AIPlan4EU: Bringing AI Planning to the European On-Demand AI Platform
Automated Planning and Scheduling is a central research area in AI that has been studied since the inception of the field and where European research has been making strong contributions over decades. Planning is a decision-making technology that consists in reasoning on a predictive model of a system being controlled and deciding how and when to act in order to achieve a desired objective. It is a relevant technology for many application areas that need quick, automated and optimal decisions, like agile manufacturing, agrifood or logistics. Although there is a wealth of techniques that are mature in terms of science and systems, several obstacles hinder their adoption, thus preventing them from making the footprint on European industry that they should make. For example, it is hard for practitioners to find the right techniques for a given planning problem, there are no shared standards to use them, and there is no easy access to expertise on how to encode domain knowledge into a planner.
The AIPlan4EU project will bring AI planning as a first-class citizen in the European AI On-Demand (AI4EU) Platform by developing a uniform, user-centered framework to access the existing planning technology and by devising concrete guidelines for innovators and practitioners on how to use this technology. To do so, we will consider use-cases from diverse application areas that will drive the design and the development of the framework, and include several available planning systems as engines that can be selected to solve practical problems. We will develop a general and planner-agnostic API that will both be served by the AI4EU platform and be available as a resource to be integrated into the users’ systems. The framework will be validated on use-cases both from within the consortium and recruited by means of cascade funding; moreover, standard interfaces between the framework and common industrial technologies will be developed and made available.
O1: Making planning accessible to practitioners and innovators
O2: Facilitate the integration of planning and other ICT technologies
O3: Making planning relevant in diverse application sectors
O4: Seamlessly integrate planning within the AI4EU platform
O5: Facilitate learning of planning for reskilling and lower the access barrier
O6: Standardize and drive academic research towards applications
The project is organized around a number of work-packages (WP) as follows.
Leader: Paola Baruchelli (FBK)
This work package is responsible for coordinating the project from both the administrative and technical perspectives, aiming towards achieving effective operation of the project as well as timely delivery of quality results.
Leader: Raj Kamal (Meritor)
This work package is responsible for the collection of use-cases and requirements. In particular, starting from the formalization of each of the use-case provided by partners of the consortium, the WP will synthesize the requirements for the UPF by considering both the technical capabilities of planning (elicited in WP4) and the business needs emerging from the use-cases.
WP3: Unified Planning Framework
Leader: Andrea Micheli (FBK)
This work package is responsible for the development of the UPF. Within this WP, we will design and develop the UPF resource, making it ready to be integrated with planning engines and TSBs. The WP will start by analyzing the technical requirements for the UPF and then move to implement the requirements produced in WP2 in a continuous and agile way. Moreover, we will study and implement self-configuration approaches within the UPF and summarize the learned lessons in the integration of planning engines and TSBs in a series of guidelines that will be part of the training and documentation material of the project.
WP4: Planning Engines
Leaders: Alfonso Gerevini and Enrico Scala (University of Brescia)
This work package is devoted to the integration of several planning engines, each one with a well-defined, concise and robust interface allowing a seamless interoperability within the project platform and beyond, using planning as a service paradigm. Each planning engine interface needs to ensure the WP3 to access the targeted planning engine in an effective way whilst satisfying the requirement established by the use-cases. Moreover, the WP4 needs to provide means for an effective evaluation (WP6).
WP5: Technology-Specific Bridges
Leaders: Sebastian Stock and Oscar Lima (DFKI)
This WP serves the two purposes of mapping planning needs and requirements of the respective use-cases to the planning machinery provided in the UPF, and of generalizing from these use-case-specific experiences to a prototypical, generic Technology Specific Bridges (TSB) to the planning formalisms, methods, and implementations provided by the UPF.
Leaders: Konstantinos Kapellos (Trasys International)
This WP is concerned with the evaluation of the project outcomes from both business and technical perspectives. The objectives of the WP are (i) Measure the performance of the planners and the impact of the UPF abstraction layer over benchmarks identified in WP4. (ii) Evaluate the business KPIs on the solutions developed within the project, combining both the TSB and the UPF and considering the use-cases devised within the consortium and the ones elicited through the cascade funding. (iii) Evaluate the acceptability, TRL and maturity of the UPF component as a whole to ensure it can be considered a relevant technology for practical business applications.
WP7: Ontegration with AI4Europe
Leaders: Alessandro Saffiotti and Uwe Köckemann (Örebro University)
The objective of WP7 is to integrate the best European know-how and tools for AI planning into the European AI on-demand platform, via the Unified Planning Framework (UPF). More specifically: to integrate the UPF into that platform both as an on-line service and as a downloadable resource; to enrich that platform by adding accessible software tools, educational resources and use-cases aimed at enabling a larger user community to employ AI planning techniques; to enable a community of early adopters to access and use the AI planning solutions made available through the AI on-demand platform, via open-call program (WP10).
Leaders: Malte Helmert and Gabriele Röger (University of Basel)
The aim of WP8 is to disseminate the knowledge and results developed in the project to stakeholders. We envisage actions engaging various user communities, in particular, SMEs but also innovators and integrators as well as other relevant stakeholders.
Leader: Fabio Zonfrilli (Procter and Gamble)
The main objective of this WP is to help project partners and external stakeholders (especially Industry and SMEs, Research Community) in the exploitation of innovative solutions based on AIPlan4EU.
WP10: Open Calls
Leaders: Luisa de Souza Goncalves and Marina Domingas (F6S)
The main objective of this WP is to attract and involve third-parties (particularly non-technological sectors representatives and technological innovators) to the AIPlan4EU network, to boost cross-border and cross-sector innovation within media sectors. This WP will include the implementation of open call procedures, their dissemination, evaluation, monitoring of the execution of the funded projects, and the collection and analysis of the results, with the aim of developing and strengthening the AIPlan4EU project.