Manufacturing industries are on the brink of widely accepting a new paradigm for organizing production by introducing perceiving, active, context-aware, and autonomous systems. This is often referred to as Industry 4.0, a move from static process chains towards more automation and autonomy.
A testbed and research scenario for this development is the RoboCup Logistis League (RCLL), an international competition where group of robots have to maintain and optimize the material flow in a (simplified) context-aware smart factory.
The Knowledge-Based Systems Group in cooperation with the research group Theory of Hybrid Systems explore the possibilities to augment the currently used action selection mechanism, which is based on a rule-based forward chaining reasoning system, with an optimization strategy based satisfiability modulo theories (SMT) solving. As a prototype, this integration will be evaluated using a full 3D-simulation of the RCLL.
This position has been filled.
- What you should bring into the project:
- C++ programming skills
- Experience with Linux-based development environments
- Experience with logic-based programming, mathematical logic and modeling, and SAT solving beneficial but not mandatory
- What we offer:
- Participation in a state-of-the-art research project
- A friendly working environment and a challenging task
- Working with simulated (and later possibly real) robots
You can find more information project page. Here are some more relevant links for more information:
- Fawkes Robot Software Framework: software framework used in this project.
- CLIPS-based Agent Framework: to be extended by the SMT-based optimization layer.
- RCLL simulation: simulation environment for this project.
- Carologistics: RoboCup team of RWTH and FH Aachen on whose integrated system we will operate.
- Wikipedia on SMT: a primer about Satisfiability modulo theories.
- Wikipedia on Industry 4.0: primer about modern manufacturing and smart factories.
If you are interested and bring the proper qualifications please contact Tim Niemueller.