IMPERA

Integrated Mission Planning for Distributed Robot Systems

The goal of the research project IMPERA is the development of strategies for distributed mission and task planning. An application example is the exploration of unknown, lunar environment using a team of mobile robots. The planning refers to mobile, distributed and heterogeneous robots. One sub goal is the development of a standardized and modular task planning architecture which is running on the systems directly without the need of dedicated infrastructure.

Duration: 01.04.2011 till 31.03.2014
Donee: German Research Center for Artificial Intelligence GmbH
Sponsor: Federal Ministry of Economics and Technology
German Aerospace Center e.V.
Grant number: This project is funded by the Space Agency (DLR Agentur), acting on a mandate from the Federal Government, grant no. 50 RA 1111.
Partner: Distributed Systems Group, University of Kassel
Application Field: Space Robotics
Related Projects: VirGo4
Virtual state prediction for Groups of reactive autonomous Robots (04.2011- 06.2014)
Related Robots: SeekurJr
Four-wheel, skid-steered mobile outdoor robot
AMPARO
Autonomous manipulation robot

Project details

Scout (Source: Markus Eich, DFKI GmbH)

The IMPERA software architecture will be augmented with different planning modules during the project and the usability will be verified using real robot systems.
The different task execution strategies are developed and iteratively tested in simulation environment. The verification and deployment of the planning modules will be achieved in an extraterrestrial setting using a team of heterogeneous robots. The usability of the IMPERA architecture will be verified in the following scenarios:

  • Dynamic sensor and communication coverage in the context of lunar exploration
  • Planning with restricted resources like energy and storage
  • Distributed exploration with the use of heterogeneous robots
  • Inspection and maintenance of lunar infrastructure
  • Transfer between spatial and symbolic representation (semantic perception)

The transfer between the spatial and semantic domain is an important issue in order to be able to plan on a symbolic level. Robots perceive the environment with sensors in the spatial domain, e.g. laser generated 3D point clouds. One part of the project deals with the classification of spatial data in order to allow symbolic planning.
For the above mentioned planning problems specific planning modules will be developed and integrated in the IMPERA planning architecture. All planning problems are dealt with in a multi-robot context and executed on real robot systems. 

Videos

IMPERA: Exploration and object-manipulation with the robot-team

A team of two robots are demonstration the abilities to localize and to transport objects.

Publications

2014

An Autonomous Mobile Manipulator for Collecting Sample Containers
Sankaranarayanan Natarajan, Sebastian Kasperski, Markus Eich
In Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS 2014), (iSAIRAS-2014), 17.6.-19.6.2014, Montreal, o.A., Jun/2014.
Reliable, Cloud-based Communication for Multi-Robot Systems
Ronny Hartanto, Markus Eich
In The 6th Annual IEEE International Conference on Technologies for Practical Robot Applications, (TePRA-2014), 14.4.-15.4.2014, Woburn, Massachusetts, IEEE, Apr/2014.
Towards Coordinated Multi-Robot Missions for Lunar Sample Collection in Unknown Environment
Markus Eich, Ronny Hartanto, Sebastian Kasperski, Sankaranarayanan Natarajan, Johannes Wollenberg
In Journal of Field Robotics, Wiley-Blackwell, volume Volume 31, number Issue 1, pages o.A., Feb/2014.
Semantic Labelling of 3D Point Clouds using Spatial Object Constraints
Malgorzata Goldhoorn, Ronny Hartanto
In Proceedings of the 9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, (VISIGRAPP-2014), 05.1.-09.1.2014, Lissabon, SCITEPRESS - Science and Technology Publications, pages 513-518, Jan/2014. ISBN: 978-989-758-002-4.

2013

Evaluation of cooperative exploration strategies using full system simulation
Sebastian Kasperski, Markus Eich, Johannes Wollenberg
In Advanced Robotics (ICAR), 2013 16th International Conference on Advanced Robotics, (ICAR-13), 25.11.-29.11.2013, Montevideo, IEEE, pages 1-6, Nov/2013.
An Application of Fuzzy DL-Based Semantic Perception to Soil Container Classification
Markus Eich
In 2013 IEEE International Conference on Technologies for Practical Robot Applications, (TePRA-2013), 22.4.-23.4.2013, Woburn, Masachusetts, o.A., Apr/2013.

Back to the list of projects
© DFKI GmbH
last updated 04.01.2024