On Managing Knowledge for MAPE-K Loops in Self-Adaptive Robotics Using a Graph-Based Runtime Model

Service robotics involves the design of robots that work in a dynamic and very open environment, usually shared with people. In this scenario, it is difficult for decision-making processes to be completely closed at time, necessary define certain variability will runtime. MAPE-K (Monitor–Analyze–Plan–Execute over Knowledge) loops are popular scheme address real-time self-adaptation. As stated their own definition, they include monitoring, analysis, planning, execution modules, which interact through knowledge model. problems solved by robot can complex, may several MAPE coexist simultaneously robotic software architecture endowed robot. The then need coordinated, use model, representation information about environment robot, but also actions being executed. This paper describes graph-based representation, Deep State Representation (DSR), as component applied robotics. DSR manages perceptions actions, allows inter- intra-coordination loops. graph updated runtime, representing symbolic geometric information. has been successfully retail intralogistics where pallet truck manage roll containers satisfying requests from human pickers working warehouse.