DARPA's $2M 1st-responder co-robots Challenge:
. faq and forums @ theroboticschallenge.org ...
2011.6: President Obama launches NRI:
. NRI (National Robotics Initiative) ... .
2012.4.10: DARPA Robotics Challenge
(design co-robots for dangerous jobs):
. the primary goal of DARPA's Robotics Challenge program2012.4.10..30: DRC (Robotics Challenge)
is to develop ground robotic capabilities
to execute complex tasks in dangerous, degraded,
human-engineered environments.
The program will focus on robots that can
utilize available human tools,
ranging from hand tools to vehicles.
The program aims to advance the key robotic technologies
of supervised autonomy, mounted mobility, dismounted mobility,
dexterity, strength, and platform endurance.
Supervised autonomy will be developed to allow
robot control by non-expert operators,
to lower operator workload,
and to allow effective operation despite low fidelity
(low bandwidth, high latency, intermittent) communications.
Broad Agency Announcement:
BAA (Broad Agency Announcement)2012.10: Kickoff for Track A and Track B of DRC .
2012.10: Kickoff for Track A and Track B
Tracks C and D Registration:
2013.4.1: Track C registration deadline
2013.10.1: Track D registration deadline
2013.6: prep'Meeting for Virtual Disaster Response Challenge .
2013.12: prep'Meeting for Disaster Response Challenge I .
2014.12: prep'Meeting for Disaster Response Challenge II .
Up to $34 million awarded:
“Sustaining U.S. Global Leadership:
Priorities for 21st Century Defense,” January 2012, p. 6.
The primary goal of the DARPA Robotics Challenge program
is to develop ground robotic capabilities
to execute complex tasks in dangerous, degraded,
human-engineered (vice natural) environments .
. the robot must use human tools and vehicles
but otherwise doesn't have to appear human:
it can consist of severable pieces that may
automatically assemble and disassemble themselves;
and, can be tethered to an
energy store, power converter, or heat dissipater
carried by the utility vehicle .
. no need to use a human cell phone;
it coordinates with humans via wifi .
A secondary program goal increased accessibility of
ground robot systems development
(both hardware and software)
and lower software acquisition cost
while increasing capability.
This will be accomplished by creating and providing:
# a hardware platform:
Government Furnished Equipment (GFE)
to some performers in the form of a robotic hardware platform
with arms, legs, torso, and head, called the GFE Platform.
-- allows participation by teams having no
hardware expertise or hardware .
# the GFE Simulator:
. an open-source(community supported and enhanced),
cloud-based, real-time, operator-interactive,
virtual test-bed simulator populated with
models of robot components and field environments,
-- physics-based models of inertia, actuation,
contact and environment dynamics --
rigorously NIST-validated on a physical test-bed
(National Institute of Standards and Technology).
--
. allows developers to cheaply develope robo'software
with a high confidence in the results:
similar to what SPICE played for IC's
(Simulation Program with Integrated Circuit Emphasis)
allowing new system designs to be evaluated
without the need for physical prototyping.
--
. reduced cost, increased competition and innovation:
catalyzes disaggregation of robot component suppliers
as a cloud-based simulator requires only an internet terminal
in order to train, design, test and collaborate on ideas .
--
. enhances STEM education with FIRST competition:
(Science, Tech, Engineering, and Math)
(For Inspiration and Recognition of Sci & Tech)
. students virtually prototype both the design
and software control of robots,
then validate their simulation's model
against actual robotics hardware experiments .
--
GFE Simulator is expected to be provided by the
Open Source Robotics Foundation, Inc.,
and will initially be based on the ROS Gazebo simulator.
Expectations for the GFE Simulator include the following:
• Models the three-dimensional environment
• Allows import of robot's
kinematic, dynamic, and sensor models
• Allows robot's co.workers to send commands over a network
(identical to those sent to a physical robot)
and receive data from the simulated robot;
(similar to that received from a physical robot)
• Uses physics-based models of inertia, actuation, contact,
and environment dynamics to simulate the robot’s motion
• Runs in real-time on the “cloud,”
likely on Graphics Processing Units (GPUs)
• usable from the cloud by at least 100 concurrent teams
The GFE Simulator supplier will manage an open-source effort
where the simulator, robot models, and environment models
are developed and improved by the supplier
as well as by contributors throughout the world.
The DARPA Robotics Challenge
will consist of three key events:
a Virtual Disaster Challenge,
and two (2) Disaster Response Challenges.
Participation in the Virtual Disaster Challenge
is required only for teams working exclusively on
control software development.
[in contrast to also designing robotic hardware ]
The suppliers of the GFE Platform & the Simulator
may not participate in the Challenges .
Track B -- 11 software teams $375k each
-- winners of Virtual Challenge get access to
Government-Furnished Equipment (GFE),
DARPA's version of Boston Dynamics`Atlas robot .
based on of Boston Dynamics`PETMAN platform.
The GFE Platform will be physically capable of
performing all of the tasks in the disaster response scenario .
The platform is expected to have
two arms, two legs, a torso, and a head:
Arm: 7 degrees of freedom,
and a hand with 2-3 fingers;
Leg: 6 degrees of freedom,
3 at the hip, 1 at the knee, and 2 at the ankle;
Head: Stereo vision, laser radar;
Mass: 150 kg
. the selected Track B performers include:
Lockheed Martin’s Advanced Technology Laboratories,
RE2, TRAC Labs, TORC Robotics,
Universities of Kansas, and Washington,
Carnegie Mellon University,
Massachusetts Institute of Technology,
Florida Institute for Human and Machine Cognition,
Ben-Gurion University,
NASA’s Jet Propulsion Laboratory .
Track C -- 100 software teams given tools
-- possibly 6 get access to a GFE robot
after competing in the 2013.5
Virtual Robotics Challenge qualifying round,
facing off against Track B performers
resulting in 6 or less Virtual Challenge Winners
who get less than $758k each for more R&D,
and access to a GFE robot,
upon submitting a proposal to DARPA .
. funded tools include cloud computing resources .
. registration is open to anyone with the skills needed to
advance core robotic software capabilities
and participate using the open-source DRC Simulator.
. useful skills include
Expertise in software for robotic perception, planning, control
Expertise in human-robot interfaces,
experience in physics-based games, models and simulation,
as well as open-source code .
exact process to be described in a future announcement. In
Track A -- 7 system teams $3M each
. develops a full system, hardware and software
modeled with system with the GFE Simulator .
. entries are facing off against Virtual Challenge Winners
in the Disaster Response Challenge#1 (2014.1.1)
resulting in 8 or less Challenge#1 Winners
who get less than $1M each for more R&D .
. accepted Track A designs reflected DARPA’s emphasis
that while the robots competing in the DRC
must be able to operate in human-engineered environments,
they do not have to be humanoid in form.
The seven Track A teams are led by:
Carnegie Mellon University’s
National Robotics Engineering Center,
Drexel University, Virginia Tech,
Raytheon, SCHAFT Inc.,
NASA’s Johnson Space Center
and NASA’s Jet Propulsion Laboratory.
Track D -- system teams given tools
. an option for teams from around the world
to develop a system without DARPA funding;
encouraged to develop robots of any form,
not just humanoids.
And while DARPA’s GFE robot will be hydraulic,
Track D robots could be actuated with any
hybrid method (electrically, pneumatically).
Track D participants don't have to use the Simulator;
their focus will be on participating in the
live challenge events in 2013 and 2014.
Such entries must pass initial qualification testing,
but will otherwise compete on an equal footing with
the DARPA-funded efforts.
. entries are facing off against Challenge#1 Winners
in the Disaster Response Challenge#2 (2014.12.31)
and the winner gets $2M .
. categories of participants:
o FOREIGN CONCERN/ENTITY;
o WOMEN-OWNED LARGE BUSINESS,
o WOMEN-OWNED SMALL BUSINESS,
o OTHER LARGE BUSINESS,
o OTHER SMALL BUSINESS,
o SMALL DISADVANTAGED BUSINESS
[identify ethnic group from among the following:
Asian-Indian American,
Asian-Pacific American,
Black American,
Hispanic American,
Native American, or Other],
o HBCU [Black Colleges and Universities],
o MI [Minority Institutions],
o OTHER EDUCATIONAL,
o OTHER NONPROFIT .
2012.10: $2M reward for advancing co-robot tech:
. DARPA is offering a $2 million prize to2012.10.24: DRC @ willowgarage:
[ the winner of the competition
-- one who's DARPA-approved design ... ]
can push the state-of-the-art in robotics
beyond today’s capabilities in support of
the DoD’s disaster recovery mission.
True innovation in robotics technology
could result in much more effective robots
that could better intervene in high-risk situations
and thus save human lives and help contain the impact
of natural and man-made disasters.
The key to successfully completing this challenge
requires adaptable robots with the ability to
use available human tools,
from hand tools to vehicles.
It is DARPA’s position that achieving
true innovation in robotics,
and thus success in this challenge,
will require contributions from communities beyond
traditional robotics developers.
. DARPA is very excited for and supportive of
international participation in the DRC,
Just as natural and man-made disasters
are common worldwide challenges,
what the response to the DRC has shown is that
the international robotics community shares a
common goal of advancing robotic technology
to the point where it can have a tangible and positive impact
on humanitarian assistance and disaster relief.
Through the DRC,
DARPA is providing the forum, tools and incentives
to come together and take steps toward that goal.
beyond today’s capabilities in support of the DoD’s2012.11.5: drcsim & gazebo @ forum.theroboticschallenge.org:
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.
DRC (DARPA Robotics Challenge)
. DRC is pushing the state-of-the-art in robotics
Success with supervised autonomy, in particular,
could allow control of robots by non-expert operators,
lower the operator’s workload, and allow
effective operation even with low-fidelity communications
(low bandwidth, high latency, intermittent connectivity).
DARPA is funding for some DRC participants
a GFE robotic hardware platform
(Government-Furnished Equipment).
Additionally, all teams will have access to a
DARPA-funded [robot world] simulator .
The DRC kicked off on October 24, 2012,
and is scheduled to run for approximately 27 months
with three planned competitions,
one virtual followed by two live.
Events are planned for June & December 2013
and December 2014.
Development plans for drcsim and gazebo2012.12.31: VRC(Virtual Robotics Challenge) Rules Release #1
are in their respective roadmaps:
gazebosim.org/wiki/DRC/Roadmap
gazebosim.org/wiki/Roadmap
Check there for the latest news on
when simulator APIs will be available.
. as noted in the roadmap,
we expect drcsim 1.1 to include (some of)
the standard ROS controllers .
2013.4.1: Track C registration deadline
2013.6: prep'Meeting for Virtual Disaster Response Challenge .
2013.10.1: Track D registration deadline
2013.12: prep'Meeting for Disaster Response Challenge I .
2013.12.21: 1st DRC (DARPA Robotics Challenge) Competition:
November 4 – 22, 2013 Platform Safety Evaluations2014.12: prep'Meeting for Disaster Response Challenge II .
December 18 – 19, 2013 Team Practice
No comments:
Post a Comment