Rescue Simulation League

A. Kleiner, Albert-Ludwigs-Universität Freiburg

RoboCup Rescue

Austrian RoboCup Workshop 2007







Motivation

Rescue Robot League



RRFreiburg: Behavior Maps

Rescue Simulation League



Virtual Competition



RRFreiburg: RFID Technology-based Exploration



Agent Competition

Motivation

The time problem after an incident

A. Kleiner, Albert-Ludwigs-Universität Freiburg RoboCup Rescue - Austrian RoboCup Workshop 2

Motivation

Where is the benefit from robotics technology?









After a disaster many places are unreachable for humans



Robots can access places humans can’t (e.g. small holes or spaces under the floor)



Robots can send video and thermo images from hazardous places

Destroyed infrastructure: Problem of selflocalization



Quality of disaster response strongly depends on information, such as maps with victim locations



Tom Haus (firemen at 9/11): “We need a tracking system that tells us where we are, where we have been, and where we have to go to”

Technology from Robotics can be deployed for information gathering and world modeling

Autonomous systems: Reduction of “cognitive load”


Rescue Robot League

Research Challenges

High degree of mobility Simultaneous Localization

And Mapping (SLAM)

Victim detection

A. Kleiner, Albert-Ludwigs-Universität Freiburg RoboCup Rescue - Austrian RoboCup Workshop

Autonomy!

4

Rescue Robot League

Build robots that are ready to leave the lab!

You might be too small … … or you might be too big


Rescue Robot League

Goals and directions









Cooperative development with simulation league

Step-wise increase of difficulty (e.g. like golf courses)

Building of standards for mapping and data exchange between heterogeneous units

Towards “mixed-initiative” solutions, i.e. humans and robots build one team for efficient disaster response


Competition setting

Three types of arenas

REGIONAL/PRELIMINARY ARENAS SHOWN, CHAMPIONSHIP ARENAS WILL BE TWICE THIS SIZE

YELLOW ARENA

RANDOM MAZE

PITCH & ROLL RAMP FLOORING (10 ° )

DIRECTIONAL VICTIM BOXES

(FOR AUTONOMOUS ROBOTS)

ORANGE ARENA

PITCH & ROLL RAMP FLOORING (10 ° , 15 ° )

HALF CUBIC STEPFIELDS

CONFINED SPACES (UNDER ELEVATED FLOORS)

VICTIM BOXES WITH HOLES

A. Kleiner, Albert-Ludwigs-Universität Freiburg

RED ARENA

FULL CUBIC STEPFIELDS

STAIRS (40 ° , 20CM RISERS)

RAMP (45 ° WITH CARPET)

PIPE STEPS (20CM)

DIRECTIONAL VICTIM BOXES

RoboCup Rescue - Austrian RoboCup Workshop 7

Competition setting

Simulated victims

Signs of life: form, motion, heat, sound,

CO

2

VISUAL IMAGE

THERMAL

IMAGE


Competition setting

Rules at a glance























GeoTIFF map formats will be used to allow comparison of maps to ground truth arena configurations.

Best-In-Class awards for autonomy and mobility will be given to robots that find the most victims in the Yellow and Red arenas respectively over all missions.

Random mazes with non-flat flooring

Stepfield pallets (Orange: half-cubic, Red: full-cubic)

Stairs (40°, 20cm riser, 25cm tread depth)

Ramp (45° to test torque and center of gravity)

Confined spaces (ceiling blocks under elevated floors)

Visual acuity (tumbling E eye charts, hazmat labels)

Directed perception boxes with victims/targets inside

Simulated Victims: 4 per arena, 12 total

Signs of life: form, heat, motion, sound, and/or CO2


Competition setting

Rules at a glance II (Missions)











15/20/25 minute missions include robot placement at the start point and operator station setup . Each team is responsible for making sure victims are functional

(heat, batteries, tags) prior to their mission start.

Teams are allowed one operator during missions.

Start points will be in the Yellow arena with all robots facing the same direction

(“north” on your map).

Yellow arena victims can be scored only by robots with autonomous navigation and victim identification. Operators may take over control at any time to move into the Orange and Red arenas but must return to the start point to resume autonomous searches.

Teleoperative robots can only score Orange or Red arena victims, which are placed on both sides of the Yellow arena to encourage complete mapping.


Teams at GermanOpen 2007


Behavior Maps

Elevation mapping and classification of rough terrain

Basic idea:

1) Robot with tilted Laser scanner and IMU sensor explores rough terrain.

2) Generation of elevation map, and classification with Markov

Random Fields (MRFs)

3) Detection of skill preconditions, e.g. starting position and angle

4) Planning and execution of skills

Lurker robot


Behavior Maps cont.


Rough terrain Elevation Map

Classified Map


Behavior Map


Behavior Maps cont.




Rescue Robotics

and the RoboCup Rescue Challenge



Motivation












Virtual Competition






Agent Competition

Rescue Virtual Competition

USARSim













Based on the Unreal game engine

(UT2004, Epic Games)

Realistic models of USAR environments, robots (Pioneer2 DX,

Sony AIBO), and sensors (Laser

Range Finder, Color Camera, IMU,

Wheel Odometry)

Multiple heterogeneous agents can be placed in the simulation environment

High fidelity simulation of up to 12 robots

Agents connect via a TCP/IP interface

NEW : Communication Server



Introduction cont.

Unreal

Client

Unreal

Server

Command

Sensor data

A. Kleiner, Albert-Ludwigs-Universität Freiburg RoboCup Rescue - Austrian RoboCup Workshop

Sonar Sensor message

17


Performance Metrics









Victim discovery



Victims are detected by a simplified sensor retuning ID/state depending on distance



Victim ID (10pt), Victim status (20pt), victim location (10pt), additional information

(20pt)

Self Localization and Mapping (SLAM)



Metric quality (50pt): How close are reported locations to ground truth?



Multi-robot fusion: Bonus for maps generated by multiple robots

Exploration





Max. 50pt if exploring the whole area

NEW : Explored areas have to be marked as “cleared”

Penalization







Robot-Victim collision (-5pt)

Teleoperation: Division of total score by (1+N) 2

NEW : One mandatory operator for each team



More new features

Improved robot models for realistic mobility








GeoTIFF format for maps

Maps will be overlaid on and compared to ground truth

Teams must specify areas “cleared”



Points deducted for victims in “cleared” areas



RRFreiburg solution at RoboCup’06









Basic Idea: RFID Technology-based Exploration









Robots generate local grid maps, generated from Laser Range data

A* based planning on local grid

Each robot distributes autonomously RFID tags and counts locally in the memory of tags the relative locations already visited

If in perception range, robots receive the data of tags and optimize their search by avoiding frequently visited places



Extension: Global planner that resets the local search if beneficial

Cheap computation on each robot due to a local world model

Locations are stored relatively to the tag, hence do not suffer under positioning errors

Efficient coordination without need for communication



Results from RoboCup’06 cont.

Area explored by all teams during the finals



Results from RoboCup’06: Exploration Trajectories

Area explored by our team (red trajectory) compared to all others

Area explored by each single robot of our team

Semi-final

(1276m 2 )

Final

(1203m 2 )



Video from the final



Rescue Robotics

and the RoboCup Rescue Challenge



Motivation












Virtual Competition






Agent Competition

Rescue Agent Competition

Introduction



Large scale disaster simulation







Simulators for earthquake, fire, civilians, and traffic

The task is to develop software agents with different roles, that





 make roads passable (police) extinguish the fires (fire brigades) rescue all civilians (ambulances)

Difference to Soccer Simulation:

A challenging Multi-Agent Problem since

Agents must cooperate



Simulator components are developed within the “Infrastructure Competition”


Conclusion







RoboCup Rescue offers a rich set of problems to AI and Robotics

Due to the difficulty for robots to cooperate in harsh environments, research is just at the beginning

Developed solutions are socially significant!



Links:





Rescue Robot League:



Homepage: http://robotarenas.nist.gov/competitions.htm

Rescue Simulation League:



Homepage: http://www.robocuprescue.org





USARSim (code base): http://sourceforge.net/projects/usarsim

Rescue Agent (code base): http://sourceforge.net/projects/roborescue


Thanks for your attention!


Rescue Simulation League - Albert-Ludwigs

RoboCup Rescue

Autonomy!

Teams at GermanOpen 2007

Behavior Maps

Behavior Maps cont.

Behavior Maps cont.

Rescue Robotics

Rescue Virtual Competition

Rescue Robotics