About Me
Contact
Education
- PhD in Mechanical Engineering, University of Texas at Austin, 2022 - Current
- MS in Robotics, Northwestern University, 2021
- BS in Mechanical Engineering, Saint Louis University, 2020
About Me
Hello! My name is Dongho Kang (DK), and I am a full-stack robotician. I am a Ph.D. Student at the University of Texas at Austin. I am a part of the Human Centered Robotics Lab.
Current Research Topics
- Dexterous Manipulation of Biomimetic Robotic Systems
- Whole-Body Locomanipulation of Humanoid Robots
- Human-Centered Robotic Perception & Navigation
Past Research
During my time at Northwestern University, I focused my research topics on whisker-based tactile sensing, manipulation, and robotic perception. My big interest in robotics comes in developing robots and sensors inspired from animals. My final project Whisker-based Tactile Sensing and Classification at Northwestern focuses on understanding and quantativelt interpreting three-dimensional dynamic data that a rat obtains through whisking over different shapes of objects in a simulation. Rats use whiskers to navigate through holes and find open space. As they scan, their whiskers make unexpected contact with an object, and the rat then explores the object to extract the details of its shape. The use of whisker inputs to detect, localize, and extract the spatial properties of objects. These unique features allow rats to operate in complete darkness1, and I hope to integrate these features into robotics research for robotic navigation.
In neuroscience, we wonder how rats process the mechanosenosry input to determine their actions during active sensing. A rat tends to bring its snout to the object as close as possible while ensuring whiskers contact the object symmetrically, and this project provides reinforcement learnings models that mimic a rat’s active sensing behaviors to investiage the coordinate transformation from the whisker frame to the haed frame through evaulating the weights of each whisker to neurons in the input layer in neural networks of reinforcement learning models.
My Autonomous Fire Fighter Robot Arm project aims integrating a fire safety feature to a common robotic arm manipulator that can be widely used in various settings such as warehouses, garages, and houses. I believe that making robots cope with emergency situations like fire is an important step for robots to operate and cooperate with humans in our daily lives.
References
[1] Hartmann MJ. A night in the life of a rat: vibrissal mechanics and tactile exploration. Ann N Y Acad Sci. 2011 Apr;1225:110-8. doi: 10.1111/j.1749-6632.2011.06007.x. PMID: 21534998.
[2] Robert D. Howe (1993) Tactile sensing and control of robotic manipulation, Advanced Robotics, 8:3, 245-261, DOI: 10.1163/156855394X00356