ELROB 2007
About
Robotics in security domains, fire brigades, civil protection and disaster control – facing the user
The „European Land-Robot Trial (ELROB)“ is organised in order to provide an overview of the European state-of-the-art in the field of UGVs/UAVs with focus on short-term realizable robot systems. ELROB is explicitly designed to assess current technology to solve problems at hand, using whatever strategy to achieve it. ELROB is presenting cutting edge robotics technology, applied to real world applications, that can save lives now and shape the direction of research for the short and medium term. With regard to available capabilities, the organisers seek to promote innovative technical approaches that will enable the operation of unmanned vehicles.
Regarding these points C-ELROB 2007 was a great success! 13 teams from five countries showed an impressive enthusiasm to cope with the tough trials.
The scenarios were:
- Non-urban: an NBC incident, search area for hazardous materials (8 participants)
- Urban: an incident with IEDs on a crowded marketplace, improve situation awareness (10 participants)
- Combined operation of UGV and UAV: fire and NBC incidents, search area for suspicious places (2 participants)
- Autonomous reconnaissance on urban and/or non-urban route: security patrol, do reconnaissance (7 participants)
Most of the teams did take the challenge sportive. The EuropeanRobotics group is more than happy to see that C-ELROB is attracting especially young researchers and stimulating the communication between the groups.
Again thank you very much for your participation!
Organisers
The event was jointly organised by the following institutions (no particular order):
- CIM Institute for Applied Computer Science and Industrial Technology, Giovanni Furìa
- Research Establishment for Applied Science (FGAN), Frank E. Schneider
- Bristol Robotics Laboratories, Alan Winfield
- University of Oulu, Intelligent Systems Group, Juha Röning
- IDSIA (Dalle Molle Institute for Artificial Intelligence), TUM, Jürgen Schmidhuber
- European Robotics
Chief Judge Team
Herman Bruyninckx
- Katholieke Universiteit Leuven
- Coordinator of EURON (EUropean RObotics research Network)
Alexander Förster
- IDSIA (Dalle Molle Institute for Artificial Intelligence)
Alan Winfield
- University of the West of England, Intelligent Autonomous Systems Laboratory
Giovanni Furìa
- University for Applied Sciences of Southern Switzerland, CIM Institute for Applied Computer Science and Industrial Technology
Frank E. Schneider
- Head of European Robotics
Scenarios
Non-urban scenario: Surveillance and reconnaissance in non-urban terrain
Terrain:
Non-urban, outdoor, mixed countryside, roads
Task:
Search autonomously (as far as possible) pre-designated area, detect points of interest (static and dynamic), identify, locate and record, report results to judge, if possible return to station in time.
Environment:
The maximum area is not larger than ?00x?00 meters. It may include paved roads, unpaved roads, trails, woods, and off-road areas. Examples of obstacles include ditches, berms, washboard, sandy ground, standing water, fire, rocks and boulders, narrow underpasses, construction equipment, concrete safety rails, power line towers, wire fences and cattle guards. In addition to the existing natural obstacles, the organisers might place obstacles (e.g. equipment) on the route that may disable a vehicle if struck. These obstacles must be detected and circumnavigated by a vehicle to successfully complete the route.
Urban scenario: Situation awareness in urban environment
Terrain:
Urban, both outdoor and indoor
Task:
Drive and explore terrain, gather information about environment, detect building to explore, inspect outside of defined building, if possible enter building, search one room (probably low light and collapsed), report results to judge, if possible return to station in time.
Environment:
The maximum area is no larger than ?00x?00m. It may include paved roads and unpaved roads. Examples of obstacles include ditches, berms, washboard, standing water, fire, boulders, narrow underpasses, construction equipment, concrete safety rails, power line towers, wire fences, and cattle guards. In addition to the existing natural obstacles, the organisers might place obstacles (e.g. equipment) on the route that may disable a vehicle if struck. The buildings may be practically collapsed. These obstacles must be detected and circumnavigated for a vehicle to successfully complete the route.
Combined UGV/UAV scenario for urban and non-urban terrain
Terrain:
Urban, non-urban, outdoor, mixed countryside
Task:
Search autonomously (as far as possible) pre-designated area by UAV, detect and locate points of interest, report results to operator and UGV, use UGV to exactly identify and record the incidents, report results to judge, if possible return to station in time.
Environment:
The maximum operational area is not larger than ?00x?00 meters. The maximum distance to the pre-designated area is no longer than ?00m. The area may include paved regions, unpaved regions, trails, and off-road desert areas. Examples of obstacles include ditches, berms, washboard, sandy ground, standing water, fire, rocks and boulders, construction equipment, concrete safety rails, power line towers, wire fences and cattle guards. In addition to the existing natural obstacles, the organisers might place obstacles (e.g. equipment) in the operational area that may disable a vehicle if struck. These obstacles must be detected and circumnavigated by a vehicle to successfully complete the route.
Autonomous reconnaissance scenario for urban and non-urban terrain
General description:
On public demand we added another scenario for large vehicles that can not participate in the urban and/or non-urban scenario. Also fast small vehicles may apply for the new scenario. The scenario is explicitly devoted to autonomous task fulfillment. It includes an urban route (approx. 3 Km) and a non-urban route (approx. 2 Km). You can do one or the other or both. Beside the autonomous navigation the system has to do some reconnaissance task (detect coloured objects while moving, locate them and record object positions (preferably in some kind of map). The route will only be „specified“ by some blurred and fuzzy GPS points (not more then 10 per route).
Terrain:
Urban, non-urban, outdoor, roads, tracks, woodland
Task:
Autonomously drive a pre-designated route, search autonomously (as far as possible) pre-designated area detect objects of interest (static and dynamic), identify, locate and record, report results to judge, if possible return to station in time.
Environment:
The maximum urban route is approx. 3 Km and the non-urban route approx. 2 Km. There will be absolutely no line of sight! The area may include paved regions, unpaved regions, trails, and off-road desert areas. Examples of obstacles include ditches, berms, washboard, sandy ground, standing water, fire, rocks and boulders, construction equipment, concrete safety rails, power line towers, wire fences and cattle guards. In addition to the existing natural obstacles, the organisers might place obstacles (e.g. equipment) in the operational area that may disable a vehicle if struck. These obstacles must be detected and circumnavigated by a vehicle to successfully complete the route.
Participating Teams
Official Results
Non-urban scenario: Surveillance and reconnaissance in non-urban terrain
- Telerob
- University of Siegen
- University of Würzburg and University of Kaiserslautern
Urban scenario: Situation awareness in urban environment
- University of Würzburg
- Telerob
- University of Hannover
Combined UGV/UAV scenario for urban and non-urban terrain
- Jacobs University Bremen
- University of Oulu
Autonomous reconnaissance scenario for urban and non-urban terrain
- University of Siegen
- University of Hannover and BASE 10
The ELROB 2007 trials have been evaluated based on this scoring scheme. Detailed result tables for all scenarios are available here. For further information have a look at the official rules.