|
Winter Quarter 2013
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||
Thursday, January 24th
This tour will be held at Willow Garage in Menlo Park. The class will convene in the front lobby at 4:30pm. Due to space limitations, it is open to enrolled students only. Abstract: Willow Garage develops hardware and open source software for personal robotics applications. Willow Garage's employees are a team of experts in robot design, control, perception, and machine learning, with both a strong theoretical background and a demonstrated drive to produce practical systems. Approximately one third are robotics researchers whose specialties include: grasping/manipulation, human-robot interaction, motion planning, perception, and task planning. Researchers provide an institutional expertise to ensure that Willow Garage stays at the technological forefront of the many depth expertise areas represented in robotic technologies. Willow Garage is only one part of the open-source robotics community. They focus their efforts in ways that will make the entire community more productive. Willow Garage actively engages research labs and companies as partners, collaborators, customers and advisors in the development of both their hardware platform and open source software. Willow Garage also supports researchers who would not otherwise have the bandwidth or funding to open source their work. Biosketches: Dave Robson is the Chief of Staff at Willow Garage. Matei Ciocarlie is a Research Scientist and Area Lead at Willow Garage, focusing on areas such as autonomous and Human-in-the-Loop mobile manipulation, shared autonomy and teleoperation, assistive robotics, and novel hand design and control. His main interest is in reliable robotic performance in unstructured, human environments, looking to add new capabilities to mobile manipulators and to make contributions to ROS, the open source Robot Operating System. He is also interested in novel hand designs that allow part of the effort of finding a stable grasp to be performed at a mechanical rather than computational level, and make use or tactile, proprioceptive or range sensing in novel ways. Kaijen Hsiaso is a Research Scientist at Willow Garage, working on grasping, manipulation, and planning under uncertainty. Kaijen's current focus is on reactive grasp adjustment and reasoning about uncertainty and geometric constraints while doing pick-and-place operations. Her overall goal is to make robots less clumsy in unstructured environments (like your home). This requires careful reasoning about the current state of the world and its uncertainties and constraints (Where is the object I want to pick up? Maybe it's over here instead? Or maybe it's not quite the shape I thought it was. Did it shift around in my hand after I grasped it?) as well as the likely results of actions given those uncertainties and constraints (Am I likely to knock this object over because I'm not sure precisely where it is? Can I still put it in this little cubby-hole if I pick it up this way?). Reasoning explicitly about uncertainty and geometric constraints is especially necessary for fiddly tasks that require precision, like grasping objects by their handles, using tools, or performing assembly tasks. Kaijen received her PhD in Computer Science from MIT in 2009, under the supervision of Tomas Lozano-Perez and Leslie Kaelbling. Her thesis, "Relatively Robust Grasping," studied how grasping can be made more robust using touch sensing, in the face of significant object pose uncertainty. The thesis proposes the use of POMDP models for manipulation, which allow the robot to intelligently select actions that gather information until certain that the grasp will succeed with high probability. Kaijen has also worked on using IR fingertip sensors for reactive grasping, grasp adaptation, and imitation learning of grasp trajectories. Henry Evans is a non-vocal Los Gatos resident with quadriplegia as a result of a stroke when he was just 40 years old. Following extensive therapy, Henry has regained the ability to move his head and use a finger, which allows him to operate computers. PR2 (Personal Robot 2) is Willow Garage's first major robot. It is a two-armed wheeled robot of human size that has two 7-DOF arms with a payload capacity of 1.8 kg. Sensors include a 5-megapixel camera, a tilting laser range finder, and an inertial measurement unit. The "texture projector" projects a pattern on the environment to create 3D information for capture by the cameras. Its head-mounted laser scanner measures distance by time-of-flight. The two computers located in the base are 8-core servers with 24 Gigabytes of RAM each. Sixteen laptop batteries power PR2.
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||
