Search

By connecting devices, people, vehicles, and infrastructures everywhere in a city, governments and their partners can improve community well-being and other economic and financial aspects (e.g., cost and energy savings). Nonetheless, smart cities are complex ecosystems that comprise many different stakeholders (network operators, managed service providers, logistic centers, and so on), who must work together to provide the best services and unlock the commercial potential of the so-called Internet of Things (IoT). This is one of the major challenges that faces today's smart city movement, and the emerging "API economy". Indeed, while new smart connected objects hit the market every day, they mostly feed "vertical silos" (e.g., vertical apps, siloed apps, and so on) that are closed to the rest of the IoT, thus hampering developers to produce new added value across multiple platforms and/or application domains. Within this context, the contribution of this paper is twofold: 1) present the strategic vision and ambition of the EU to overcome this critical vertical silos' issue and 2) introduce the first building blocks underlying an open IoT ecosystem developed as part of an EU (Horizon 2020) Project and a joint project initiative (IoT-EPI). The practicability of this ecosystem, along with a performance analysis, is carried out considering a proof-of-concept for enhanced sporting event management in the context of the forthcoming FIFA World Cup 2022 in Qatar. 2017 IEEE. This work was supported in part by the EU's H2020 Program for Research, Technological Development, and Demonstration, under Grant 688203, and in part by the National Research Fund Luxembourg under Grant 9095399. Scopus

Purpose – The purpose of this paper is to propose a collaborative tracking and tracing (T&T) system that enables supply chain actors to join and leave the system in run-time without disrupting the function of the system. Design/methodology/approach – A collaborative T&T system is introduced using a conceptual approach. Supporting empirical data are collected through a deductive case study of a Swedish automotive supply chain. Findings – A collaborative T&T system based on composite and observer design patterns is an appropriate solution for inter-organizational T&T. Research limitations/implications – This research contributes to the body of knowledge in the field of logistics T&T. The conceptually developed collaborative T&T system needs to be validated empirically. Practical implications – The collaborative T&T system developed conceptually here could be used as a model for the practical development of inter-organizational T&T systems. Originality/value – The introduction of a collaborative T&T system, adopting the theories of software engineering and product data management, represents an original contribution to the field of T&T in logistics and transportation.

PurposeThis paper aims to present how the success of inter‐organizational systems (IOS) implementation projects can be increased by aligning the different incentives of buyers and suppliers.Design/methodology/approachThe research method employed is case study and its unit of analysis is a network of supplier and wholesaler (buyer) companies acting in the Finnish technical trade industry, which are implementing inter‐organizational tracking. The implementation project followed an implementation process model developed to execute the case study.FindingsFor a buyer, the challenge in IOS implementation is that suppliers feel the adoption more difficult and have less identifiable benefits. However, in the case study, suppliers were ready to implement tracking solution because they understand that improvements in IOS help to apply common industry data exchange standards and will lead to better supply chain collaboration, which also increases their operational performance in the long run.Research limitations/implicationsThis paper concentrates on supplier and buyer incentives but also the role of other supply chain members such as logistics providers could be analyzed to examine different factors for IOS implementation.Practical implicationsIf the buyer takes a cooperative approach to IOS integration, suppliers can be motivated to integrate tracking as a part of their own operations. This high‐level integration offers more options to improve the management and hence the performance of the whole supply chain than low‐level integration.Originality/valueIOS implementation projects are seldom studied from the perspectives of buyers and suppliers in the supply chain.

In our vision of the Internet of Things, it is possible to easily query and set up information flows between any kinds of products, devices, computers, users and information systems in general. However, for the moment it is not possible due to the lack of sufficiently generic and standardized application-level interfaces for exchanging the kind of information required by an Internet of Things. The Quantum Lifecycle Management (QLM) messaging standards have been developed and are proposed as a standard application-level interface that would fulfill such requirements. The article presents the design principles and provides a high-level description of QLM messaging. Real-life implementations illustrate why such a messaging interface is needed and compares it with related standards.

International audience; Intelligent products may be considered as information vectors, conveying their own information from a phase of its life cycle to another. Considering that such a product could be made with "communicating material", in previous work, a data dissemination process has been developed with the aim of selecting information from a database, that should be stored on the product according to the current stage of its life cycle. This selection is based on an indicator of relevance which depends on a multitude of criteria, whose weights are evaluated by a group of experts. The set of expert opinions must be formalized in accordance with a mathematical theory and then, synthesized by a suitable aggregation method. In this framework, three aggregation methods are introduced and compared. This comparison is carried out based on the scenario of data dissemination when using intelligent products. Results enable to assess the goodness of fit of the three aggregation methods.

The basis for Sustainable PLM is enabling Intelligent Products to communicate between themselves and with other systems in order to reduce CO"2 emissions, energy usage, and environmental damage. This type of communication between Intelligent Products and other information systems with the objective of reducing environmental impacts is an example of closed-loop product lifecycle management. The objective of the paper is to outline an architectural information system model for implementing Sustainable PLM based on experiences from a number of real-life applications. The technological challenge for developing Sustainable PLM is the high number and variety of information systems that need to communicate over organizational limits and over time. In the paper we describe how Sustainable PLM has been implemented using Intelligent Products in a number of representative real-life applications.

Part 14: Product, Service and Systems; International audience; Lifecycle management enables enterprises to manage their products, services or product-service bundles. IoT and CPS have made products and services smarter by closing the loop of data across different phases of lifecycle. Similarly, CPS and IoT empower cities with real-time decision-making capabilities enabled by real-time data streams from heterogeneous objects. Yet, cities are smarter and more powerful when relevant data can be exchanged between different systems across different domains. From engineering perspective, smart city can be seen as a System of Systems (SoS) composed of interrelated/ interdependent smart systems and objects. To better integrate people, processes, and systems in the smart city ecosystem, this paper discusses the use of PLM/ SLM to better manage smart cities. Considering the differences between ordinary and smart service systems, this paper seeks better understanding of lifecycle aspects in the smart city context. As a proof-of-concept, the proposed approach is applied to a smart parking use-case.

The significance of tracking in operations management has been overshadowed, theoretically by the concept of supply chain visibility, and practically by the attention grabbing radio frequency identification (RFID) technology. This paper describes how uses of tracking for operations management, specifically, to improve the management of project and service supply chains, were explored and developed in a ten-year research program. Key results of the program are synthesized and linked to the relevant academic discourse in operations management using design science methodology.

PurposeThe purpose of the paper is to evaluate the feasibility of implementing a tracking based inventory management system in temporary storage locations of a project delivery chain. To describe the use of tracking based inventory information for improved logistics control in equipment delivery and installation.Design/methodology/approachA solution design experiment was carried out in 16 temporary storage locations with one original equipment manufacturer and four installation partners.FindingsIt is feasible to implement tracking based inventory management in temporary storage locations. The challenge is to ensure that installation partners adopt the system. The benefit is improved logistics control of equipment delivery and installation for the original equipment manufacturer.Research limitations/implicationsTracking information is more useful than conventional stock keeping in project delivery. By monitoring the dwell time of delivery items it is possible to identify and resolve problems in project execution.Practical implicationsInventory management in temporary storage locations help project management, project logistics, and central logistics organizations carry out their work more effectively. Implementation can be based on tracking.Originality/valueThe paper's value lies in empirical tests and evaluation of tracking based inventory management in temporary storage locations.

The Industrial Internet promises to radically change and improve many industry's daily business activities, from simple data collection and processing to context-driven, intelligent and pro-active support of workers' everyday tasks and life. The present paper first provides insight into a typical industrial internet application architecture, then it highlights one fundamental arising contradiction: “Who owns the data is often not capable of analyzing it”. This statement is explained by imaging a visionary data supply chain that would realize some of the Industrial Internet promises. To concretely implement such a system, recent standards published by The Open Group are presented, where we highlight the characteristics that make them suitable for Industrial Internet applications. Finally, we discuss comparable solutions and concludes with new business use cases.

A manufactured product usually has a great amount of design knowledge and other product information associated with it in CAD drawings and other technical documentation. Today, such product information mainly enables preventive maintenance of products. By collecting usage, performance and maintenance information about the product, it could be possible to perform more predictive maintenance. The key issue is to document product information in a way that would enable analysing the relation between usage parameters and actual product failures. Semantic networks are here proposed as an intermediate knowledge representation format for combining such static and dynamic product information.

Tracking of shipments is an important element of customer service in the transportation industry; and essential for logistics services as merge‐in‐transit. However, contemporary tracking systems are designed for use within a single company, and are thus invariably inadequate for multi‐company environments. The single company focus has led to a reduced span of monitoring and a diluted accessibility of information due to proprietary tracking codes and information architectures centred on the tracking service provider. This paper presents a novel forwarder‐independent approach for solving the difficulties of tracking in multi‐company supply networks. The research argues that the proposed tracking approach is superior to contemporary approaches for material flow tracking in short‐term multi‐company distribution networks.

The management of single-item level information has grown to be one of the greatest challenges of supply network management. The main reasons for this are the increasing product customisation and increasingly complex supply networks. Product customisation adds to the quantity and specificity of product-related information. Current mainstream solutions, based on integrating product information databases, are not suitable for complex, short-term supply networks. This paper presents an approach and a proposed system for managing single-item level information. The approach we call product centric information management is based on centralising information to the individual products. The proposed system uses software agents, peer-to-peer information sharing, and a coding mechanism that utilises the domain names of the Internet. We also review applications of the system in tracking and logistics control.

International projects present really difficult logistics challenges. In international investment projects, a vast number of individualised deliveries has to be managed through a large supply network in a tight timeframe. This article investigates how the logistic challenges of international projects can be solved by utilising advanced web technologies and product identification. The paper presents a control system being built at Helsinki University of Technology, which is based on distributed programming, and wireless identification technologies. The aim of the system is to change the controlling mechanisms of project deliveries by giving the deliveries themselves the means with which to control their route. This enables the material flows in the project delivery chains to be controlled from the inside of the material flow itself.

In the so-called "Internet of Things" (IoT), mobile users and objects will be able to dynamically discover and impromptu interact with heterogeneous computing, physical resources, as well as virtual data. It is a fact today that more standardized formats, protocols and interfaces must be built in the IoT to provide more interoperable systems. However, even if a protocol would become the de facto IoT standard for data exchange, this would not solve all issues related to system and information integration into the IoT. Indeed, a key challenge is to allow integrating all types of existing domain- or vendor-specific application with such a standard. In this regard, this paper develops a generic framework for such an integration that consists in using the basic communication interfaces supported by the domain-specific application (e.g., basic read and write operations) to extend them into more advanced interfaces provided by IoT standards (e.g., to support subscription mechanisms). In this paper, the set of standardized interfaces defined in a recent IoT standard proposal, referred to as Quantum Lifecycle Management (QLM) messaging standards, are considered for developing the integration framework. A case study using a building-specific application, namely openHAB, is then presented to validate the framework practicability.

The challenge faced by supplier companies in the grocery supply chain for implementing collaborative planning, forecasting and replenishment (CPFR) is how to get the retailer to forecast, especially when it has not been necessary before. In this paper a solution that would allow collaboration on a wide scale is presented. The forecasting approach is called “rank and share” and uses input from the retailer’s existing planning process – the category management process. The benefit of using category management as the basis is that the retailer can scale up collaboration with a large number of suppliers without increasing planning resources. For the supplier the benefit is point of sales forecasts at the time of the assortment decision. To support this collaborative forecasting process there is a need for more robust replenishment solutions, new measures to illustrate benefits, and for a distributed planning architecture and software. Potential solutions for these are also discussed in the paper.

Building Information Management systems have started to leverage new kinds of digital information infrastructures that integrate activities related to design, budgeting, scheduling, analysis, material management, and human resources. Companies implementing such systems have no other option today than exchanging information among themselves in a proper and efficient way. Industry foundation classes (IFCs) provide useful information structures for such a data sharing. However they do not specify how to capture, exchange and synchronize the information between distinct entities (i.e. information systems like sensors, servers, smart products…) throughout the building lifecycle. Accordingly, this paper investigates existing messaging protocols in order to identify which one is the most appropriate for supporting building lifecycle management; i.e a flexible protocol that provides sufficiently generic communication interfaces. A platform set up on a university campus based on the selected messaging protocol is then presented. Within this context, the research agenda that should be pursued to develop new techniques and algorithms for optimizing the building energy management is announced.

International audience; The so-called Internet of Things (IoT) presents a tremendous opportunity for multitude of users to be connected to anything, whenever needed, wherever needed, by whoever needs it. Such opportunities, nonetheless, require more advanced and standardized communication interfaces to facilitate interactions between any types of "things" (smart devices, sensors, systems, networks, etc.). Recent standard proposals as the Quantum Lifecycle Management (QLM) messaging standards were developed and are proposed to provide such standardized interfaces for IoT data exchange. These standards make it possible to develop innovative and standardized techniques to address other issues in the IoT such as the management of replicas of a same data between distinct objects in a peer-to-peer, loosely coupled ways. This paper investigates new strategies-based agent models for peer-to-peer data synchronization in the IoT using the standardized interfaces provided by the QLM standards. This enables the development of models not designed domain-, vendor-or application-specific, as is often the case. Our synchronization models are implemented and assessed considering a real home automation platform.

International audience; The amount of data output into our environment is increasing each day, and the development of new technologies constantly redefines how we interact with information. In the context of product life cycle management, it is not uncommon to use intelligent products to ensure an information continuum throughout the product life cycle (e.g., for traceability purposes). Integrating intelligence and information into products themselves is now possible through numerous technologies (RFID, communicating materials). However, these technologies currently have low memory capacities (several kilobytes or megabytes), whereas to product databases are becoming larger and larger (several gigabytes or terabytes). As a result, a data dissemination process is required to determine the relevant information that should be stored on the product. This paper proposes a multiple-criteria decision-making (MCDM) method based on a fuzzy Analytical Hierarchy Process (fuzzy AHP). This method is context-aware and supports the aggregation of opinions from a group of experts. An application is proposed to embed context-sensitive information in a "communicating textile".

Part IV: ICT and Emerging Technologies; International audience; This paper presents an overview of the proposed QLM standard under development within the QLM Work Group of The Open Group. QLM aims to become a reference set of standards to be used to provide and exchange information between “intelligent” products and other systems. A part explains an introduction to QLM, the paper presents also an application scenario where QLM standards are already used in industrial practice.

With increasing globalization and loosely-coupled business relations between different companies, the importance of information exchange standards is increasing. GS1's Electronic Product Code Information Services (EPCIS) is currently one of the main standards proposed for inter-organizational data exchange for trace and track purposes in the supply chain. However, some parts of the EPCIS framework are yet to be defined and the standard has to overcome some obstacles to be used as a global standard for trace and track applications. This paper tries to address the main question whether EPCIS has the potential to ‘take off' as a globally accepted data-exchange standard.

This paper addresses the question regarding the point at which books should be tagged in the book supply chain, and where tracking could begin at different levels of adoption among retailers. Alternative solution designs are analysed by comparing the costs and benefits of the supply chain-wide radio frequency identification (RFID) tagging with RFID tracking solutions that cover only part of the supply chain. The analysis is based on modelling the RFID tag as a product feature and considering the tagging of books as a potential postponement decision. The cost estimates are based on activity-based costing and used to compare alternative solution designs for introducing RFID tracking in book retailing. Attaching RFID tags in the manufacturing phase is in many settings likely to be cheaper than downstream tagging. However, early tagging requires a threshold share of retailers to adopt RFID tracking in their store operations and be willing to bear the additional product costs.

Research on after-sales supply chain management has commonly emphasized strategic business aspects and the application of generic operations control principles. The adoption of Internet and identification technology in after-sales operations opens up new and interesting perspectives that may enable a radical reorganization of after-sales supply chain planning and control. This chapter introduces the product centric service concept, which is the particular organizational perspective that is the basis for the reorganization of the after-sales supply chain. A two-layer approach for organizing after-sales supply chain planning and control is described and the potential benefits explained.

Building automation is a domain where interoperability between equipment made by different manufacturers is rare. In addition to competing standards, completely proprietary solutions are also common. This is a great challenge for implementing ‘ubiquitously smart buildings’, where building automation systems, user interfaces and services can interact seamlessly. The paper describes how a Semantic Information Broker (SIB) can be used as an enabler of interoperability, where an ecosystem of supplementary services is created through manufacturer-agnostic agents.

The Internet of Things notion is sometimes being employed to signify the use of Radio Frequency Identification (RFID) for tracking and tracing of products in supply chains. However, RFID is only one Auto-ID technology among others. The world is already full of products with embedded identification, processing power, sensors etc. that can do much more than ordinary RFID tags. When such products will have the means to communicate between themselves and with other systems we will eventually reach a limit where they could be called Intelligent Products. Intelligent Products are capable of collecting information and reacting on it proactively, e.g. estimating needs for maintenance or repair. With increased computing power and communication capabilities, products may also become pro-active.

The TraSer project is an EU-funded project that investigates the best way small and medium-sized companies can develop and support network-level information services. The project involves seven different network-level solution pilots that include physical asset tracking and tracking of electronic product data the results of which show that increased tracking and tracing possibilities offer great potential.

Currently only larger companies get most benefit from advanced tracking. A research project aims to provide a lighter option suitable also for smaller companies. Primary goal is free, open-source software package offering affordable item-centric tracking and tracing solutions. One way to find new potential solutions and applications is through a series of workshops, where the idea is to give the audience a hands-on experience of the tracking system usage and the current solutions available. For this purpose, we have created a framework for the development of tracking-based business and implemented an open-source tracking software demo. The paper gives an overview of our proposed framework, guidelines how to conduct a successful workshop and instructions how to use our workshop demo system.

The management of item-level information is one of the biggest challenges currently facing supply chain management. Managing product-related information grows ever more difficult because increasing product customisation adds to the amount and variety of product-related information, and increasingly complex supply networks complicate the integration of product information databases. A potential solution for the problems of item-level information management is moving to product centric information management, namely centralising the information to individual products and accessing the relevant information directly through them. This paper presents an approach and a system for managing item-level information. The system is based on software agents, peer-to-peer information, sharing, and a coding scheme that utilises the already allocated domain names of the Internet. Applications of the system to tracking and logistics control are reviewed.

Traditionally, production control on construction sites has been challenging, and still remains challenging. The ad-hoc production control methods that are usually used, most of which are informal, foster uncertainty that prevents smooth production flow. Lean construction methods such as the Last Planner System have partially tackled this problem by involving site teams into the decision making process and having them report back to the production management system. However, such systems have relatively long “lookahead” planning cycles to respond to the dynamic production requirements of construction, where daily, if not hourly control is needed. New solutions have been proposed such as VisiLean, KanBIM, etc., but again these types of construction management systems require the proximity and availability of computer devices to workers. Through this paper, the authors investigate how the communication framework underlying such construction management systems can be further improved so as to fully or partially automate various communication functions across the construction project lifecycle (e.g., to enable lean and close to real-time reporting of production control information). To this end, the present paper provides evidences of how the Internet of Things (IoT) and related standards can contribute to such an improvement. The paper then provides first insights – through various construction scenarios – into how the proposed communication framework can be beneficial for various actors and core business perspectives, from lean construction management to the management of the entire building lifecycle.

With the evolution of vehicular networks, the Intelligent Transportation System (ITS) has emerged as a promising technology for autonomous road transport. For a successful deployment of ITS, security and reliability are the most challenging factors to be tackled to ensure Vehicle-to-Infrastructure (V2I) and Infrastructure-to-Infrastructure (I2I) communications. Due to unreliable communications in vehicular networks, implementing fault-tolerant techniques for the Road Side Unit (RSU) infrastructure is an imperial need. Within this context, the contributions of this paper are twofold: (i) we propose a distributed fault-tolerant framework for V2I and I2I communications based on edge computing to resolve hardware- and network connectivity-based failures. The fault tolerance issue is addressed by employing open messaging standards as a subscription-based data replication solution at the edge. We also adopt Kubernetes for the fault-tolerant management, combined with high-availability mechanism, allowing automatic reconfiguration of the data processing pipeline; and (ii) we implement a demonstrator system for vehicular networks-based smart mobility to assess fault tolerance capabilities. The experimental results show that our proposed framework dynamically tolerates RSU-related failures during the vehicular communication phase.

In order to create energy-efficient, ubiquitous and green information systems, it will be necessary to exchange information and co-ordinate action between systems that have traditionally not been interoperable. Providing such interoperability is a major challenge unless the underlying information systems are implemented in a way that allows for the collection of relevant information, such as (near) real-time sensor readings and higher-level events, as well as and the ability to take proper actions based on that information. The paper shows how and why instance-informed information systems are a requirement for implementing energy-efficient and green information systems, as well as showing how such information systems have been implemented in several real-world applications.

The promise of process integration between organizations too often is unfulfilled and new approaches are needed. Distributed control is a new and exciting opportunity to build more effective process networks for a wide range of applications in logistics and product development. A solution based on distributed control around the consumers of services in process networks is proposed. In logistics, it is the physical delivery that becomes the focus for distributed control when you approach the service environment from the consumer perspective. In collaborative design and manufacturing, it is the product model that becomes the focus of control. A consumer perspective provides key guidelines that help manufacturers and service providers identify the design of process networks that most efficiently add value in different industries and for different applications.

This paper presents an overview of the field of Intelligent Products. As Intelligent Products have many facets, this paper is mainly focused on the concept behind Intelligent Products, the technical foundations, and the achievable practical goals of Intelligent Products. A novel classification of Intelligent Products is introduced. which distinguishes between three orthogonal dimensions. Furthermore, the technical foundations in the areas of automatic identification and embedded processing, distributed information storage and processing, and agent-based systems are discussed, as well as the achievable practical goals in the contexts of manufacturing, supply chains, asset management, and product life cycle management. (C) 2008 Elsevier B.V. All rights reserved.

The importance of product information management during the whole lifetime of the product has increased due to the technical sophistication of products as well as stricter governmental regulations for lifecycle management. Just sending the relevant product information downstream in the supply chain does not solve the challenges of product information management of complex products due to difficulties in updating the information and a risk of information overflow in the supply chain. This article describes an agent-based information management model that can be used for managing the information of complex products at a component level in a distributed manner. Further the paper presents an information management platform that can achieve information management requirements by using seven distinct messages.

Main advantages of distributed software are that computers connected over a network may access information stored anywhere in the network at any time and get automatically notified about information changes. This paper describes how a distributed software is built for collaborative demand forecasting. Demand forecasts of both providers and clients can be accessed and used for getting a better idea about the marketplace and thereby do more accurate demand forecasting.

Agent-based architectures, taking queues from object-oriented programming, can make product information accessible in controlled ways over the Net.

Managing product information for product items during their whole lifetime is challenging, especially during their usage and end-of-life phases. A major challenge is how to keep a link between the product item and its associated information, which may be stored in backend systems of different organisations. In this paper, we analyse and compare three approaches for addressing this task, i.e. the EPC Network, DIALOG and WWAI.

International audience; IoT-enabled smart city service systems are well recognized to address issues of urbanization in the city environment. In most cases, those systems are vertically locked; and from lifecycle perspective, independently designed, built and operated. Therefore, there is a need for a global vision to horizontally integrate those systems to ensure smooth flow of information across different domains. To ensure interoperability and better management across different phases of smart city lifecycle, this paper highlights the need for smooth exchange of two types of data/ information: (i) generated data from IoT data sources; (ii) lifecycle system related information. This paper proposes the use of The Open Group IoT standards to ensure interoperability and smooth data exchange; and the use of lifecycle management system to create Bill of Materials; export Objects' Tree and exchange lifecycle system related information. It also demonstrates the interaction between the proposed lifecycle system and IoT platform within smart parking use-case.

Explainable AI (XAI) has emerged in recent years as a set of techniques and methodologies to interpret and explain machine learning (ML) predictors. To date, many initiatives have been proposed. Nevertheless, current research efforts mainly focus on methods tailored to specific ML tasks and algorithms, such as image classification and sentiment analysis. However, explanation techniques are still embryotic, and they mainly target ML experts rather than heterogeneous end-users. Furthermore, existing solutions assume data to be centralised, homogeneous, and fully/continuously accessible—circumstances seldom found altogether in practice. Arguably, a system-wide perspective is currently missing. The project named “Personalized Explainable Artificial Intelligence for Decentralized Agents with Heterogeneous Knowledge ” (Expectation) aims at overcoming such limitations. This manuscript presents the overall objectives and approach of the Expectation project, focusing on the theoretical and practical advance of the state of the art of XAI towards the construction of personalised explanations in spite of decentralisation and heterogeneity of knowledge, agents, and explainees (both humans or virtual). To tackle the challenges posed by personalisation, decentralisation, and heterogeneity, the project fruitfully combines abstractions, methods, and approaches from the multi-agent systems, knowledge extraction/injection, negotiation, argumentation, and symbolic reasoning communities.

Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue. Intelligent software agents can behave intelligently in well-defined scenarios, relying on Machine Learning (ML), symbolic reasoning, and the ability of their developers for tailoring smart behaviors to specific application domains. However, to forecast the evolution of all possible scenarios is unfeasible. Thus, intelligent agents should autonomously/creatively adapt to the world’s mutability. This paper investigates the meaning of imagination in the context of cognitive agents. In particular, it addresses techniques and approaches to let agents autonomously imagine/simulate their course of action and generate explanations supporting it, and formalizes thematic challenges. Accordingly, we investigate research areas including: (i) reasoning and automatic theorem proving to synthesize novel knowledge via inference; (ii) automatic planning and simulation, used to speculate over alternative courses of action; (iii) machine learning and data mining, exploited to induce new knowledge from experience; and (iv) biochemical coordination, which keeps imagination dynamic by continuously reorganizing it.

Recently, the eXplainable AI (XAI) research community has focused on developing methods making Machine Learning (ML) predictors more interpretable or explainable. Unfortunately, researchers are struggling to converge towards an unambiguous definition of notions such as interpretation or explanation---which are often (and mistakenly) used interchangeably. Furthermore, in spite of the sound metaphors that Multi-Agent System (MAS) could easily provide to address such a challenge, an agent-oriented perspective on the topic is still missing. Thus, this paper proposes an abstract and formal framework for XAI-based MAS, reconciling notions and results from the literature.

Recently, the Deep Learning (DL) research community has focused on developing efficient and highly performing Neural Networks (NN). Meanwhile, the eXplainable AI (XAI) research community has focused on making Machine Learning (ML) and Deep Learning methods interpretable and transparent, seeking explainability. This work is a preliminary study on the applicability of Neural Architecture Search (NAS) (a sub-field of DL looking for automatic design of NN structures) in XAI. We propose Shallow2Deep, an evolutionary NAS algorithm that exploits local variability to restrain opacity of DL-systems through NN architectures simplification. Shallow2Deep effectively reduces NN complexity – therefore their opacity – while reaching state-of-the-art performances. Unlike its competitors, Shallow2Deep promotes variability of localised structures in NN, helping to reduce NN opacity. The proposed work analyses the role of local variability in NN architectures design, presenting experimental results that show how this feature is actually desirable.