Thomas M. Roehr

Thomas M. Roehr

Auto-generated profile, based on publicly available information

Thomas M. Roehr

DFKI GmbH Robotics Innovation Center

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

1 November 2021 in IEEE Transactions on Robotics
Verified
Journal Article
Open access
TRThomas M. Roehr
Thomas M. Roehr
While traditional robotic systems come with a monolithic system design, reconfigurable multirobot systems can share and shift physical resources in an on-demand fashion. Multirobot operations can benefit from this flexibility by actively managing system redundancies depending on current tasks and having more options to respond to failure events. To support this active exploitation of redundancies in robotic systems, this article details an organization model as basis for planning with reconfigurable multirobot systems. The model allows us to exploit redundancies when optimizing a multirobot system’s probability of survival with respect to a desired mission. The resulting planning approach trades safety against efficiency in robotic operations and thereby offers a new perspective and tool to design and improve multirobot missions. We use a simulated multirobot planetary exploration mission to evaluate this approach and highlight an exemplary performance landscape. Our implementation of the organization model is open-source available (https://github.com/rock-knowledge-reasoning/knowledge-reasoning-moreorg).

7 September 2018 in INTELIGENCIA ARTIFICIAL
Verified
Journal Article
Open access
PDF file
TRThomas M Roehr
Thomas M Roehr
The application of reconfigurable multi-robot systems introduces additional degrees of freedom to design robotic missions compared to classical multi-robot systems. To allow for autonomous operation of such systems, planning approaches have to be investigated that cannot only cope with the combinatorial challenge arising from the increased flexibility of modular systems, but also exploit this flexibility to improve for example the safety of operation. While the problem originates from the domain of robotics it is of general nature and significantly intersects with operations research. This paper suggests a constraint-based mission planning approach, and presents a set of revised definitions for reconfigurable multi-robot systems including the representation of the planning problem using spatially and temporally qualified resource constraints. Planning is performed using a multi-stage approach and a combined use of knowledge-based reasoning, constraint-based programming and integer linear programming. The paper concludes with the illustration of the solution of a planned example mission.

12 December 2024
Verified
Book Chapter
Closed access
PDF file
SBS. Bartsch
S. Bartsch
FCF. Cordes
F. Cordes
TRT. M. Roehr
T. M. Roehr
RSR. U. Sonsalla
R. U. Sonsalla
FKF. Kirchner
F. Kirchner

11 May 2023 in Acta Astronautica
Verified
Journal Article
Closed access
MYMehmed Yüksel
Mehmed Yüksel
TRThomas M. Roehr
Thomas M. Roehr
MJMarko Jankovic
Marko Jankovic
WBWiebke Brinkmann
Wiebke Brinkmann
FKFrank Kirchner
Frank Kirchner

5 July 2021 in AI Perspectives
Verified
Journal Article
Open access
PDF file
TRThomas M. Roehr
Thomas M. Roehr
DHDaniel Harnack
Daniel Harnack
HWHendrik Wöhrle
Hendrik Wöhrle
FWFelix Wiebe
Felix Wiebe
MSMoritz Schilling
Moritz Schilling
FKFrank Kirchner
Frank Kirchner
In this paper we introduce Q-Rock, a development cycle for the automated self-exploration and qualification of robot behaviors. WithQ-Rock, we suggest a novel, integrative approach to automate robot development processes.Q-Rockcombines several machine learning and reasoning techniques to deal with the increasing complexity in the design of robotic systems. TheQ-Rockdevelopment cycle consists of three complementary processes: (1) automated exploration of capabilities that a given robotic hardware provides, (2) classification and semantic annotation of these capabilities to generate more complex behaviors, and (3) mapping between application requirements and available behaviors. These processes are based on a graph-based representation of a robot’s structure, including hardware and software components. A central, scalable knowledge base enables collaboration of robot designers including mechanical, electrical and systems engineers, software developers and machine learning experts. In this paper we formalizeQ-Rock’s integrative development cycle and highlight its benefits with a proof-of-concept implementation and a use case demonstration.