What is the challenge that is being addressed?

A cloud kitchen runs a commercial kitchen operation for the purpose of preparing food for delivery and takeout. Cloud kitchens enable restaurateurs to expand existing restaurants or start virtual-only brands at a minimal cost. The provider of the cloud kitchen operates a Kitchen-as-a-Service (KaaS) business deriving value from efficiently aggregating shared resources both in the physical space and in the decision making. Physical space aggregation includes resource sharing at different stages of meal preparation, such as those needed for cooking, processing, storing and freezing ingredients. It further includes coordinated restocking of ingredients, delivery services for the prepared meals and inter-kitchen logistics. On the decision-making side, a KaaS provider helps the restaurateurs manage their recipes (as unique differentiating processes of meal preparation), find optimal assignments of recipes to kitchen resources, estimate ingredients consumption and demand, minimize food waste due to expirations of ingredients and market the meals to the consumers.

The dynamicity of the KaaS business, constantly in the process of bootstrapping new restaurateurs and optimizing existing ones, calls for a decision-making technology which allows fast and easy model modifications without the overhead of custom-coded solutions as provided by AI Planning.

What is the AI solution the project plans to implement?

The core decision making problem, consists of solving AI Planning problems with time and resource constraints, which consist of cooking equipment, appliances and staff modeled as limited resources, ingredients modeled as consumable resources, recipes modeled as planning actions, and orders, customers and couriers modeled as objects. Filuta AI implements the TSB under Apache 2.0 license, integrating with well-defined APIs into the existing commercial Enterprise Resource Planning system (ERP) operated by the KaaS provider. The ERP provides the flow of orders and the real-time observations of the operations (states of all entities in the system). Further the TSB integrates with third-party predictive analytics providers for traffic predictions and demand forecasting. Finally, the TSB integrates into the Unified Planning Framework (UPF), leveraging it as an interface to planning engines. The domains for UPF shall be provided by directly compiling a Blockly model into UPF.