A Development Cycle for Automated Self-Exploration of Robot Behaviors

Thomas M. Roehr, Daniel Harnack, Hendrik Wöhrle, Felix Wiebe, Moritz Schilling, Oscar Lima, Malte Langosz, Shivesh Kumar, Sirko Straube, Frank Kirchner
In AI Perspectives, n.n., volume 3, number 1, pages o.A., Jul/2021.
DOI: 10.1186/s42467-021-00008-9

Abstract

In this paper we introduce Q-Rock, a development cycle for the automated self-exploration and qualification of robot behaviors. With Q-Rock, we suggest a novel, integrative approach to automate robot development processes. Q-Rock combines several machine learning and reasoning techniques to deal with the increasing complexity in the design of robotic systems. The Q-Rock development 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 formalize Q-Rock's integrative development cycle and highlight its benefits with a proof-of-concept implementation and a use case demonstration.

Keywords

development cycle,knowledge representation,robot behaviors,robotics,self-exploration,semantic annotation

Links

Cite and export

Choose a format, then copy or download.

@article{Roehr2021Development,
  author    = {Roehr, Thomas M. and Harnack, Daniel and Wöhrle, Hendrik and Wiebe, Felix and
               Schilling, Moritz and Lima, Oscar and Langosz, Malte and Kumar, Shivesh and Straube,
               Sirko and Kirchner, Frank},
  title     = {A Development Cycle for Automated Self-Exploration of Robot Behaviors},
  journal   = {{AI} Perspectives},
  volume    = {3},
  number    = {1},
  month     = jul,
  year      = {2021},
  doi       = {10.1186/s42467-021-00008-9},
  url       = {https://robotik.dfki-bremen.de/en/research/publications/11622}
}
Download (.bib) 
TY  - JOUR
AU  - Roehr, Thomas M.
AU  - Harnack, Daniel
AU  - Wöhrle, Hendrik
AU  - Wiebe, Felix
AU  - Schilling, Moritz
AU  - Lima, Oscar
AU  - Langosz, Malte
AU  - Kumar, Shivesh
AU  - Straube, Sirko
AU  - Kirchner, Frank
TI  - A Development Cycle for Automated Self-Exploration of Robot Behaviors
T2  - AI Perspectives
VL  - 3
IS  - 1
PY  - 2021
DA  - 2021/07//
DO  - 10.1186/s42467-021-00008-9
AB  - In this paper we introduce Q-Rock, a development cycle for the automated self-exploration and qualification of robot behaviors. With Q-Rock, we suggest a novel, integrative approach to automate robot development processes. Q-Rock combines several machine learning and reasoning techniques to deal with the increasing complexity in the design of robotic systems. The Q-Rock development 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 formalize Q-Rock's integrative development cycle and highlight its benefits with a proof-of-concept implementation and a use case demonstration.
KW  - development cycle
KW  - knowledge representation
KW  - robot behaviors
KW  - robotics
KW  - self-exploration
KW  - semantic annotation
UR  - https://robotik.dfki-bremen.de/en/research/publications/11622
LA  - eng
ER  -
Download (.ris) 
Roehr, T. M., Harnack, D., Wöhrle, H., Wiebe, F., Schilling, M., Lima, O., Langosz, M., Kumar, S., Straube, S., & Kirchner, F. (2021). A Development Cycle for Automated Self-Exploration of Robot Behaviors. AI Perspectives, 3(1). https://doi.org/10.1186/s42467-021-00008-9


Back to the list
to top