In addition to the expansion of infrastructure and supply structures, the increase in the world population is also leading to an increasing demand for raw materials. All of this makes safety in underground structures such as tunnels and mines a significant issue, especially in the event of damage or emergencies. Underground structures represent a major challenge for emergency services due to the extraordinary framework conditions. Poor visibility, smoke development, temperature, emissions, use of explosives, release of hazardous substances and structural hazards are among the influencing factors that not only put special demands on emergency services, but also push their equipment and devices to the limit. The use of semi-autonomous robots equipped with sensors for supporting analysis tasks enables location-adapted deployment techniques and quick decision-making.
The aim of ROBO-MOLE is to create increased safety for emergency services and accident victims in the event of incidents in underground structures. This is realized through automatic detection and identification of hazardous substances in combination with real-time situation map creation. To achieve this, a semi-autonomous robot is designed to support analysis tasks, and is equipped with a wide and flexible range of sensors (positioning, imaging and detection of hazardous substances). These are combined to enable safe navigation and control under difficult conditions and to be able to detect and map hazards.
One of the innovations in this project is the robust position determination and path planning, which to this day represents a major challenge in underground navigation, as it must be achieved without external infrastructure or map information. Another innovation is the complex 3D modeling in real time, which enables a quick orientation for the planning of the mission. The challenge here is the fast processing and display of the situation map, which requires particularly efficient algorithms and new methods due to the large amount of data. This includes the semantic processing and enrichment of the data so that critical structures and objects can be detected automatically. The development of the proposed semi-autonomous system for exploring and analyzing the site is intended to make underground operations more efficient and safer.machen.
Projektleiter:
Ass.Prof. Dr. Nina Gegenhuber Montanuniversität Leoben/Lehrstuhl für Subsurface Engineering
Weitere Projektpartner:
Disaster Competence Network Austria
Technische Universität Graz – Institut für Geodäsie
Technische Universität Graz – Institut für Softwaretechnologie
Austrian Institute of Technology – Digital Safety and Security
JOANNEUM RESEARCH Forschungsgesellschaft mbH– Digital
Riegl Research Forschungsgesellschaft mbH
IQSoft GmbH
CBRN Protection GmbH
E-NETIC
BMLV – Kommando Streitkräfte
Berufsfeuerwehr Graz
Berufsfeuerwehr Linz
Berufsfeuerwehr Innsbruck
Kontakt:
Ass.Prof. Dr. Nina Gegenhuber
Montanuniversität Leoben
Lehrstuhl für Subsurface Engineering
Franz-Josef Straße 18
8700 Leoben
Nina.gegenhuber@unileoben.ac.at
+43 3842 3401
