The DARPA Robotics Challenge
The primary technical goal of the DARPA Robotics Challenge is to develop ground robots capable of executing complex tasks in order to extend aid to victims of natural or man-made disasters and conduct evacuation operations. Some disasters, however, due to grave risks to the health and wellbeing of rescue and aid workers, prove too great in scale or scope for timely and effective human response.
Competitors in the DARPA Robotics Challenge are expected to focus on robots that can use standard tools and equipment commonly available in human environments, ranging from hand tools to vehicles, with an emphasis on adaptability to tools with diverse specifications.
Humanoid Robot Platform
A humanoid robot, based on the Boston Dynamics Petman robot shown in the video, will be provided to the top six performers in the virtual challenge. The robots will execute each individual team's software for the remaining challenge competitions. While the robot will be physically capable of performing all of the challenge tasks, Team ViGIR is using its “Collaborative Autonomy” approach to address the software challenge of how to make the best use of the human abilities in the human-robot team.
Further Reading and Information
The DARPA Robotics Challenge is scheduled to launch in October of 2012 and will run for approximately 27 Months until one team remains. There will be three seperate challenges during this time. One of these challenges will take place in simulation while the rest will be live.
Introducing Team ViGIR
Virginia-Germany Interdisciplinary Robotics Team
No stranger to competitive robotics, Team ViGIR consists of researchers from TORC Robotics, Technische Universität (TU) Darmstadt, and Virginia Tech.
“We are really looking forward to taking on another DARPA challenge. These challenges have really shaped the field of robotics in last decade. DARPA’s challenges create a high stakes environment that is a catalyst for innovation, and I think we have the team for the job.” states Michael Fleming, CEO at TORC Robotics.
TORC engineers have been part of both the DARPA Grand Challenges and the Urban Challenge, where TORC led the software development VictorTango’s 3rd place finish. A strong competitor in the RoboCup challenges, TU Darmstadt adds significant experience in autonomous humanoid robotics for search and rescue. The team will leverage experience from Virginia Tech’s Center for Human-Computer Interaction (HCI) - a world leader in design and research of novel HCI concepts - and winner of three straight 3D User Interface IEEE competitions.
About the Simulation, Systems Optimization and Robotics (SIM) Group at TU Darmstadt
TU Darmstadt is one of the leading public engineering research universities in Germany. The Simulation, Systems Optimization and Robotics Group at the Department of Computer Science conducts research in autonomous robot teams, bio-inspired robots and dynamic modeling and optimization methods.
The research results have been honored, among others, with the 1st prize of the EURON/EUROP European Robotics Technology Transfer Award, the Louis Vuitton Best Humanoid Award, and several world championship titles for autonomous humanoid and four-legged robot soccer teams in the highly competitive annual RoboCup competitions.
For more information, click here.
About the Center for Human-Computer Interaction (CHCI) at Virginia Tech
CHCI is a world-class interdisciplinary research center at Virginia Tech, exploring the design of technological artifacts to support human activity and the impact of interactive technologies on the user experience. Housed in the Department of Computer Science, CHCI has 29 faculty affiliates across the university, including internationally recognized leaders in areas such as virtual and augmented reality, information visualization, gestural interaction, graphics and animation, creativity and the arts, and social collaborative computing. CHCI members lend their skills in user interface design, user experience evaluation, and usability engineering to projects in a broad range of application domains.
For more information, click here.
More Information & Sponsors
For more information, or to sponsor our team, contact Andrew Culhane (culhane@torcrobotics.com). Several sponsorship opportunities exist that will provide your company or organization with key insight into this exciting research as well as an ability to market yourself on the team’s website and on the robot.
Humanoid Robot Control for the DARPA Robotics Challenge
Student researchers will be part of team VIGIR – Virginia-Germany Interdisciplinary Robotics Team, which includes TORC Robotics, Virginia Tech Computer Science and TU Darmstadt (Germany). The team will participate in Track B of the DARPA Robotics Challenge, a disaster response scenario motivated by the Fukushima disaster, and develop human-robot interfaces and control software for the PETMAN/ATLAS full-size humanoid robot built by Boston Dynamics.
The official DARPA Robotics Challenge Website
Video of the Petman Humanoid Robot Platform
3 Credit Hour Courses Include:
ECE 4994 Undergraduate Research
Dr. David C. Conner (ECE)
conner@torcrobotics.com
TORC Robotics
Senior Research Scientist,
Adjunct Assistant Professor,
Virginia Tech, ECE
ECE 4994 topics will include:
- Introduction to humanoid robot control and grasping
- Control policy design
- Open loop
- Feedback-based
- Visual servoing
- Open loop
- Feedback-based
- Visual servoing
- Software engineering and development in C/C++
- Use of industry standard tools:
- Robotics Operating System (ROS)-based middleware and libraries (www.ros.org)
- Gazebo Robotics Simulation environment (www.gazebosim.org)
- GraspIt planning systems (www.cs.columbia.edu/~cmatei/graspit)
- OpenCV (http://opencv.willowgarage.com)
- Subversion, Redmine, and other software engineering tools
Required Student Expertise:
- Programming languages: C, C++, C#, Python, or Java
- UNIX – ECE 2524
- Signals and systems – ECE 2704
Preferred Skills:
- Robotics/AI – ECE 4704, 4524
- Software engineering – ECE 3574
- Control systems – ECE 4405
- Statistical analysis – Stat 4714
- Computer vision experience
- Matlab and/or Scipy programming
- Microsoft Visual Studio
CS 4994 Undergraduate Research
Dr. Doug Bowman (CS)
dbowman@cs.vt.edu
Director of the Center for Human-Computer Interaction
Virginia Tech, Computer Science
CS 4994 topics will include:
- Usability engineering process
- User interface (UI) design
- Assessing information and interaction requirements
- Developing graphical UI including 3D virtual environments
- Developing advanced UI based on gestures, speech, multiple displays, etc.
- UI evaluation