wireless sensor network
- Aerial Manipulation
- Haptics/VR
- Autonomous Mobility
- Telerobotics
- Mechanics/Control
- Industrial Control
- Mobile Manipulation
- Simultaneous Visual and
   Inertia Calibration

- Mechanics of Closed Chains
- Motion Optimization via
   Nonlinear Dimension
   Reduction

- Probabilistic Optimal Planning
   Algorithm for Minimum
   upstream Motions

- Automated Plug-In Recharging
   System for Hybrid Electric
   Vehicle
Motion Optimization via Nonlinear Dimension Reduction
Nonlinear dimension reduction techniques from machine learning can be exploited to determine dynamically optimal motions for high degree of freedom systems. Using the Gaussian Process Dynamical Model (GPDM) to learn the low-dimensional embedding, and a density function that provides a nonlinear mapping from the low-dimensional latent space to the full-dimensional pose space, we determine optimal motions by optimizing in the latent space, and mapping the optimal latent space trajectory to the pose space. space. The notion of variance tubes are developed to ensure that kinematic and other constraints are appropriately satisfied without sacrificing naturalness or richness of the motions.

For more information, visit the lab webpage.

jhp9395@robotics.snu.ac.kr, 02-880-7149