Using artificial intelligence for supporting museum organization F. Amigoni 1, V. Schiaffonati 2 1 Artificial Intelligence and Robotics Laboratory - DEI - Politecnico di Milano - amigoni@elet.polimi.it 2 Artificial Intelligence and Robotics Laboratory - DEI - Politecnico di Milano - schiaffo@elet.polimi.it Abstract The application of artificial intelligence tools to cultural heritage is acquiring an increasing importance, promoting new technological solutions for museums and art exhibitions. We present a system, called Minerva, able to automatically organize virtual museums, given the set of works of art and the environments in which they must be displayed. We discuss an experimental implementation of Minerva that arranges a part of the archeological finds belonging to the collection of the Archeological Museum of Milan. 1. Introduction The study of computational tools for enhancing the fruition of cultural contents is a topic of increasing importance in current research [3]. In particular, the application of artificial intelligence (AI) tools to cultural heritage is acquiring a central role, promoting new technological solutions for museums and art exhibitions. We present a software system, called Minerva, able to automatically organize virtual museums, given the set of works of art and the environments in which they must be displayed. By organization we mean two distinct processes: the preparation, which is the arrangement of works of art in conceptually relevant ordered groups, and the allocation, which is the placement of these groups within a given geometrical space trying to preserve their arrangement. We present an experimental implementation of Minerva that settles some archeological finds belonging to the collection of the Archeological Museum of Milan. Minerva is an example of how traditional and recent AI techniques can be successfully applied not only to the fruition of works of art, but also to their organization and management. From a technical point of view, Minerva blends together the classical inferential techniques of AI [6] and the recent paradigm and technology of multiagent systems that is very influential in current AI research [8]. It is thus composed of agents that are programs designed to be modular and independent in their activation and operation. In designing Minerva we have emphasized the possibility to interact with the user: the final organized museum is the expression of the inferential processes performed by the system supported by a dialogic interaction with the user. This paper is organized as follow. The next section describes a typical scenario of employment of Minerva as supporting a museum organizer during the organization of an archeological museum. Section 3 presents an overview of the technical implementations of the system. Section 4 concludes the paper. 2. A scenario of use The main purpose of Minerva is the automatic organization of museums, given the works of art and the environments in which they must be displayed. The task of organizing a museum is usually thought as a typical human-exclusive activity based on aesthetic and personal judgments. The final result is a global coherent setting that allows an effective visit of the museum. However, the organization follows explicit criteria and some of them can be considered for an automatic organization. Among the latter ones, there exist physical criteria: for instance, some works of art cannot be inserted in some rooms, some rooms can be scarcely lighted, too hot, or too cold to host works of art. In addition, also artistic criteria can be taken into account: they can play a central role in
the final result, since they concern, for example, how to give emphasis to particularly important works of art or how to build connections among different works of art. It is worth noting that the purpose of Minerva is not to substitute humans in organizing museums; rather it aims at supporting them in their work by enhancing their creativity, while providing a sophisticated computational tool for automatizing some tasks related to the museum organization. The museum produced at the end of the organization process is the result of both the intelligent abilities of the system and the decisions of the human user. Indeed, the user interacts with the program and intervenes when the system is not able to manage some part of the process. In order to describe the functioning of the system, let us consider an implementation of Minerva that organizes an archeological museum. The works of art the system manages are a subset of those belonging to the collection of the Archeological Museum of Milan. The user (typically, a museum organizer) can select a set of works of art and an environment in which to display them. Moreover, he or she can tune the various criteria driving the processes of preparation and allocation of the selected works of art in the selected environment (Figure 1). Fig. 1 The criteria of the preparation process for an archeological museum. The criteria of the preparation process determine the groups of works of art and the order in which are shown. For an archeological collection the chronological criterion is, of course, the most important one. Besides that, other five criteria can be selected: they have been chosen on the basis of what a small group of archeological experts told us to be relevant in organizing archeological museums. They are: the place of origin of the works of art, their material, their culture, their function, and the kind of objects (such as statues, steles, and busts). According to these criteria, the works of art are classified in homogeneous ordered groups (Figure 2). During the preparation process, the user has the possibility to change both the groups (e.g., by splitting a group) and their order.
Fig. 2 The ordered groups of works of art. The parameters of the allocation process control all the aspects of the placement of the works of art in the environment, including the maximum and minimum occupation of rooms and shrines and the order (clockwise or anticlockwise) in which the works of art are placed in the rooms. When the preparation and the allocation activities have been performed, the user can visit the automatically organized museum in a VRML virtual reality setting, as shown in Figure 3. Fig. 3 The VRML virtual visit of an automatically organized archeological museum. Each work of art is virtually reproduced according to its three-dimensional model obtained from the real object or from its representations (e.g., pictures). In the virtual museum, the user can follow a list of viewpoints and access the detailed information (including a better VRML model and a number of textual descriptions at various levels of detail) associated to the works of art by clicking on the works of art themselves.
3. Overview of technical implementation Minerva is implemented as a multiagent system composed of autonomous computational entities, called agents: some of them exploit the inferential techniques of AI in order to carry out the organization and management of the works of art. The museum organizations are the result of the cooperation activity of the agents of Minerva. A preliminary description of the archeological version of the system can be found in [1], while a more detailed technical description of Minerva can be found in [2]. The central concept of our system is that of agent. The agents are intelligent and autonomous programs providing specific abilities and are coded in JAVA. More precisely, we employ the JADE framework [5] as middleware and the JESS framework [4] to perform inferential activities. In the following the main agents of Minerva are described. The user interface agent generates the pages displayed to the user via a HTML browser and manages the interaction with him or her according to what discussed in the previous section. In particular, the user interface agent translates the geometrical description of the allocation of a collection in an environment, which is initially produced in the Minerva internal format, to the format displayed to the user (VRML [7]). The user interface component reads (from the works of art database) the threedimensional models of the works of art and inserts them in the three-dimensional model of the environment (read from the environments database) according to the geometrical result of the allocation process. Then, the VRML model is displayed to the user who can navigate inside it. Let us now turn to the agents that constitute the kernel of Minerva. Given a collection of works of art and an environment (selected by the user), two agents operate to find, respectively, a preparation and an allocation. The first agent, called preparator agent, automatically determines, on the basis of the criteria selected by the user, the conceptual arrangement in which the works of art of the collection will be displayed. Firstly, it classifies the works of art in groups and, then, it orders these groups. More precisely, the preparator agent uses the JESS engine to apply inferential techniques for classifying the works of art of the selected collection into groups, each one composed of homogeneous objects. In doing this, the preparator agent exploits the expertise inserted in its knowledge base about criteria concerning the possible ways in which the pieces of a collection can be classified and grouped. This expertise has been acquired from human experts in archeological museum organizations. The criteria, expressed as rules in JESS, the preparator agent applies to create and order groups of homogeneous objects are those selected by the user (Section 2). At the end of the process the preparator agent stores the groups of works of art in a taxonomic tree. The ordered groups produced by the preparator agent and the environment selected by the user constitute the input for the allocator agent. The allocator agent automatically finds, within a given environment, the best geometrical allocation for the works of art of the groups in the taxonomic tree, preserving the ordering on groups imposed by the preparator agent. Also the allocator agent exploits the knowledge inserted in its knowledge base about criteria concerning where to place the works of art in a given environment. These criteria, expressed as rules in JESS, consider, among others, the minimum and maximum occupation of the space in a room, the minimum and maximum occupation of the perimeter of a room, and the distances governing the collocation of the shrines according to the location of the doors, windows, and other shrines. The groups of works of art are allocated in the rooms in decreasing order (as established by the preparator agent). In particular, the allocator agent tries to allocate each group in a different room. If it fails, the allocator agent asks the user if the group should be spread over more rooms or more groups should be allocated in the same room. 4. Conclusions In this paper we have illustrated, by discussing Minerva and its experimental validation for an archeological museum, how traditional and recent AI techniques can be successfully applied to cultural heritage and, in particular, to the innovative organization, management, and fruition of works
of art. Future work will be devoted to improve some technical aspects of Minerva: in particular, the communication and the negotiation aspects of agent interaction and the automatic retrieval of information concerning the works of art from the Web. Furthermore, we aim to apply the same kernel of Minerva to the organization of other museums and collections, where other criteria are employed during the organization process. This extension of the system has basically two purposes: to validate Minerva in different contexts and to assess the generality of its architecture. Acknowledgements We would like to thank Glauco Mantegari e Lucio Perego, for their advice concerning the organization criteria of archeological works of art, and Fabio Ghidotti, for the implementation of the system. References [1] Amigoni, F., Schiaffonati, V., Somalvico, M., Minerva: an artificial intelligent system for composition of museums in Proceedings of the International Cultural Heritage Informatics Meeting (ICHIM01), 2, pp. 389 398, 2001 [2] Amigoni, F., Schiaffonati, V., The Minerva Multiagent System for Supporting Creativity in Museums Organization, Proceedings of the IJCAI2003 (Eighteenth International Joint Conference on Artificial Intelligence) Workshop on Creative Systems: Approaches to Creativity in AI and Cognitive Science, pp. 65-74, 2003 [3] Edmonds, E., Candy, L., Explorations in Art and Technology, Springer-Verlag, 2002 [4] Friedman-Hill, E., Java Expert System Shell, Sandia National Laboratories, http://herzberg.ca.sandia.gov/jess/, 2005 [5] JADE, Java Agent Development Framework, TILAB, http://sharon.cselt.it/projects/jade/, 2005 [6] Russell, S., Norvig, P., Artificial Intelligence: A Modern Approach, Prentice Hall, 2002 [7] VRML, Virtual Reality Modeling Language, Web 3D Consortium, http://www.web3d.org/, 2005 [8] Weiss, G., Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence, The MIT Press, 1999