Willow Garage Blog
Last year, the production team from Lion Television descended on the Willow Garage office for a day of intensive filming. Lion Television is a top-notch independent production company and they were hard at work on America Revealed. America Revealed Website
Host Yul Kwon the production team got the know our company and the PR2 pretty well.
Photo Credit: PBS
America Revealed is a four-part PBS series that has been looking at the systems and networks that keep America running. With the first three episodes already aired, Willow Garage plays a role in the final episode, "Made in the USA." This episode examines the fact that the United States is actually the number one manufacturing nation on Earth, and what manufacturing looks like in the U.S. in the future.
The show airs in the Bay Area on KQED this Wednesday, May 2 at 10:00 pm. To check the local listing in your area, please click here America Revealed Schedule
Part of the day involved our PR2 robot taking one of the company dogs for a walk.
Photo Credit: Willow Garage
We're very curious to see whether this will survive the editing process.
The segment did air. You can watch it here on the PBS website.
The history of open source is replete with significant moments in time, and today Willow Garage would like to humbly submit our own milestone -- the announcement of the Open Source Robotics Foundation. As Willow Garage has worked to grow and shepherd ROS within the robotics world our hope was that ROS would one day stand on its own. With the announcement today of the OSR Foundation, that day is finally here.
The mission of the OSR Foundation is "to support the development, distribution, and adoption of open source software for use in robotics research, education, and product development." You will find this mission on the new OSR Foundation Web site, but not much else. In the coming weeks, we will be expanding on our goals, our short- and long-term plans, and the individuals and organizations that will be leading the OSR Foundation. For now, contact OSRF for more information or to get involved.
The first initiative of the OSRF will be participation in the DARPA Robotics Challenge, announced recently. The DARPA Robotics Challenge, or DRC, will launch in October 2012 and offers a $2 million prize "to whomever can help push the state-of-the-art in robotics beyond today’s capabilities in support of the DoD’s disaster recovery mission." The full announcement of the initiative specifically mentions the Fukushima nuclear accident as a recent example of a potential robotic application although other recent disasters such Hurricane Katrina and the oil spill at Deepwater Horizon also quickly come to mind.
DARPA today sponsored a Proposer's Day Workshop where more information about the Robotics Challenge is available via Webcast. During the Webcast, Nate Koenig from Willow Garage gave a brief talk on the current and future state of the open source Gazebo robot simulator, which will be extended by the OSR Foundation to support the DARPA Robot Challenge.
The DARPA Robotics Challenge supports the National Robotics Initiative announced by the Obama Administration in June 2011.
The folks from Oddwerx came to Willow Garage for a visit recently. For those who aren't already familiar with Oddwerx, it is a very cool initiative to turn an iPhone or Android phone into an autonomous robot.
In the first video you can see how Ted Larson, Bob Allen and Brandon Blodget from Oddwerx took a PS3 Game Controller and plumbed it together to send its ROS messages to an Oddwerx Robot running its own ROS node for controlling the motors and legs. They took advantage of the existing ROS packages which support interacting with the PS3 joystick, which is in use on many robots including the PR2.
Fashion was front and center in this second video when the Oddwerx robot "grew" purple hair. In addition to responding to PS3 ROS messages, the robot was programmed to send audio/video to enable teleoperation. Since ROS employs publish/subscribe, multiple subscribers can just listen into the live video feed.
Oddwerx is now a Kickstarter project. If you share their vision to turn smartphones into mobile robotic ROS platforms, then support this effort on Kickstarter.
The National Science Foundation's (NSF) recently announced four new "Expeditions in Computing" awards and we are proud to announce Willow Garage's involvement in one of the winning awards. The NSF's Directorate for Computer and Information Science and Engineering (CISE) has awarded $10 million in funding over five years in support of Making Socially Assistive Robots, also known as Robots Helping Kids. This initiative will be developing the techniques that will enable the design, implementation, and evaluation of robots that encourage social, emotional and cognitive growth in children.
For example, clinicians and families struggle to provide individualized educational services to children with social and cognitive deficits; a group whose numbers have quadrupled in the U.S. in the last decade alone. In addition, educators struggle at many schools to provide language instruction for children raised in homes where a language other than English is spoken, the fastest-growing segment of the school-age population.
Robots Helping Kids aims to support the individual needs of children with socially assistive robots that help to guide the children toward long-term behavioral goals that are customized to the particular needs of each child and that develop and change as the child does.
Needless to say, socially assistive robots have the potential to substantially impact the effectiveness of education and healthcare for children. This initiative includes strong education and training elements, especially for K-12 students in this target population, and for undergraduates via an annual training summit.
The Lead Principal Investigator for this initiative is Brian Scassellati from Yale University who is joined by Co-PIs Maja Matarić of USC and Cynthia Breazeal from MIT. A host of other individuals are also involved from Stanford University, Tufts University, and Yale University. Leila Takayama leads Willow Garage's involvement. Dr. Takayama will partner with Stanford University's Clifford Nass in the evaluation of the initiative. Their responsibility is determining the efficacy of the methods and systems for generating insights into human social abilities via these robotic systems.
Willow Garage would like to congratulate not only our partners in the Robots Helping Kids initiative, but all of the NSF award recipients. A complete list of the recipients is listed at the NSF Web site.
The list of PR2 owners gets longer and more impressive every day. PR2 continues to push the frontiers and is now on it's way to yet another continent. The University of Technology, Sydney (UTS) is now the proud owner of a PR2. Professor Mary-Anne Williams and her team have already spent a few weeks at Willow Garage working on the robot and preparing for the trip back to New South Wales, Australia. Professor Williams directs the Magic Lab at UTS and Associate Dean (Research and Development) in the Faculty of Engineering
At Carnegie Mellon University, Search-based Planning Lab (SBPL) led by Maxim (Max) Likhachev also has his hands on a new PR2. The group has already worked with the PR2 and ROS when Max was at the GRASP lab of University of Pennsylvania. Max's group will be using the PR2 to continue their research on real-time decision-making and motion planning for robots working in complex environments.
Cornell University has a new PR2 named Kodiak, which is joining the Personal Robotics Lab. Assistant Professor Ashutosh Saxena's research focuses on the ability of robots to operate autonomously in unstructured human environments. Professor Saxena will be providing PR2 with the basic skills of recognizing human activities, scene understanding, grasping and placing objects, and more. The PR2 will then be used in initiatives such as arranging a disorganized house, find and fetch items on request, putting items in a fridge, and more.
Lastly, another PR2 now calls Germany its home. (There is already one in Freiburg and another at TUM.) This time under the direction of Professor Jianwei Zhang, Director of the Department of Informatics at the Institute of TAMS (Technical Aspects of Multimodal Systems) at the University of Hamburg. The goal at TAMS is to develop methods and implement integrated real-time systems for acquiring, processing and applying information from multiple channels like robotic vision, speech and sound, touch through action, and more.
Robot stuck? Is your program clogged up with imaginary obstacles? Never fear, you're in the clear because Reset It!™ is here!
The family of Reset It!™ apps for your Android phone instantly fix a variety of demo problems:
- Reset It Collision Map!™
- Reset It Cost Map!™
- Reset It Kinect!™
- Reset It Planning Scene!™
- Reset It Attached Objects!™
For a limited time, we'll throw in Reset It All!™, which includes all of the above apps plus patented ResetBoot™ technology to guarantee a 100% reset.
Get Reset It!™ now and your next flawless demo is just a tap away.
Motion planning is necessary to allow robots to move safely in real human environments while avoiding obstacles. It relies on accurate and fast collision checking to know whether poses of the robot in the world are in collision or not. Motion planners often have to deal with partial or noisy information about the environment they operate in.
During his summer internship at Willow Garage, Jia Pan worked on new motion planning approaches and a new BSD-licensed library for collision checking. Jia is currently a PhD student in Prof. Dinesh Manocha's group at UNC Chapel Hill, a world-leader in collision checking and motion planning. Jia implemented the new Flexible Collision Library (FCL), which provides the latest in collision checking capabilities including proximity information and continuous collision detection. Jia also implemented a motion planner that accounts for uncertainty and unknown space, so that planned paths are less likely to go through areas not seen by the sensors on the robot.
Willow Garage is proud to announce our collaboration with Adept Technology. Along with Southwest Research Institute (SwRI), the three organizations are working together to contribute to the ROS-Industrial project. There is more information in Adept's official announcement.
ROS-Industrial has now demonstrated control of the Adept Viper 650, 6-axis industrial robot arm. This is the second robot vendor that has demonstrated a ROS-Industrial interface. This achievement demonstrates the ability of ROS-Industrial to leverage the functionality and capabilities within ROS across different robot vendor hardware and configurations. Because ROS-Industrial aims to standardize the interfaces to industrial arms in general, high level application functionality will be able to be deployed across hardware platforms. Even today, the capabilities within ROS-Industrial, including path planning and dynamic pick and place, far exceed the capabilities of any commercially available robot software. ROS-Industrial enables new applications and broadens the industrial robot market.
ROS-Industrial is a BSD-licensed ROS stack that contains libraries, tools and drivers for industrial hardware. The goals of ROS-Industrial are to:
- Create a community supported by industrial robotics researchers and professionals
- Provide a one-stop location for industry-related ROS applications
- Develop robust and reliable software that meets the needs of industrial applications
- Combine the relative strengths of ROS with existing industrial technologies (i.e. combining ROS high-level functionality with the low-level reliability and safety of industrial robot controllers).
- Create standard interfaces to stimulate “hardware-agnostic” software development (using standardized ROS messages)
- Provide an easy path to apply cutting-edge research in industrial applications, using a common ROS architecture
- Provide simple, easy-to-use, well-documented APIs
St. Paul, Minnesota, USA, May 14, 2011
|Submissions Due:||01 April 2012|
|Notification of Acceptance:||16 April 2012|
|Final Papers Due:||01 May 2012|
|Workshop at ICRA:||14 May 2012|
Motivation and Objectives
As robots and autonomous systems move away from laboratory setups towards complex real-world scenarios, both the perception capabilities of these systems and their abilities to acquire and model semantic information must become more powerful. The autonomous acquisition of information, the extraction of semantic models, and exploration strategies for deciding where and how to acquire the most relevant information pertinent to a specific semantic model are the research foci of an annual series of workshops at ICRA, called Semantic Perception, Mapping and Exploration (SPME).
Semantic perception for intelligent systems such as robots has seen a lot of progress recently, with many new and interesting techniques being developed in parallel by different research groups. Moreover, with the advent of inexpensive and accurate 3D imaging sensors, there has been an explosion of interest in 3D point clouds across a broad range of people. Not neglecting this trend, this edition of the workshop series puts a special focus on (3D) Semantic Perception.
While there is a lot of work on 3D perception that is freely available, and initiatives as PCL and 3DTK are enabling the community to build on previous results in order to push the frontiers for researchers further, there are some open questions left to be answered. There is no consensus yet emerging on the standard solutions, features and algorithms needed for semantic perception, mapping and exploration, and if the current approaches are viable on the long run. This workshop provides the venue for discussing the definition and uses of semantic information for and by perception, and to identify the most important directions of future research and development of new tools that would aid it.
We solicit paper submissions, optionally accompanied by a video, both of which will be reviewed (not double-blind) by the program committee. The review criteria will be: technical quality, significance of system demonstration, and topicality. We aim to accept 9 to 12 papers for oral presentation at the meeting. Papers should be up to 6 pages in length, and formatted according to the IEEE ICRA style. Videos will be shown during an afternoon session open to the public.
Accepted papers and videos will be assembled into proceedings
that are going to be published online, and distributed in CD format at the workshop.
In addition, we will pursue publication of a special journal issue to include the best papers.
This edition of the annual workshop series focuses on (3D) semantic perception.
Topics of interest include, but are not necessarily limited to:
- Extracting semantic information from visual sensors, 3D sensors, or different sensor modalities
- Semantic scene interpretation (and decomposition into parts of interest)
- Semantic object perception (incl. localization, identification, anchoring)
- Categorization or classification of objects, rooms, and environments
- Modeling (of objects and environments), registration using semantic information etc.
- Specifying and exploiting background knowledge for semantic perception and mapping
All papers must be submitted electronically as PDF files through the easychair submission system using: https://www.easychair.org/conferences/?conf=spme2012.
In case of problems or larger video attachments, contact the organizers: firstname.lastname@example.org.
- Francesco Amigoni, Politecnico di Milano, Italy
- Michael Beetz, Technische Universität München, Germany
- Sven Behnke, University of Bonn, Germany
- Wolfram Burgard, University of Freiburg, Germany
- Henrik Christensen, Georgia Institute of Technology, USA
- Tom Duckett, University of Lincoln, UK
- Joachim Hertzberg, University of Osnabrück, Germany
- Patric Jensfelt, KTH Royal Institute of Technology, Sweden
- Kurt Konolige, Willow Garage, USA
- Jim Little, University of British Columbia, Canada
- Bhaskara Marthi, Willow Garage, USA
- Alessandro Saffiotti, Örebro University, Sweden
- Markus Vincze, TU Vienna, Austria
The workshop will feature several invited talks from key researchers in the field:
- Gary Bradski, Willow Garage, Inc / Stanford University, USA
- Wolfram Burgard, University of Freiburg, Germany
- Trevor Darrell, UC Berkeley, USA
- Dieter Fox, University of Washington, USA
- Patric Jensfelt, KTH Royal Institute of Technology, Sweden
- Jim Little, University of British Columbia, Canada
- Dirk Holz, University of Bonn, Germany
- Zoltan-Csaba Marton, Technische Universität München, Germany
- Andreas Nüchter, Jacobs University Bremen gGmbH Germany
- Andrzej Pronobis, KTH Royal Institute of Technology, Sweden
- Radu Bogdan Rusu, Willow Garage Inc., Stanford University, USA
Partner workshop at ICRA
This is the first of two workshops at ICRA dealing with semantic perception, and we would also like to draw your attention to the other workshop on Friday. It is a hands-on workshop focusing, amongst other topics, on narrowing down the definition of semantics, life-long learning in the context of semantic mapping, knowledge representations and higher-level perception. Accepted are posters and demos. For more information see: http://ias.cs.tum.edu/events/spmk-icra2012.
Please join us this May for the inaugural edition of ROSCon!
ROSCon 2012 is a chance for ROS developers of all levels, beginner to expert, to spend an extraordinary weekend learning from and networking with the ROS community. Get tips and tricks from experts, network, and share ideas with fellow developers from around the globe.
ROSCon is a developers' conference, in the model of PyCon and BoostCon. The two-day program will comprise tech talks and tutorials that will introduce you to new tools and libraries, and teach you more about the ones you already know.
We received an overwhelming number of session proposals, which made for some tough decisions in the review process, and an acceptance rate of 27%. The program includes in-depth coverage of fundamentals, like tf and URDF, and introductions to higher-level concepts, like motion planning and multi-robot systems. We'll also hear about interesting applications of ROS, from teaching to field robotics. And we have two excellent keynotes, from Morgan Quigley of Stanford (and original author of ROS) and Julia M. Badger of NASA JSC.
We have some great sponsors to thank: Bosch, Motoman, Clearpath, Heartland, Willow Garage, CoroWare, Schunk, and Yujin. We're excited to have such strong industry support!
If you have any questions, send email to email@example.com.