Willow Garage Blog

Our founder Scott Hassan challenged the PR2 Beta Site participants to get the PR2 to "do something cool, funny, or useful." To be fair to advisors and bosses, entrants were also told that the "competition should not interfere with your work or research duties."

What could these sites do in a short period of time? Checkout the results below.

First Place ($5000): Sockification, Berkeley: Ping Chuan Wang, Stephen Miller, Mario Fritz, Trevor Darrell, Pieter Abbeel

Second Place ($3000): Mailman, Bosch: Ben Pitzer

Third Place ($2000): PR2 Band, University of Pennsylvania: Ben Cohen, Daniel Benamy and Mike Phillips

Other entries

• PR2 StrongBOT, Georgia Tech
• Towel Folding, Social Network Edition, Berkeley
• Book Bot, MIT
• Checkout Bot, Stanford
• Self Portrait, Bosch
• PR2 Darumasan, JSK
• Painter, KU Leuven
• Head tracking, Penn

One of the new features in ROS C Turtle was a critical component of our recent "hackathons."  When fetching a drink out of a refrigerator, for example, a robot has to perform numerous tasks such as grasping a handle, opening a door, and scanning for drinks.  These tasks have to be carefully orchestrated to deal with unexpected conditions and errors. We've previously used complex task-planning systems to orchestrate these actions, but our developers and researchers needed something more rapid for prototyping robot behaviors.

One of our interns came up with an answer.  SMACH ("State MACHine", pronounced "smash") is a task-specification and coordination architecture that was developed by Jonathan Bohren as part of his second internship here at Willow Garage. Jonathan came to us from the GRASP Lab at University of Pennsylvania and is now headed off to the Laboratory for Computational Sensing and Robotics (LCSR) at Johns Hopkins.  During his extended stay here, SMACH was used in a variety of PR2 projects.

SMACH was first used in the rewrite of our plugging and doors code, then further refined during our billiards, cart-pushing, and drink-fetching hackathons. In all of these projects, the ability to code these behaviors quickly was critical, as was the ability to create more robust behaviors for dealing with failure.

SMACH is a ROS-independent Python library, so it can be used with and without ROS infrastructure. It comes with important developer tools like a visualizer for the current SMACH plan and introspection tools to
monitor the internal state and data flow. There are already many SMACH tutorials that can be found on the ROS wiki, and we hope to see SMACH used to produce many more cool robotics apps!

This fourth installment features both aerial and indoor robots, as well research and commercial:

• Penn Quadrotors: ROS is now being used in robots that fly. ROS communication and modular infrastructure is being used by researchers at Penn to help their aerial robots perform "aggressive" manuevers.
• Robotino: the Robotino platform, which is distributed Festo Didactic and developed by REC, now has a complete set of ROS drivers, including support for the ROS navigation stack.
• Shadow Dextrous Hand: Shadow Robot's dextrous hand now comes with ROS software for both real and simulated hardware.
• Wash U's B21r and ERRATICs: The Media and Machines Lab at Washington University uses ROS to power their iRobot B21r and have shared their drivers with the rest of the iRobot/RWI community. Wash U also uses ROS to power their fleet of Videre ERRATICs and iRobot Creates.

Previously Part I, Part II, Part III:

• TUM-Rosie: TU München built a Kuka-based mobile manipulation platform to research robots with a high-degree of cognition.
• CKbots: the Modlab's small, modular robots are too small to run ROS themselves, but they can connect to a ROS system to test algorithms that need a bit more horsepower.
• Marvin: the autonomous car from Austin Robot Technology and UT Austin competed in the DARPA Urban Challenge and has now been ported to ROS.
• HERB: the mobile manipulator, based on a Segway RMP200 and Barrett arm, was built to be a "robotic butler" and is used as a collaboration between Intel Pittsburgh and Carnegie Mellon University.
• Care-O-bot 3: Fraunhofer IPA's mobile manipulation platform has broad support for ROS. The accompanying open-source repository includes everything from device drivers to simulation in Gazebo.
• Bosch RTC's robot: Bosch RTC's Segway RMP-based robot has been used to develop new ROS libraries, including an exploration stack.
• EL-E and Cody: Georgia Tech's Healthcare Robotics Lab has released drivers and has also released code to accompany research papers.
• Kawada HPR2-V: the JSK Lab at Tokyo University has integrated this omni-directional variant of the HRP-2 with the ROS navigation stack.
  
• Prairie Dog: the Correll Lab at Colorado University uses this iRobot Create-based platform for teaching and research.
  
• STAIR 1: the Stanford University mobile manipulation research platform that provided the predecessor of the ROS framework.
• Aldebaran Nao: a small, commercially available humanoid robot that demonstrated the ability of the ROS community (Brown University and University of Freiburg) to come together and develop open source drivers.
• i-Sobot: an even smaller humanoid robot controlled by the ROS PS3 joystick driver. The developer has been publishing a Japanese-language blog on ROS, helping ROS reach new audiences.
• Junior: Stanford Racing's autonomous car that finished a close second in the DARPA Urban Challenge. Junior's main software framework is IPC, but ROS's modular libraries have made it easy to integrate ROS-based perception libraries into their obstacle classification system.