Posts Tagged: ‘disaster response’

Curves repository is now public

3 February, 2017 Posted by tradr_admin

The objective of the TRADR project is to enable a team of humans and robots to collaborate in a disaster response scenario which can last over several days. To achieve this, one of the core capabilities of the robots is their capacity to create a 3D map of their environment and to localize themselves within this map.

The TRADR consortium has recently open-sourced three libraries with the purpose of enabling robots equipped with 3D laser scanners to perform the above mentioned tasks. The curves library is used to represent the robot’s continuous-time trajectory in 3D space while the laser_slam library implements the back-end estimation functionalities of the localization and mapping system. The SegMatch library finally enables the robots to recognize previously visited places and to transmit this information to the back-end in order to close loops and to register trajectories of different robots.

Links to libraries:

The following figure illustrates a map which was generated by fusing 3D laser scanner measurements from two unmanned ground vehicles which were collected during the TRADR Evaluation exercise at the Gustav Knepper Power Station in Dortmund, Germany. The map is coloured by height and the robot trajectories are represented as blue and red lines.

For more information about the place recognition algorithm please consult our paper ( and have a look at our video ( Easy to run demonstrations can be found in the wiki page of the SegMatch repository. More to come!

Invited talk at Istituto Italiano di Tecnologia (IIT), Sept. 15

15 September, 2016 Posted by tradr_admin

On Sep 15 Tomas Svoboda from the Czech Technical University in Prague gave an invited talk about robot-assisted disaster response at the Istituto Italiano di Tecnologia (IIT).

Istituto Italiano di Tecnologia (IIT) is a Foundation and financed by the State to conduct scientific research in the public interest, for the purpose of technological development.

T. Svoboda is Research Fellow and Assistant Professor at the Czech Technical University, Faculty of Electrical Engineering, Department of Cybernetics since 2003.





euRathlon – TRADR Summer School, August 22-26, 2016 in Oulu, Finland

22 August, 2016 Posted by tradr_admin


The ERL Emergency / TRADR summer school on Heterogeneity in Robotics Systems was held at University of Oulu’s facilities in Oulu (Finland) from the 22nd to the 26th August 2016. The summer school was jointly organised by the University of Oulu, the University of the West of England, Bristol, and TRADR EU-FP7 project.

The trend in this area is going towards multi-robot systems with different outfits, processing powers and operation spaces (ground, water, air) that shall be deployed over long periods and several sorties. This raises many challenges, including multi-modal heterogeneous mapping, semantic analysis and reasoning, (collaborative) planning under uncertainty.

The summer school program consisted of lectures on these topics, and hands-on sessions during which the participants work on practical tasks using several robots with different sensory equipment. The intended audience were undergraduate students, Master students, PhD students, postdoc students, researchers from universities/organizations and engineers from industry companies around the world.

To complete the academic program of the summer school, six speakers were invited to give a lecture to the attendees on different topics. As a reaction to the feedback given in the 2015 summer school, the total amount of lectures was lowered to give the students more time for practical exercises.


TRADR Year 2 Review in Dortmund, Germany

16 March, 2016 Posted by tradr_admin

The TRADR Year 2 review took place in Dortmund (Germany) on Wednesday March 16 and Thursday March 17. On Wednesday the consortium presented its scientific results and on Thursday we demonstrated the integrated system at Phönix Phönix West, an abandoned furnace. The integrated system showcased Y2 work, with emphasis on persistence. The demonstration mission was carried out by a team consisting of a mission commander, a team leader, two UGVs each with an operator and one UAV with an operator and a pilot. One of the UGVs had a camera-equipped arm. The human team members operated remotely from a command truck, except for the UAV pilot in line of sight. The team assessed a part of the building, searched for victims and sources of potentially dangerous materials. The UAV was used for initial overview and subsequent search on the outside, the UGVs explored multilevel terrain inside, partially obstructed by smoke. Main focus was on acquiring and sharing situation awareness among team members across multiple sorties and across team shifts. The robots mapped the environment, provided a video feed and were used to take photos. The human team members were equipped with interfaces presenting them information according to their role(s). Team communication and information about the progress of the mission were collected and accessible in a mission reporting tool. We demonstrated various partial autonomy features designed to facilitate the human operators’ task, including terrain profile estimation from interoceptive sensing, adaptive traversability to automatically control the UGV flippers, a novel free-look control mode for the UGV, virtual bumpers on the UAV. Finally, a mixed-initiative path planning approach and a novel mapping framework designed to support persistence and decrease computational load were also presented. The overall progress of the project was evaluated by the predicate “very good”.

TRADR team at Exercise Unified Response in London

4 March, 2016 Posted by tradr_admin

Several members of the TRADR team participated as observers at the Exercise Unified Response in London, March 1-4.

It was a large scale training exercise taking place at several sites in and around London, involving about 70 agencies and disaster response teams not only from London Firebrigade, but also international help from Italy, Cyprus and Hungary.  The exercise simulated a building collapse over the Waterloo underground station in central London. The scenario was built in a disused power station in Dartford, Kent.  We got really good insight, especially at the various higher levels, what a response to such a serious incident involves. It was also extremely valuable to see such a complex scenario from close up and see the immense activity of the responders, the higher  levels of tactical and strategic command and many of the other actors involved in the response.Last but not least, there were aspects of the evaluation worth taking inspiration from.