Young children mimic everything they see and hear around them—sometimes to comic effect. While learning from observed behaviors comes naturally to children, it’s a different story for robots. For a robot to learn to perform a task, one effective way is to define the geometric null space—the set of poses needed for the skill—and its constraints. Together, these form a mathematical representation of the skill that can be performed by any robot in any environment.
Read how A*STAR's researchers come together and develop a versatile framework that enables robots to learn from human demonstrators via six basic skills: Grasp, Place, Move, Pull, Mix and Pour.
The A*STAR-affiliated researchers contributing to this research are from the Institute of High Performance Computing (IHPC), Institute for Infocomm Research (I2
R) and Advanced Remanufacturing and Technology Centre (ARTC).
Read the full article published on A*STAR Research