Perception for Robotics
Caroline Pantofaru, Willow Garage
Biography: Dr. Caroline Pantofaru joined Willow Garage in September 2008 as a Research Scientist in the area of computer vision. Her current focus is on perceiving people, from detecting people to tracking to human activity recognition. Understanding the locations, actions and intentions of humans in its proximity will allow a robot to more successfully interact with its world, both by not startling or crashing into people, and by helping people with various tasks. Human activity recognition can also contribute to other areas of research. For example, there are many objects in the world, such as chairs, that are not defined by their visible physical properties but rather by how people use them. Understanding people's actions can improve recognition of these sorts of objects.
In addition to the task of perceiving people, Dr. Pantofaru's research interests include object recognition, especially in using the rich contextual information available to a robot, as well as learning from large datasets such as the Internet, which can provide a robot with a wealth of information before it even opens its eyes.
Dr. Pantofaru completed her Ph.D. at The Robotics Institute, Carnegie Mellon University in May 2008 under the supervision of Martial Hebert. She also spent some time in Cordelia Schmid's group at INRIA in Grenoble, France. Her thesis, titled Studies in Using Image Segmentation to Improve Object Recognition, focused on issues related to using the image regions generated by unsupervised image segmentation to recognize objects and accurately identify their shape, especially in a weakly supervised training scenario where accurate object outlines are unknown.
