Ebook: Prediction and Recognition of Piracy Efforts Using Collaborative Human-Centric Information Systems

An Advanced Study Institute (ASI) “Prediction and Recognition of Piracy Efforts Using Collaborative Human-Centric Information Systems” was held in Salamanca, Spain, September 19-30, 2011.

An ASI is one of many types of funded group support mechanisms established by the NATO Science Committee to contribute to the critical assessment of existing knowledge on new important topics, to identify directions for future research, and to promote close working relationships between scientists from different countries and with different professional experiences.

The NATO Science Committee was approved at a meeting of the Heads of Government of the Alliance in December 1957, subsequent to the 1956 recommendation of “Three Wise Men” – Foreign Ministers Lange (Norway), Martino (Italy) and Pearson (Canada) on Non-Military Cooperation in NATO. The NATO Science Committee established the NATO Science Programme in 1958 to encourage and support scientific collaboration between individual scientists and to foster scientific development in its member states. In 1999, following the end of the Cold War, the Science Programme was transformed so that support is now devoted to collaboration between Partner-country and NATO-country scientists or to contributing towards research support in Partner countries. Since 2004, the Science Programme was further modified to focus exclusively on NATO Priority Research Topics (i.e. Defence Against Terrorism or Countering Other Threats to Security) and also preferably on a Partner country priority area.

The objective of this ASI was to discuss how to help predict, recognise and deter maritime piracy through the use of collaborative human-centric information support systems. Maritime piracy is a widespread international concern. Over the years, it has been on the rise, with the number of attacks increasing substantially. Vessels are extremely susceptible to hostile boarding owing to inherent vessels' vulnerability due to slowness (tonnage, deep sea vessels, massive size and weight). Furthermore, technological improvements have resulted in smaller crews on (larger) vessels. In addition, ship owners are reluctant to directly address the issue of maritime piracy for commercial reasons. The lack of law enforcement makes pirates more daring since they know that there are no police officers or government officials present in the middle of the sea to capture them while they are committing their crimes. It is necessary to defeat piracy and violent marine crime through anti-piracy and counter-piracy operations: “Anti-piracy training and operational security awareness is mandatory for vessel owners and vessel crew.” Crisis Management and anti-piracy programs must be defined and followed in order to reduce the vulnerability of the vessel.

Collaborative human-centric information support systems can significantly improve the ability of every nation to predict and prevent a pirate attack or (if unsuccessful) to rapidly recognize the nature and size of the attack, and then improve the collective response to that emergency. Inherent to the concept of collaborative information support systems are: human-system integration, cognitive system engineering methodologies, collaborative environment technologies, knowledge exploitation and data/information mining technologies instantiated into concepts/approaches of decision support (collaborative information systems) centred to human, where the human is an integrated part of the system.

Operating in the crisis management and anti-piracy program environment, the decision makers at all levels (e.g., incident commanders and their staff) can use collaborative human centric information support capabilities to:

• Understand the vulnerabilities of the maritime location by considering all social, geopolitical, economical, inter-agency policy and jurisdictional aspects;

• Rapidly develop shared understandings of the operational environment; to plan operations; to monitor the situation and the execution of the plans; to ensure that each individual worker is productive and concentrated on its assigned roles and tasks;

• Formulate evaluation criteria, decide on what to do, and synchronize a diverse set of plans and actions; aiding experts to work together effectively with other relevant environment authorities (military-civilian) at all levels, and with international allies. This encompasses situation monitoring and coordination with multi-agency, multi-jurisdiction and multi-national operations.

• Enhance existing business procedures to address security issues and provide enhanced situational awareness and inter-agency co-operation: support the development of A Standard Operating Procedure (SOP);

• Support Crew Security Awareness and Detection Training: the proactive involvement of the crew to DETECT and DETER attackers will dramatically increase the operational security of any vessel; the adversaries rely on three heavy fundamentals when attacking a vessel – Surprise, Speed, and Violence (or implied violence). The ability to DETECT and DETER should also be coupled with the ability to RESPOND.

• Provide capability and technologies for deterrence, interdiction and/or response based on estimation of threat characteristics and types, threat stages and ranges and behaviour; Advise on Anti-Piracy Tracking Devices;

• Support better policing: develop close cooperation with local law enforcement agencies and provide them with intelligence of better and better quality, they'll be able to move aggressively and make arrests;

• Enable the RESPONSE communities to timely and securely access data, information, services, etc. relevant to their roles and responsibilities, regardless of what agency operates the facilities where the critical data and services reside.

This ASI involved both technology and domain experts, as well as students from pertinent fields of study who enhanced their awareness of the requirements, issues and policy, as well as information technology support systems to help predict, recognise and deter maritime piracy efforts through lectures, plenary sessions and brainstorming sessions in smaller interdisciplinary groups. A significant observation of previous similar NATO ASIs and ARWs has been that the domain experts (personnel from various organizations responsible for maritime security) have little understanding of the wide variety of technology solutions that are available and the way they can enhance the performance of such support systems. Similarly, although technology experts have a general understanding of the requirements in various security systems, they don't have visibility into operations and implementation including constraints and issues due to a variety of factors (policy, geopolitical, legal, personnel, training, etc.). The attendance of many leading scientists, domain experts as well as other participants (students) from many countries with backgrounds in a variety of contributing disciplines provided an opportunity for them to improve mutual understanding and become cognizant of the specific requirements and issues of anti-piracy operations and the pertinence of collaborative human-centric information support systems in a variety of applications exploitable in their respective countries.

Although an ASI is not usually structured to include brainstorming sessions to conduct in depth analysis of these aspects, this ASI program included study sessions where smaller groups of students lead by 3-4 lecturers discussed the information provided during the lectures and brainstormed on how collaborative human-centric information systems and collaborative decision support capabilities could help in prediction and recognition of maritime piracy efforts. During the plenary discussions a framework for piracy prevention, containment and consequence management was proposed, which leveraged the assertions from a previous NATO ASI stating that decision support is achieved through analysis of three interrelated aspects, namely people, organization and technology. It is necessary to analyse the relationships between organizational structure, the processes (operational, logistical, political, legal, inter-jurisdictional, etc.) that the people are involved in, and the technologies that are available to provide decision support enhancing performance of these processes. As part of the study sessions, the small teams of lecturers and students selected specific elements of this framework, analysed the relationships within the framework and evaluated the technologies to enable enhanced decision support. Within the scope of this ASI it was not feasible to analyse the whole framework, or even do an exhaustive analysis of the selected elements. The participants agreed that subsequent events, especially in a form of a workshop, would be very beneficial to continue such analyses. Results of the study sessions are presented in the last chapter of this book.

Participants representing Armenia, Belgium, Canada, Czech Republic, France, Germany, Israel, Italy, The Netherlands, Portugal, Russia, Spain, Tunisia, the United Kingdom and the USA contributed to this ASI. A distinguished group of experts was assembled, and the technical program was organized with the generous and very capable assistance of the Organizing Committee composed of Dr. Éloi Bossé (Canada), Dr. Khalel Mellouli (Tunisia), Dr. Elisa Shahbazian (Canada), Dr. Galina Rogova (USA), Dr. Jesus Garcia (Spain), Dr. Edward Pogossian (Armenia), Dr. Bassel Solaiman (France), Dr. Adel Guitouni (Canada) as well as a support team from the host country (Spain). The organizers offer their deep appreciation to the ASI participants, who devoted so much of their time and talents to make the ASI successful.

We are grateful to the NATO Security Through Science Programme, which provided important financial support. The organisers are especially grateful to Prof. Fernando Carvalho Rodrigues, head of the Human and Societal Dynamics Panel (HSD), whose suggestions for providing a systemic approach to the discussions and the technical program contributed to the success of the ASI.

This ASI was originally planned to take place in Tunisia at Magic Life Manar Hotel Hammamet, on 17-29 April, 2011 but due to the political unrest in Tunisia, we had to find an alternate location. Special thanks to Dr Jesús García of University Carlos III of Madrid and Dr Juan Manuel Corchado Rodríguez, the Dean of School of Science of University of Salamanca who offered that alternative in Salamanca.

The Organizing committee would like to specifically thank:

• The School of Science of University of Salamanca that contributed in every way to ensure a successful event by obtaining the ASI recognition and participation by Spanish Ministry of Defence and providing very competent local support staff, excellent conference facilities, affordable housing and meals, as well as an interesting social program.

• The Department of the Navy of the U.S. Office of Naval Research Global (ONRG) for their financial support, helping to ensure participation of highly qualified experts in this ASI and offset the additional organizational effort required to move the ASI into a new hosting country.

In addition, the following organizations supported this ASI: the U.S. Department of Homeland Security, the Science & Technology Directorate; the Department of Mathematics and Statistics of Université de Montreal Canada; Encompass Consulting, USA; and OODA Technologies, Inc., Canada.

A very special acknowledgement goes to Ani Shahbazian who undertook the very challenging task of performing the English Language editing of all the lecturers' manuscripts and producing a camera-ready document for the publisher.

And, finally, all of our thanks go to the people of the University of Salamanca, who certainly displayed, in every way, their warmth and hospitality.

Éloi Bossé

Québec City, Canada

Elisa Shahbazian

Montreal, Canada

Galina Rogova

Honeoye Falls, USA

December 2012

Maritime piracy is a widespread international concern. Over the years, it has been on the rise, with the number of attacks increasing substantially. Vessels are extremely susceptible to hostile boarding. This is favoured by inherent vulnerability due to slowness (tonnage, deep sea vessels, massive size and weight), as well as lack of reporting and law enforcement: ship owners are reluctant to directly address the issue of maritime piracy for commercial reasons. Furthermore, technological improvements have resulted in smaller crews on (larger) vessels. The main objective of this paper is to set the scene for discussions on prediction, recognition and deterrence of maritime piracy through the use of collaborative human-centric information support systems. Collaborative human-centric information support systems can significantly improve the ability of every nation to predict and prevent an incident or to rapidly recognize its nature and extent for an effective collective response. Inherent to the concept of collaborative information support systems are: human system integration concepts, cognitive systems engineering methodologies, collaborative environment technologies, knowledge exploitation and data/information mining technologies instantiated into human-centred (where the human is an integrated part of the system) decision support (collaborative information systems) concepts/approaches. Operating in the crisis management and anti-piracy program environment, decision makers at all levels (e.g., incident commanders) and their staff can use collaborative humancentric information support capabilities.

Africa has raised international awareness for the general deterioration of maritime security and emphasised the trans-boundary nature of maritime threat, especially with regards to the legal challenges of asserting and exercising jurisdiction. The first section of this paper will show that, in the case of West and Central Africa there is a correlation between the unprecedented and rapid rise of maritime threat and the growth in resource exploitation, military expenditure and the geographical and historical context. The discussion will overview the typology and underline the severity of maritime attack in the area by way of the resultant new risk index allocation by the Lloyds Joint War Committee's Listed Areas. The second part of the paper will examine the 2003, IMO and MOWCA Integrated Coastguard Network concept and will detail the need for such an approach, the current situation and the solutions necessary to speed its progress. The article will also consider the importance of stronger and more robust structures for bringing into play multi-national and inter-agency partnerships that can be drawn on to support African Nations in suppressing asymmetric threats, and will conclude with a discussion relating to the identification and assessment of technological capability gaps and long-term requirements in West and Central Africa for increased situational awareness in territorial waters.

The use of Privately Contracted Armed Security Personnel (PCASP) on ships transiting High Risk Areas (HRA) is a topic bounded in controversy. During 2010 and 2011 the issue was debated in depth by maritime stakeholders due to the dramatic increase of ships attacked or laid hostage by pirates in the Gulf of Aden. In response, the International Maritime Organisation during 2011 provided guidance in the form of circulars which outlined the key points that a ship-owner should consider before employing PCASP. The first part of this article explores the background that led to the concept of PCASP first being debated at the International level. The following sections continue by examining and detailing the complexities of the different legal systems that may impact on a ship owner should they choose to employ PCASP. Finally the paper concludes with the pressing International concerns and possible future consequence of PCASP on ships transiting HRAs.

The concept of Maritime Security Operations was finally agreed upon in NATO. The framework now provides a basis to be able to legitimately perform security operations by using current and future maritime capabilities. Modern maritime operations require a comprehensive situational awareness picture in order to perform tasks in a more efficient and stinting manner. Regrettably, the strongest limitation is due to the limited available number of necessary assets (either maritime and/or air) to collect those data that must be managed by Humans (operators) before being distributed. However, because of the quantity of data to be exploited, decision making value can be diminished by an overlying flow of information, which might create wrong understanding (i.e., managing the whole instead of thinking and drawing on their own experience and then applying discernment to achieve “an” understanding on what is happening in the physical domain). Besides this problem, Coalition staff are more and more populated by heterogeneous operators with different profiles, which might inject “characteristic” errors, eventually spoiling the value of the local situational assessment. In the C4I World, we are observing a conceptual social revolution due to an unstoppable increase in the use of network technology to facilitate cooperation and information sharing within and amongst different social organizations, including civilian and non-military agencies of different countries. In these complex multi-domain settings, the label Network Enabled Capability (NEC) is used to describe the “assumed” increased value of a well-networked organization in order to provide decision superiority over opponents. However, in a complex networking environment, information sharing must be absolutely trustable, clear and able to provide correct meaningful information to users. This challenge is affected by political/legal constraints, technical issues related to system interoperability and by Human System Integration (HSI) errors that might cause wrong assumptions and diminish final quality. How much human perception may affect the cognitive process and, therefore, decision making, is a field we still must fully explore. Apparently, the operators' “geographical” attitude, operational service background and education might offer too subjective an evaluation during sensitive operations. Human understanding might be considered conditional and require a more holistic approach and new models to reduce judgment subjectivity.

Since 2008, the sea-jacking of a larger number of merchant ships has put greater focus and pressure on the international community. NATO's Planning Board for Ocean Shipping (PBOS) Transport Group (TG) undertook the task of updating an existing report by collecting input from a number of international agencies involved in maritime security and producing the report summarised in this chapter.

Largely separate efforts characterize the current state of anti-piracy intelligence operations. Lessons from other forms of irregular conflict – counterinsurgency (COIN) in particular – can inform the gathering, processing, and distribution of information vital to ultimately persevering against the pirate threat. The author offers seven general guidelines to assist in this regard: Maintain a Systems Approach; Adapt Organizations; Train Everyone to Serve as a Sensor; Equip Everyone to Serve as a Sensor; Adapt Rather than Rely on Cold War Intelligence Approaches; Expand the Concept of “Coalition”; Influence Select Segments of the Population. Adaptation will be essential in moulding this guidance to the demands of an anti-piracy undertaking. Orchestrating the intelligence capabilities each participant can bring to bear will be of overarching importance if those capabilities are to effectively serve as implements in achieving ultimate success.

Traditional deductive recognition-based methods – whether model-based or anomaly-based – are not appropriate to the counter-piracy application. Both threats and normal activity are often extremely difficult to model. Furthermore, an intelligent adversary can be expected to maximize ambiguity and exploit the defence response cycle. Rather than a deductive recognition-based approach, we recommend a diagnostic (abductive) one: (a) focus on potential victims rather than potential pirates, (b) detect and diagnose potential encounters and estimate time-to-go, and (c) manage assets for situation resolution and interdiction, based on assessed encounter impact, likelihood, available and required time to respond, and confidence in these factors. An interactive situation management concept is presented, in which the operator is able to visualize the predicted evolution of the maritime situation, together with the predicted evolution of the system's state of knowledge and of response opportunities.

Surveillance in Counter-Terrorism and Counter-Insurgency type environments requires exploitation of all possible types of available information. U.S. experience in Iraq and Afghanistan has shown the advantages of incorporating surveillance from both trained and inexperienced human observers, and the importance of accounting for certain types of Contextual Information to include cultural factors and non-physical data such as data regarding a political situation (such data now labelled as “soft” or unstructured), along with integration of the data from traditional electronic sensors (labelled as “hard”). Because much of these soft data cannot be well-qualified or calibrated, the evidential basis for decision-making is one of only partially-known uncertainty, creating a requirement to consider new decision-making paradigms for decision-making under extreme uncertainty and unknown/partially-known uncertainty, and for learning strategies based on optimized query-response techniques. This paper will address the design issues and approaches for prototyping new Information Fusion processes that are able to combine all of the data types mentioned above, linked to a decision-support framework employing these new decision-making paradigms.

Though piracy accounts for only a small fraction of the general losses of the maritime industry, it poses a serious threat to maritime security because of the connections between organized piracy, and wider criminal networks and corruption on land. Fighting piracy requires monitoring waterways, harbors and criminal networks on land to increase decision makers' ability to predict piracy attacks, and to manage operations to prevent or contain them. Piracy surveillance involves representing and processing a huge amount of heterogeneous information, often uncertain, unreliable and irrelevant, within a specific context to detect and recognize suspicious activities, and alert decision makers on vessel behaviors of interest with minimal false alarm. The paper discusses the role of information fusion, and context representation and utilization in building an piracy surveillance picture.

This article presents two empirical studies investigating the extent to which intelligence analysts are able to integrate new information about the reliability of intelligence sources into their judgment. The first study used a limited number of pieces of intelligence, and binomial reliability values. The second study included a larger number of sources, and reliability values distributed on a 5-point scale. A comparative analysis of the results suggests that analysts are less likely to significantly modify their judgment if they are faced with a large amount of information to analyse, possibly showing the vulnerability of analysts' to heuristic biases in this case.

Development of advanced technology (e.g. High Level Information Fusion (HLIF), Data Mining, Artificial Intelligence (AI), human factors, etc.) enabled decision support for prediction and recognition of piracy activity is an extremely challenging problem. It requires the consideration of multiple interrelated factors and constraints for numerous aspects of the system, including legal, jurisdictional, information sharing and exchange, information availability and quality, user roles and hierarchy, application of hardware and software technologies, etc. which do not lend themselves to simple analyses. There are numerous stakeholders, and no one has either an understanding of or access to, the entire knowledge to be able to resolve any of these challenges by themselves. There are too many unknowns in a traditional top-down design methodology to be feasible to use. Because scenarios are task-based and descriptive, it was judged that the Scenario Based Design (SBD) approach needs to be explored for advanced technology-enabled systems, in which human is a part of the system. This chapter presents an initial discussion on how SBD methodology could be applied to incrementally develop advanced decision support capabilities for prediction and recognition of piracy activity in collaboration with the stakeholders.

Agent-based modelling has gained popularity as a useful technique for obtaining insights into the behaviour of complex adaptive systems in various fields including economics, sociology and ecology. With its complex interactions between routes, schedules and engagement strategies, transit through piracy-affected waters is a problem very well suited for the application of this powerful modelling approach. Within the AgentC project, we have been developing a data-driven, agent-based model of global maritime traffic explicitly accounting for the effects of maritime piracy. The model employs finite state machines to represent the behaviour of merchant, pirate and naval vessels. It accurately replicates global shipping patterns and approximates real-world distribution of pirate attacks. By conducting and analysing results from thousands of simulation runs, the developed model and related tools allow gaining qualitative and quantitative insights into complex relationships governing piracy risks and costs. Further on, we utilize the simulation to conduct what-if analysis of possible piracy counter-measures and evaluate their effectiveness. Because of their strong application potential, the model and the tools are currently considered by the U.N. International Maritime Organization for potential use in assessing future operational counter-piracy measures, including new transit corridors and extended group transit schemes.

Complex situations, either military or civilian, require higher-level information fusion to provide decision-makers with proper situation assessment/awareness, and impact/threat assessment. Basic models such as the OODA loop and Endsley's model are highlighted and compared. The role of taxonomies/ontologies, and the need for some standardization (STANAG or MIL-STD) is stressed. Critical issues such as reliability, credibility, and information relevance is also described, since they strongly affect the quality of the results obtained through information fusion. Network-enabled operations, which can be achieved through information exchange via data links, require that fusion nodes be distributed, one per platform. Prosecution of pirates is most easily achieved by ships that are dispatched using the Common Operating Picture shared by the patrol aircraft, UAVs, satellites, ships and ground stations.

In Part 1 of this lecture, a description of fusion levels was provided in general terms, without specific reference to any application. The focus was mainly on general principles, recent developments, and challenges. In Part 2, a specific application of information fusion to missions requiring a Maritime Patrol Aircraft (MPA) is presented. The prediction and recognition of attempted piracy require an extensive use of long-range maritime patrol aircraft, such as the Canadian Aurora, whose capabilities are described at length (sensors, autonomy, etc.). Network-enabled operations, which can be achieved through information exchange via datalinks, require that fusion nodes be distributed, one per platform, the Aurora, or CP-140 being one of these platforms. Prosecution of pirates is most easily achieved by ships that are dispatched using the Common Operating Picture shared by the MPA, UAVs, satellites, ships and ground stations.

The INFORM Lab testbed allows experimenting with high-level distributed information fusion and dynamic resource management, given multiple constraints on the resources and their communications networks. This presentation describes the architecture, the concepts of goals and situation evidence, algorithms for distributed information fusion and dynamic resource management. The testbed provides general services which include a multi-layer plug-and-play architecture, and a general multi-agent framework based on John Boyd's OODA loop.

In Part 1 of these lectures, the INFORM Lab testbed was described with respect to its general architecture, OODA nodes, multi-layer plug-and-play architecture, and general multi-agent framework based on John Boyd's OODA loop. Part 2 demonstrates some promising results from a non-cooperative scenario involving complex behaviour between multiple ships trying to hide their motives, as would be the case in a piracy scenario. The flexibility of the testbed is also demonstrated.

Multiple public web sites can be used to obtain ship-related information that is relevant to Maritime Domain Awareness (MDA). However, the quality or timeliness of this information can be suspect. In this paper, a software application, called the consistency application, is presented for the comparison of ship-related information from multiple data sources. The consistency application allows a user to compare the information from these multiple data sources and generate a comparison score for the specific ship information supplied by the data source, and also for the data source as a unit. This allows the user to assess the consistency of the information provided from the data source, as compared to other sources. The consistency application presently links four MDA-related information sources.

In the area of surveillance and reconnaissance, it is necessary to have an adequate situation awareness to be able to react to a critical situation in time. A critical situation develops over time and space, and is indicated by specific characteristics. These characteristics have to be known, and they need to be perceived and identified before danger occurs. Additionally, maritime surveillance areas are generally large, and threats in this domain are often asymmetric and cannot easily be classified. Therefore, widely distributed information sources, automatic situation analysis, and the possibility to share information of interest are necessary. An approach that makes it possible to percept information about a specific situation is to gather data from different sensor platforms (above and under water) and sensor types (e.g., optical and infrared imagery, video, radar, sonar). To serve user needs, relevant information has to be extracted and integrated into an overall picture. Therefore, methods of data fusion and classification are necessary. As threats are not easily identified by pure object classification (e.g., pirates and fishermen are making use of simple boats), situation analysis methods take specific motion patterns as indicators for abnormal behaviour into account. To disseminate the results and to share them with a broader community, methods and means of data dissemination have to be defined. The paper describes an architecture that implements this approach. The architecture has been proved in EU and NATO projects, and combines civil and military operations.

Smart environments based on ubiquitous computing open new possibilities for various aspects of human activity. This paper proposes an approach to emergency situation response that benefits from ubiquitous computing. The approach is based on utilizing profiles to facilitate the coordination of activities of emergency response operation members. The idea behind the approach is to self-organize resources of smart environments according to the state of situation caused by an emergency event. The resources self-organize a collaborative network that comprises physical devices, software services, organizations and persons. The purpose of the resources is to undertake joint actions for emergency response. The emergency response system intended for operating in smart environments has a service-oriented architecture. Some Web-services making up the architecture are intended to model emergency situations, while others model resource functionalities or have supporting functions. A case study illustrates the main ideas presented in the paper.

Ontology-based representations are gaining momentum among other alternatives for implementing the knowledge model of high-level fusion applications. In this paper, we provide an introduction to the theoretical foundations of ontology-based knowledge representation and reasoning, with a particular focus on the issues that appear in maritime security, where heterogeneous regulations, information sources, users, and systems are involved. We also present some current approaches and existing technologies for high-level fusion, based on ontological representations. Unfortunately, current tools for the practical implementation of ontology-based systems are not fully standardized or even prepared to work together in medium-scale systems. Accordingly, we discuss different alternatives to face problems such as spatial and temporal knowledge representation or uncertainty management. To illustrate the conclusions drawn from this research, an ontology-based semantic tracking system is briefly presented. Results and latent capabilities of this framework are shown at the end of the paper, where we also envision future opportunities for this kind of application.

Building an effective situational picture requires the fusion of potentially heterogeneous information coming from multiple sources. In this work, we propose the architecture of a Resource Management Module (RMM) meant to refine and optimize the performance of a multi-sensor fusion engine. Specifically, the RMM is designed to improve performance of the tracking and classification tasks performed by the engine. Here, attention will be focused on assisting the tracking process, while taking into account the current state of things in the observed environment and the available contextual information.

Maritime security depends on the ability and capability to build “a comprehensive awareness of maritime activity, which encompasses territorial and international waters, and to act accordingly” [1]. This level of awareness can be reached in several steps, evolving from single-sensor into multi-sensor multi-cue systems, exploiting heterogeneous information extracted by different (hard and soft) sources, and integrating contextual information with the purpose of generating a faithful and timely comprehensive maritime picture. Heterogeneity and context play a crucial role at different levels of fusion, allowing the combination of complementary and multifaceted information, which should be shared among national or international actors. In this paper, we discuss why these global trends must be adopted and expanded to build analytical models which can effectively face asymmetric threats.

The Aracnocóptero is an aerial platform designed to capture photographs and images in multiple formats, and to carry sensors and scientific-technical measuring equipment. It is a collapsible, lightweight, multi-rotor, vertical take-off UAV (Unmanned Aerial Vehicle) aircraft made of maximum resistance aerospace materials. It includes a communications centre and a station base, which are transportable, lightweight and compact. The Aracnocóptero platform control and guidance software is composed of an agent-based system specialized in gathering and processing different types of information. The multi-agent system (MAS) that controls the Aracnocóptero uses different types of interfaces for its various applications and for the reconstruction of telemetric values obtained from the UAV. Due to its adaptability, the Aracnocóptero platform can be extended to a number of uses.

In this contribution, a Multi-Agent System architecture is proposed to deal with the management of spatially distributed heterogeneous nets of sensors, with specific focus on the problem of Pan-Tilt-Zoom or active cameras. The design of surveillance multi-sensor systems design implies undertaking to solve two related problems: data fusion and coordinated sensor-task management. Generally, proposed architectures for the coordinated operation of multiple sensors are based on the centralization of management decisions at the fusion centre. However, the existence of “intelligent” sensors capable of making decisions brings the possibility of conceiving alternative decentralized architectures. This problem could be approached by means of a Multi-Agent System (MAS). Specifically, this paper proposes a MAS architecture for automatically controlling sensors in video surveillance environments. In this case, the MAS fits perfectly in inherently distributed scenarios due to the area dimensions to be monitored. We deal specifically with Pan-Tilt-Zoom cameras to perform tasks depending on operator preferences, such as automated and distributed tracking for one or many targets, coordinated sweeps of areas, camera orientation to minimize overlapping areas, and so on. Both the architecture and an application example are described.