[robocup-worldwide] Call for Participation: RoboCup 2016 Rescue Robot League (Leipzig, Germany)

Johannes Pellenz johannes.pellenz at gmail.com
Tue Dec 29 12:23:54 EST 2015


----------------------
Call for Participation
----------------------

RoboCup Rescue Competition 2016

June 30 - July 04, 2016 in Leipzig, Germany

http://www.robocup2016.org/
http://wiki.robocup.org/wiki/Robot_League

Dear all,

The registration for the RoboCup Rescue World Championship in Leipzig
(Germany) is open. Please check the Rescue web site [1] for the
most current information. The 2016 rules will be announced at [2]. For now,
please check the lower section of this email for information about the rule
changes.

The important dates for the registration are:

* January 23, 2016: Submission of Team Participation Form [3].
  Please submit the form to rescue.robot.league at nist.gov
* February 15, 2016: Submission of Team Description Paper
  (The template will be provided to the teams that submit the
   Team Participation Form. So please make sure that you provide a valid
   email address with the Team Participation Form.)
* March 15, 2016: Announcement of qualified teams.

I am looking forward to seeing you all in Leipzig!

Kind regards
 Johannes Pellenz
 EXEC and local chair of the Rescue Robot League
 on behalf of the Rescue Robot League OC and TC

[1] http://wiki.robocup.org/wiki/Robot_League
[2] http://wiki.ssrrsummerschool.org/doku.php?id=rrl-rules-2016
[3] http://www.nist.gov/el/isd/upload/Champ2016_Country_TeamName-_TPF.doc

---

Background information about the competition (with changes for 2016)

* Objective

The RoboCupRescue Robot League is an international league of teams with
one objective: Develop and demonstrate advanced robotic capabilities for
emergency responders using annual competitions to evaluate, and teaching
camps to disseminate, best-in-class robotic solutions.

* Approach

The league hosts annual competitions to 1) increase awareness of the
challenges involved in deploying robots for emergency response
applications such as urban search and rescue and bomb disposal,
2) provide objective performance evaluations of mobile robots operating
in complex yet repeatable environments, and 3) promote collaboration
between researchers. Robot teams demonstrate their capabilities in
mobility, sensory perception, localization and mapping, mobile
manipulation, practical operator interfaces, and assistive autonomous
behaviors to improve remote operator performance and/or robot
survivability while searching for simulated victims in a maze of terrains
and challenges.

* Competition Vision

When disaster happens, minimize risk to search and rescue personnel while
increasing victim survival rates by fielding teams of collaborative mobile
robots which enable human rescuers to quickly locate and extract victims.
Specific robotic capabilities encouraged in the competition include
the following:
  - Negotiate compromised and collapsed structures
  - Locate victims and ascertain their conditions
  - Produce practical sensor maps of the environment
  - Establish communications with victims
  - Deliver fluids, nourishment, medicines
  - Emplace sensors to identify/monitor hazards
  - Mark or identify best paths to victims
  - Provide structural shoring for responders

These tasks are encouraged through challenges posed in the arena, specific
mission tasks, and/or the performance metric. Demonstrations of other
enabling robotic capabilities are always welcome.

* Search Scenario

A building has partially collapsed due to earthquake. The Incident
Commander in charge of rescue operations at the disaster site, fearing
secondary collapses from aftershocks, has asked for teams of robots to
immediately search the interior of the building for victims. The mission
for the robots and their operators is to find victims, determine their
situation, state, and location, and then report back their findings in a
map of the building with associated victim data. The section near the
building entrance appears relatively intact while the interior of the
structure exhibits increasing degrees of collapse. Robots must negotiate
and map the lightly damaged areas prior to encountering more challenging
obstacles and rubble. The robots are considered expendable in case of
difficulty.

* New in 2016: Test of basic capabilities first

This year we plan to transition the competition into a format that more
closely resembles Response Robot Exercises that have been so effective for
communicating capabilities between robot manufactures and responders. Where
each robot gets evaluated in standard and draft standard test method trials
early in the event to demonstrate functionality, reliability, operator
proficiency and autonomous/assistive capabilities, before getting "deployed"
into more complicated scenarios.

This change is essentially just moving the Best-In Class trials we've always
conducted at the end of the week, and expanding them to be conducted over
the first two days as Preliminaries. This will enable concurrent testing
opportunities for robots, comprehensive trials to get a statistically
significant data sets, and controlled increases in complexity to test robots
just beyond their comfort level to compile more and more points.

Teams will score Preliminary points in every test method they are capable of
performing, say one point per task repetition in 20 minute trials. Enough to
know that the robot is ready to combine test methods into more operationally
significant sequences, which would be the basis of the Semifinals for
roughly
half the teams.

The tasks are elemental, and each task repetition breaks down even further
into subtasks. These are  bounded intervals to demonstrate "hands-off"
autonomous behaviors. For example, each mobility terrain is a 5 m traversal
down range and a return back up range over the same 5 m of terrain. Each
traversal direction can be considered a bounded subtask for points,
accomplished either teleoperatively or autonomously.

Successful task repetitions with no operator interventions will be
considered
autonomous, and score a multiple of points to roughly account for typically
increased time to complete the task. The multiplier will also provide
incentive to try tasks autonomously. If an intervention is needed, and the
task is ultimately accomplished, the points will revert to the baseline
teleoperative points. It is our highest hope that robots can demonstrate
repeated tasks autonomously, 10 or more continuous repetitions ideally, to
establish a level of reliability and confidence for particular behaviors.
Then move on to demonstrate a complimentary behavior in a different test
method.

The different mobility terrains might include:
  - variable slalom (a S-shaped corridor),
  - parallel rails (the distance between the rails can be adopted to
    your robots track width),
  - gaps,
  - continuous ramps,
  - (elevated) crossing ramps,
  - step-fields,
  - sand and gravel,
  - hurdles,
  - stairs,
  - closed doors (with handles to open the doors), and
  - labyrinth.

The task to be fulfilled by the robot might include:
  - inspect pipes attached to a pipe star,
  - turn a valve mounted at the wall,
  - build a shoring structure from wooden blocks.

The autonomous capabilities might include:
  - autonomous navigation over even terrain,
  - autonomous navigation over rough terrain (such a ramps and stepfields),
  - autonomous detection and mapping of QR codes, hazmat signs, victims,
  - autonomous mapping of the environment (walls, stepfields, barrels).

Remember, no single task means anything -- 10 or more continuously
successful
tasks begin to indicate a reliable capability. And no individual test trial
means anything -- the complementary tests across a suite work together to
comprehensively evaluate the system. But each of these data points help
development and can help measure progress along the way to success.

The Finals will remain a comprehensive search task in the overall maze for
the best performing robots, made up of all the available test apparatuses
and
tasks as rooms in the maze. As always, the search scenario would be
conducted
from random start points and performed in the order of tasks that the team
chooses.

* New in 2016: Outdoor test -- transport material and victims autonomously

Also new in 2016 will be an outdoor test. The objective here is to transport
material (such as lumber for shoring or drilling tools) autonomously to
the disaster site. On the way back, bring victims to the paramedics, again
autonomously. The area for the task will be about 50 m by 100 m. The
transportation has to be done strictly autonomously - no teleoperation
is allowed. There will be three different levels of difficulty for the
outdoor test:
  1. Line following: A clearly visible line shows the way from the
     start point to the goal. The robot can use its vision system
     to follow this line. When it arrives at the end point, the
     team can manually turn the robot and send it back to the start point.
     This continuous until the time is up. The winner is the robot that
     achieved the longest distance.
  2. Dense GPS way points (UTM coordinates, zone 33). The teams are
provided
     with a dense list (approximately every 2 m) of way points that guides
     the robot from the start point to the target area. When it arrives at
     the end point, the robot can turn and drive it back to the start point.
     No manual interaction is allowed. This continuous until the time is
up.
     The winner is the robot that achieved the longest distance.
  3. Sparse GPS way points (UTM coordinates, zone 33). Same as (2.), but
     way points are only given for important landmarks such as turns and
     crossings. Objects might block the direct connection between two
     way points, so the robot must deal with these obstacles and find
     paths around them.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/robocup-worldwide/attachments/20151229/a96f7057/attachment.html>


More information about the robocup-worldwide mailing list