Q-Rock

AI-based Qualification of Deliberative Behaviour for a Robotic Construction Kit

Scientific Leader:
 
Project coordinator:
 
Project leader:
 
Contact person:

Robots learn their capabilities directly from their hardware and together with knowledge from humans, these become core elements for deliberative behavior. In Q-Rock a bidirectional mapping between hardware and behavior is established. With the help of Q-Rock, a user can specify a system by just specifying the intended behavior.

Duration: 01.08.2018 till 31.07.2021
Donee: German Research Center for Artificial Intelligence GmbH
Sponsor: Federal Ministry of Education and Research
Grant number: This research and development project is funded by the Federal Ministry of Education and Research (FKZ 01IW18003).
Application Field: Assistance- and Rehabilitation Systems
Agricultural Robotics
Electric Mobility
Logistics, Production and Consumer
SAR- & Security Robotics
Underwater Robotics
Space Robotics
Related Projects: D-Rock
Models, methods and tools for the model based software development of robots (06.2015- 05.2018)
Related Robots: COMPI
Compliant Robot Arm
Mobipick
Related Software: Phobos
An add-on for Blender allowing editing and exporting of robots for the MARS simulation
BOLeRo
Behavior Optimization and Learning for Robots

Project details

Q-Rock - From Hardware to Behaviour

The Goal: Robots learn their capabilities directly from their hardware and together with knowledge from humans, these become core elements for deliberative behavior. In Q-Rock a bidirectional mapping between hardware and behavior is established. With the help of Q-Rock, a user can specify a system by just specifying the intended behavior.

The Approach: The project Q-Rock implements methods to allow the robot to explore its own capabilities based on the existing hardware configuration. The Q-Rock project is building upon the hardware database that was the result of the D-Rock project. The learned capabilities are then grouped using machine learning techniques and applying human knowledge about the behavior. Together with a semantic description, these blocks turn into cognitive cores, which are the building blocks for deliberative behavior. A learning framework will be conceptualized and implemented using evolutionary algorithms, deep learning and analytical approaches, so that the robot can explore the capabilities based on actuators and sensors. Finally, a bidirectional mapping between hardware and deliberative behavior will be created through a combination of dialogue based reasoning and structural reasoning approaches. With this loop closure between hardware and behavior, a user should be able to specify a system based on the intended behavior of the robot, without the necessity of being an expert on sensors, actuators or software.
The project is using a continuous integration approach to first define necessary interfaces and then set up the whole system with dummies where necessary. With the project making progress, these dummies will be filled with the frameworks and methods developed.

Videos

Intrinsic interactive reinforcement learning: Using error-related potentials

Video-Vorschaubild
By playing the video, you accept YouTube's privacy policy.

Thanks to human negative feedback, the robot learns from its own misconduct.

Q-ROCK: Digital Baukasten für neues Robotik-Design aus Anwenderperspektive

Video-Vorschaubild
By playing the video, you accept YouTube's privacy policy.

Publications

2023

A Reference Implementation for Knowledge Assisted Robot Development for Planetary and Orbital Robotics
Mehmed Yüksel, Thomas M. Röhr, Marko Jankovic, Wiebke Brinkmann, Frank Kirchner
In Acta Astronautica, Elsevier Ltd., volume 2023, pages 1-16, 2023.

2022

Ontology-Driven Robot Design for Future Orbital and Planetary Robotics with korcut
Mehmed Yüksel, Thomas M. Röhr
European Aeronautics Science Network International Conference (EASN), Oct/2022.
Combinatorics of a Discrete Trajectory Space for Robot Motion Planning
Felix Wiebe, Shivesh Kumar, Daniel Harnack, Malte Langosz, Hendrik Wöhrle, Frank Kirchner
Editors: William Holderbaum, J. M. Selig
In 2nd IMA Conference on Mathematics of Robotics, (IMA-2022), 08.9.-10.9.2021, London, Springer International Publishing, series Springer Proceedings in Advanced Robotics, Jan/2022. ISBN: 9783030913519.

2021

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.
Active Exploitation of Redundancies in Reconfigurable Multi-Robot Systems
Thomas M. Roehr
In IEEE Transactions on Robotics, IEEE, volume n.n., pages 1-17, Jun/2021.

2020

Online Reconfiguration of Distributed Robot Control Systems for Modular Robot Behavior Implementation
Malte Wirkus, Sascha Arnold, Elmar Berghöfer
In Journal of Intelligent & Robotic Systems, Springer Publishing, volume 100, number 3, pages 1283-1308, Dec/2020.
A survey on modularity and distributivity in series-parallel hybrid robots
Shivesh Kumar, Hendrik Wöhrle, José de Gea Fernández, Andreas Mueller, Frank Kirchner
In Mechatronics, Elsevier Ltd., volume 68, pages 102-367, Jun/2020.
An Analytical and Modular Software Workbench for Solving Kinematics and Dynamics of Series-Parallel Hybrid Robots
Shivesh Kumar, Kai von Szadkowski, Andreas Mueller, Frank Kirchner
In Journal of Mechanisms and Robotics, ASME, volume 12, number 2, pages 1-12, Apr/2020.
BOLeRo: Behavior Optimization and Learning for Robots
Alexander Fabisch, Malte Langosz, Frank Kirchner
In International Journal of Advanced Robotic Systems, SAGE Publications, volume 17, number 3, pages n.n.-n.n., 2020.

2019

Model Simplification For Dynamic Control of Series-Parallel Hybrid Robots - A Representative Study on the Effects of Neglected Dynamics
Shivesh Kumar, Julius Martensen, Andreas Mueller, Frank Kirchner
In Proceedings in IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS-2019), 04.11.-08.11.2019, Macau, IEEE, Dec/2019.
An Analytical and Modular Software Workbench for Solving Kinematics and Dynamics of Series-Parallel Hybrid Robots
Shivesh Kumar, Andreas Mueller
In 43rd Mechanisms and Robotics Conference, Parts A and B, (IDETC/CIE-2019), 18.8.-21.8.2019, Anaheim, CA, ASME, Oct/2019.
A modular approach for kinematic and dynamic modeling of complex robotic systems using algebraic geometry
Shivesh Kumar, Andreas Müller
In Invited Talk at SIAM AG Conference, (SIAM AG-2019), 09.7.-13.7.2019, Bern, SIAM, Jul/2019.

2018

HyRoDyn: A Modular Software Framework for Solving Analytical Kinematics and Dynamics of Series-Parallel Hybrid Robots
Shivesh Kumar, Kai von Szadkowski, Andreas Müller, Frank Kirchner
In Poster at 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS-2018), 01.10.-05.10.2018, Madrid, IEEE/RSJ, series IROS Poster proceedings, pages 1-1, Oct/2018.

Back to the list of projects
© DFKI GmbH
last updated 11.09.2024