As human-machine interaction contexts become increasingly prevalent, it becomes crucial to identify and formalize the characteristics and parameters influencing trust. This enables the creation of agents capable of inducing higher trust and recognizing whether a partner is trustworthy or not. In this article, we focus on one of the key components affecting trust: competence, the ability to successfully complete a selected task. We evaluate this concept within a Multi-Agent Reinforcement Learning (MARL) framework and introduce the Competence Trust Factor (CTF). Our results demonstrate that incorporating the CTF significantly improves task performance and agent collaboration in various scenarios.

We provide a customizable environment based on Deep Reinforcement Learning (DRL) strategies for handling cooperative multi-UAV (Unmanned Aerial Vehicles) scenarios when delays are involved in the decision-making process for tasks such as spotting, tracking, coverage and many others. Users can choose among various combinations of tasks and parameters and customize the scenarios by implementing new desired functionalities. This environment provides the opportunity to compare different approaches, taking into account either implicitly or explicitly the delays applied to actions and observations. The awareness of the delay, along with the possible usage of real-world-based external files, increases the reality level of the environment by possibly easing the knowledge transferability process of the learned policy from the simulated environment to the real one. Finally, we show that use cases could generate new benchmarking tools for collaborative multi-UAV scenarios where DRL solutions must consider delays.

One major limitation to the applicability of Reinforcement Learning (RL) to many practical domains is the large number of samples required to learn an optimal policy. To address this problem and improve learning efficiency, we consider a linear hierarchy of abstraction layers of the Markov Decision Process (MDP) underlying the target domain. Each layer is an MDP representing a coarser model of the one immediately below in the hierarchy. In this work, we propose a novel form of Reward Shaping where the solution obtained at the abstract level is used to offer rewards to the more concrete MDP, in such a way that the abstract solution guides the learning in the more complex domain. In contrast with other works in Hierarchical RL, our technique has few requirements in the design of the abstract models and it is also tolerant to modeling errors, thus making the proposed approach practical. We formally analyze the relationship between the abstract models and the exploration heuristic induced in the lower-level domain. Moreover, we prove that the method guarantees optimal convergence and we demonstrate its effectiveness experimentally.

No abstract available.

As social robots become more prominent in our lives, their interaction with humans takes an increasing role, and new collaborative scenarios emerge. This development brings the need to realize robust test methods enabling the design and evaluation of Human-Robot Interaction (HRI) teaming tasks to prove functionality and promote adoption. In this article, we present a general-purpose and repeatable methodology for conducting studies in collaborative HRI in the range of robotic competitions. The methodology includes a step-by-step approach to design HRI teaming tasks tailored to be enacted in a robotic competition and to evaluate the performance of social robots to execute the designed tasks, exploring the relationship between robots’ performance and user perceptions based on the feedback of the users participating to such tasks. We assess the feasibility of the methodology to design and evaluate an HRI teaming task in the context of “Smart CIties RObotics Challenges” (SciRoc) competition, which targets at investigating the impact of social of robots in smart cities.

In this work we have investigated the concept of “restraining bolt”, inspired by Science Fiction. We have two distinct sets of features extracted from the world, one by the agent and one by the authority imposing some restraining specifications on the behaviour of the agent (the “restraining bolt”). The two sets of features and, hence the model of the world attainable from them, are apparently unrelated since of interest to independent parties. However they both account for (aspects of) the same world. We have considered the case in which the agent is a reinforcement learning agent on a set of low-level (subsymbolic) features, while the restraining bolt is specified logically using linear time logic on finite traces f/f over a set of high-level symbolic features. We show formally, and illustrate with examples, that, under general circumstances, the agent can learn while shaping its goals to suitably conform (as much as possible) to the restraining bolt specifications.1

In this paper, we present the outcomes of the first user study designed and evaluated in the context of the Smart City Robotics Challenge (SciRoc Challenge). The study presented in this paper has the main novelty of having been devised and implemented in a realistic environment: a robot competition where robot tasks were developed by participant teams, robots were fully autonomous, and user questionnaires were part of the competition score. Specifically, our study was performed over a scenario configured to instruct a robot to take an elevator of a shopping mall asking for customers support. Leveraging the dedicated questionnaire designed for the tested scenario, we validated the experimental hypothesis if user perception of robots' behaviour may be influenced by the user's gender. In the end, we discuss the results of our study.

In this work, we perform a wide variety of experiments with different deep learning architectures on datasets of limited size. According to our study, we show that model complexity is a critical factor when only a few samples per class are available. Differently from the literature, we show that in some configurations, the state of the art can be improved using low complexity models. For instance, in problems with scarce training samples and without data augmentation, low-complexity convolutional neural networks perform comparably well or better than state-of-the-art architectures. Moreover, we show that even standard data augmentation can boost recognition performance by large margins. This result suggests the development of more complex data generation/augmentation pipelines for cases when data is limited. Finally, we show that dropout, a widely used regularization technique, maintains its role as a good regularizer even when data is scarce. Our findings are empirically validated on the sub-sampled versions of popular CIFAR-10, Fashion-MNIST and, SVHN benchmarks.

In Markov Decision Processes (MDPs), rewards are assigned according to a function of the last state and action. This is often limiting, when the considered domain is not naturally Markovian, but becomes so after careful engineering of extended state space. The extended states record information from the past that is sufficient to assign rewards by looking just at the last state and action. Non-Markovian Reward Decision Processes (NRMDPs) extend MDPs by allowing for non-Markovian rewards, which depend on the history of states and actions. Non-Markovian rewards can be specified in temporal logics on finite traces such as LTLf/LDLf, with the great advantage of a higher abstraction and succinctness; they can then be automatically compiled into an MDP with an extended state space. We contribute to the techniques to handle temporal rewards and to the solutions to engineer them. We first present an approach to compiling temporal rewards which merges the formula automata into a single transducer, sometimes saving up to an exponential number of states. We then define monitoring rewards, which add a further level of abstraction to temporal rewards by adopting the four-valued conditions of runtime monitoring; we argue that our compilation technique allows for an efficient handling of monitoring rewards. Finally, we discuss application to reinforcement learning.

While robots are more and more deployed among people in public spaces, the impact of cyber-security attacks is significantly increasing. Most of consumer and professional robotic systems are affected by multiple vulnerabilities and the research in this field is just started. This paper addresses the problem of automatic detection of anomalous behaviors possibly coming from cyber-security attacks. The proposed solution is based on extracting system logs from a set of internal variables of a robotic system, on transforming such data into images, and on training different Autoencoder architectures to classify robot behaviors to detect anomalies. Experimental results in two different scenarios (autonomous boats and social robots) show effectiveness and general applicability of the proposed method.

In this paper, we present an approach to develop a new type of questionnaire for evaluating customers' perceptions in the upcoming Smart CIty RObotic Challenge (SciRoc). The approach consists of two steps. First, it relies on interviewing experts on Human-Robot Interaction (HRI) to understand which robot's behaviours can potentially affect the users' perceptions during a HRI task. Then, it leverages a user survey to filter out those robot's behaviours that are not significantly relevant from the end user perspective. We concretely enacted our approach over a specific scenario developed in the context of SciRoc, which instructs a robot to take an elevator of a shopping mall asking support to the customers of the mall. The results of the survey have allowed us to derive a final list of 17 behaviours to be captured in the questionnaire, which has been finally developed relying on a 5-point Likert-scale.

Understanding activities of people in a monitored environment is a topic of active research, motivated by applications requiring context-awareness. Inferring future agent motion is useful not only for improving tracking accuracy, but also for planning in an interactive motion task. Despite rapid advances in the area of activity forecasting, many state-of-the-art methods are still cumbersome for use in realistic robots. This is due to the requirement of having good semantic scene and map labelling, as well as assumptions made regarding possible goals and types of motion. Many emerging applications require robots with modest sensory and computational ability to robustly perform such activity forecasting in high density and dynamic environments. We address this by combining a novel multi-camera tracking method, efficient multi-resolution representations of state and a standard Inverse Reinforcement Learning (IRL) technique, to demonstrate performance that is better than the state-of-the-art in the literature. In this framework, the IRL method uses agent trajectories from a distributed tracker and estimates a reward function within a Markov Decision Process (MDP) model. This reward function can then be used to estimate the agent's motion in future novel task instances. We present empirical experiments using data gathered in our own lab and external corpora (VIRAT), based on which we find that our algorithm is not only efficiently implementable on a resource constrained platform but is also competitive in terms of accuracy with state-of-the-art alternatives (e.g., up to 20% better than the results reported in [1]).

Detection, classification, and tracking of people and vehicles are fundamental processes in intelligent surveillance systems. The use of publicly available data set is the appropriate way to compare the relative merits of existing methods and to develop and assess new robust solutions. In this paper, we focus on the maritime domain and we describe the generation of boat classification data sets, containing images of boats automatically extracted by the ARGOS system, operating 24/7 in Venice, Italy. The data sets are unique in their nature, since they come from an incomparable environment like Venice, but they present very interesting challenges to vehicle classification, due to changes in the environmental conditions, boat wakes, waves, reflections, etc. We thus believe that robust techniques, validated through the ARGOS Boat Classification data sets, will improve the development and deployment of solutions in similar applications related to vehicle detection and classification.

Background modeling in fast changing scenarios is a challenging task due to unexpected events like sudden illumination changes, reflections, and shadows, which can strongly affect the accuracy of the foreground detection. In this paper, we describe a real-time and effective background modeling approach, called FAFEX, that can deal with global and rapid changes in the scene background. The method is designed to identify variations in the background geometry of the monitored scene and it has been quantitatively tested on a publicly available data set, containing a varied set of highly dynamic environments. The experimental evaluation demonstrates how our method is able to effectively deals with challenging sequences in real-time.

As robots are expected to become more and more available in everyday environments, interaction with humans is assuming a central role. Robots working in populated environments are thus expected to demonstrate socially acceptable behaviors and to follow social norms. However, most of the recent works in this field do not address the problem of explicit representation of the social norms and their integration in the reasoning and the execution components of a cognitive robot. In this paper, we address the design of robotic systems that support some social behavior by implementing social norms. We present a framework for planning and execution of social plans, in which social norms are described in a domain and language independent form. A full implementation of the proposed framework is described and tested in a realistic scenario with non-expert and non-recruited users.

Most of existing benchmarking tools for service robots are basically qualitative, in which a robot’s performance on a task is evaluated based on completion/incompletion of actions contained in the task. In the effort reported in this paper, we tried to implement a synthetical benchmarking system on domestic mobile platforms. Synthetical benchmarking consists of both qualitative and quantitative aspects, such as task completion, accuracy of task completions and efficiency of task completions, about performance of a robot. The system includes a set of algorithms for collecting, recording and analyzing measurement data from a MoCap system. It was used as the evaluator in a competition called the BSR challenge, in which 10 teams participated, at RoboCup 2015. The paper presents our motivations behind synthetical benchmarking, the design considerations on the synthetical benchmarking system, the realization of the competition as a comparative study on performance evaluation of domestic mobile platforms, and an analysis of the teams’ performance. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Scientific competitions are becoming more common in many research areas of artificial intelligence and robotics, since they provide a shared testbed for comparing different solutions and enable the exchange of research results. Moreover, they are interesting for general audiences and industries. Currently, many major research areas in artificial intelligence and robotics are organizing multiple-year competitions that are typically associated with scientific conferences. One important aspect of such competitions is that they are organized for many years. This introduces a temporal evolution that is interesting to analyze. However, the problem of evaluating a competition over many years remains unaddressed. We believe that this issue is critical to properly fuel changes over the years and measure the results of these decisions. Therefore, this article focuses on the analysis and the results of evolving competitions. In this article, we present the [email protected] competition, which is the largest worldwide competition for domestic service robots, and evaluate its progress over the past seven years. We show how the definition of a proper scoring system allows for desired functionalities to be related to tasks and how the resulting analysis fuels subsequent changes to achieve general and robust solutions implemented by the teams. Our results show not only the steadily increasing complexity of the tasks that [email protected] robots can solve but also the increased performance for all of the functionalities addressed in the competition. We believe that the methodology used in [email protected] for evaluating competition advances and for stimulating changes can be applied and extended to other robotic competitions as well as to multi-year research projects involving Artificial Intelligence and Robotics.

Object classification from images is an important task for machine vision and it is a crucial ingredient for many computer vision applications, ranging from security and surveillance to marketing. Image based object classification techniques properly integrate image processing and machine learning (i.e., classification) procedures. In this paper we present a system for automatic simultaneous optimization of algorithms and parameters for object classification from images. More specifically, the proposed system is able to process a dataset of labelled images and to return a best configuration of image processing and classification algorithms and of their parameters with respect to the accuracy of classification. Experiments with real public datasets are used to demonstrate the effectiveness of the developed system.

The Pattern Recognition (PR) and Artificial Intelligence (AI) scientific communities have shared knowledge and effort in order to obtain more effective solutions for many different research areas. However, although the techniques and approaches are somewhat similar, the two communities often tackle problems from rather different perspectives. In the first paper ‘Social Interactions by Visual Focus of Attention in a Three-Dimensional Environment', by Bazzani, Tosato, Cristani, Farenzena, Paggetti, Menegaz and Murino, a novel approach to social interaction discovery is presented; instead of using global or local appearance features, the authors exploit the Subjective View Frustum, which approximates the visual field of a person in a three-dimensional representation of the scene. The main contribution of the second paper 'Human action recognition using an ensemble of body-part detectors', by Chakraborty, Bagdanov, Gonzalez and Roca, is to transform the problem of action recognition into that of recognising the distinctive motion of specific body parts, for instance, the legs for walking, the hands for boxing, etc. The intuition behind the approach is that several human actions can be described more compactly and effectively by considering only the relevant motions of the body parts actually performing the actions. We hope you enjoy the special section. Luca Iocchi is Associate Professor at Sapienza University of Rome, Italy. His main research interests are in the areas of cognitive robotics, action planning, multi-robot coordination, robot perception, robot learning, sensor data fusion. He is being involved in several projects aiming at developing intelligent robotic systems and intelligent surveillance systems. He is active in many conferences and journals related to artificial intelligence and robotics, as well as in the organisation of scientific competitions, such as RoboCup@Home. Andrea Prati is Associate Professor at the University IUAV of Venice. He collaborated in several research projects at regional, national and international level. His research interests belong to different themes, from embedded devices for sensor networks in computer vision applications, to robotic vision, to multimedia, to performance analysis for multimedia computers. However, his main research activity is on video-surveillance topics: object tracking in distributed, multi-camera environments; analysis and removal of the shadows; behaviour analysis through trajectory classification. Andrea Prati is author of more than 130 papers in international journals and conference proceedings; he has been invited speaker and reviewer for many international journals. He is also a member of the Editorial Board of Journal of Optical Engineering (SPIE) and Journal on Ambient Intelligence and Smart Environments (IOS Press). He has also been the Program Chair of ICIAP 2007. He has been the PC of ACM/IEEE Intl Conf on Distributed Smart Cameras (ICDSC) in 2011 and 2012, and will be for 2013 edition in Palm Springs, CA (USA). He is also organising as General Chair the 2014 ICDSC edition in Venice. He is a senior member of IEEE, and a member of ACM and GIRPR. Roberto Vezzani is an Assistant Professor at University of Modena and Reggio Emilia and he works in the Engineering Department 'Enzo Ferrari'. His research interests mainly belong to video surveillance systems, with particular focus on behaviour analysis, people tracking and re-identification. He is the author of the ViSOR web repository, an online platform for sharing research videos and annotations developed within the European project VidiVideo. He was the technical coordinator of the European Project THIS, for transport hub intelligent video surveillance. He is author of more than 50 papers on international journals and conferences.

Mobility in large touristic cities (such as Rome and Venice), where needs of citizen and tourists are different(and sometimes even conflicting), is a very relevant problem and infomobility is thus increasingly important. Since active technologies, requiring the passengers to wear some devices(e.g., RFID devices) are not commonly available and cannot be enforced on citizens and tourists, a complete passive sensor system is needed. In this paper we describe development and experimentation of techniques for human activity recognition for infomobility applications based on 3D data extracted from stereo and Kinect cameras. More specifically, we considered the problem of automatic estimation of the number of people present in a bus stop area in a crowded city, like Venice and experimented an approach integrating 3D data analysis, feature extraction and machine learning techniques. Results assessing the feasibility and performance of the proposed approaches are also presented in this paper.

Multi-robot patrolling is a fundamental functionality for multi-robot surveillance and environmental monitoring and has been longly investigated. However, benchmarks for multi-robot patrolling, the realization of realistic simulators and testing on real robotic platforms are still very limited. In this paper we discuss the application of state-of-the-art patrolling strategies in realistic applications, showing that it is important to take into account: perception needs of the robots, uncertainty on action execution, characteristics of the environment, closed-loop coordinated behaviors, and realistic simulation environments.

The execution of tasks for a robotic agent embedded in a dynamic environment brings about several challenges, due to unpredictable (or unobservable) events, and to inaccurate perception. Moreover, the agent can perform multiple tasks and each task can be achieved by applying different plans, therefore the decision about which strategy is the most convenient, given the current situation of the world, is important for assessing an intelligent overall behavior of the agent. This paper tackles the problem of on-line execution monitoring in a novel way with respect to previous work, since: (1) it considers uncertainty in the duration of actions with a probabilistic model of action duration; (2) it evaluates the cost of each possible plan at run-time in terms of probability of successful termination within a desired expected time. The approach has been evaluated both in a robotic soccer and a surveillance scenario.

We propose an adaptive tracking system for assisted living that integrates user information about emergency events. Information fusion between user data and visual data is performed in order to estimate and assess the situation at hand. The system is able to dynamically switch between different segmentation and tracking algorithms improving its performance, as shown by the proposed examples.

Visual surveillance in dynamic scenes is currently one of the most active research topics in computer vision, many existing applications are available. However, difficulties in realizing effective video surveillance systems that are robust to the many different conditions that arise in real environments, make the actual deployment of such systems very challenging. In this article, we present a real, unique and pioneer video surveillance system for boat traffic monitoring, ARGOS. The system runs continuously 24 hours a day, 7 days a week, day and night in the city of Venice (Italy) since 2007 and it is able to build a reliable background model of the water channel and to track the boats navigating the channel with good accuracy in real-time. A significant experimental evaluation, reported in this article, has been performed in order to assess the real performance of the system.

We focus on the aspect of sensing in reasoning about actions under qualitative and probabilistic uncertainty. We first define the action language E for reasoning about actions with sensing, which has a semantics based on the autoepistemic description logic ALCK NF , and which is given a formal semantics via a system of deterministic transitions between epistemic states. As an important feature, the main computational tasks in E can be done in linear and quadratic time. We then introduce the action language E + for reasoning about actions with sensing under qualitative and probabilistic uncertainty, which is an extension of E by actions with nondeterministic and probabilistic effects, and which is given a formal semantics in a system of deterministic, nondeterministic, and probabilistic transitions between epistemic states. We also define the notion of a belief graph, which represents the belief state of an agent after a sequence of deterministic, nondeterministic, and probabilistic actions, and which compactly represents a set of unnormalized probability distributions. Using belief graphs, we then introduce the notion of a conditional plan and its goodness for reasoning about actions under qualitative and probabilistic uncertainty. We formulate the problems of optimal and threshold conditional planning under qualitative and probabilistic uncertainty, and show that they are both uncomputable in general. We then give two algorithms for conditional planning in our framework. The first one is always sound, and it is also complete for the special case in which the relevant transitions between epistemic states are cycle-free. The second algorithm is a sound and complete solution to the problem of finite-horizon conditional planning in our framework. Under suitable assumptions, it computes every optimal finite-horizon conditional plan in polynomial time. We also describe an application of our formalism in a robotic-soccer scenario, which underlines its usefulness in realistic applications.

Intense efforts to define a common structure in robotic applications, both from a conceptual and from an implementation point of view, have been carried out in the last years and several frameworks have been realized for helping in developing robotic applications. However, due to the diversity of these applications, as well as of the research groups involved, a common framework is still far from being accepted. In this paper we focus on modularity and re-usability, as major features for robotic applications. We thus characterize existing frameworks for robot software development through the choices made on concurrent execution of modules and information sharing among them and we present OpenRDK, a modular framework focused on rapid development of distributed robotic systems. OpenRDK has been designed and developed with many years of experience following userspsila advice and has been successfully used for the development of many diverse applications with different kinds of robots. After such an extensive test, OpenRDK is now an open source project.

In this paper we present a novel technique to estimate the state of heterogeneous features from inaccurate sensors. The proposed approach exploits the reliability of the feature extraction process in the sensor model and uses a Rao-Blackwellized particle filter to address the data association problem. Experimental results show that the use of reliability improves performance by allowing the approach to perform better data association among detected features. Moreover, the method has been tested on a real robot during an exploration task in a non-planar environment. This last experiment shows an improvement in correctly detecting and classifying interesting features for navigation purpose.

In real-world robotic applications, many factors, both at low-level (e.g., vision and motion control parameters) and at high-level (e.g., the behaviors) determine the quality of the robot performance. Thus, for many tasks, robots require fine tuning of the parameters, in the implementation of behaviors and basic control actions, as well as in strategic decisional processes. In recent years, machine learning techniques have been used to find optimal parameter sets for different behaviors. However, a drawback of learning techniques is time consumption: in practical applications, methods designed for physical robots must be effective with small amounts of data. In this paper, we present a method for concurrent learning of best strategy and optimal parameters, by extending the policy gradient reinforcement learning algorithm. The results of our experimental work in a simulated environment and on a real robot show a very high convergence rate.

The problem of assigning tasks to a group of robots acting in a dynamic environment is a fundamental issue for a multirobot system (MRS) and several techniques have been studied to address this problem. Such techniques usually rely on the assumption that tasks to be assigned are inserted into the system in a coherent fashion. In this work we consider a scenario where tasks to be accomplished are perceived by the robots during mission execution. This issue has a significative impact on the task allocation process and, at the same time, makes it strictly dependent on perception capabilities of robots. More specifically, we present an asynchronous distributed mechanism based on Token Passing for allocating tasks in a team of robots. We tested and evaluated our approach by means of experiments both in a simulated environment and with real robots; our scenario comprises a set of robots that must cooperatively collect a set of objects scattered in the working environment. Each object collection task requires the cooperation of two robots. The experiments in the simulation environment allowed us to extract quantitative data from several missions and in different operative conditions and to characterize in a statistical way the results of our approach, especially when the team size increases

Autonomous surveillance and monitoring of structures is one of the most studied tasks in the past years. In this paper we present an approach in mobile robotic surveillance to detect the presence of people or other moving objects in scenario and classify them as human body and not human body by stereo vision.

Tracking multiple people in a dynamic environment is important in many applications. Recent research in this area has focused either on geometric analysis or appearance models. In this paper we distinguish four types of tracking problems, and then describe an approach for combining geometric analysis and appearance-based tracking to "hold on to" people in three of these situations.

Scan matching is used as a building block in many robotic applications, for localization and simultaneous localization and mapping (SLAM). Although many techniques have been proposed for scan matching in the past years, more efficient and effective scan matching procedures allow for improvements of such associated problems. In this paper we present a new scan matching method that, exploiting the properties of the Hough domain, allows for combining advantages of dense scan matching algorithms with feature-based ones.

In this paper we present an asynchronous distributed mechanism for allocating tasks in a team of robots. Tasks to be allocated are dynamically perceived from the environment and can be tied by execution constraints. Conflicts among team mates arise when an uncontrolled number of robots execute the same task, resulting in waste of effort and spatial conflicts. The critical aspect of task allocation in Multi Robot Systems is related to conflicts generated by limited and noisy perception capabilities of real robots. This requires significant extensions to the task allocation techniques developed for software agents. The proposed approach is able to successfully allocate roles to robots avoiding conflicts among team mates and maintaining low communication overhead. We implemented our method on AIBO robots and performed quantitative analysis in a simulated environment.

Multirobot systems (MRS) are, nowadays, an important research area within robotics and artificial intelligence and a growing number of systems have recently been presented in the literature. Since application domains and tasks that are faced by MRS are of increasing complexity, the ability of the robots to cooperate can be regarded as a fundamental feature. In this paper, we present a survey of the recent work in the area by specifically examining the forms of cooperation and coordination realized in the MRS. In particular, we propose a new taxonomy for classification of the approaches to coordination in MRS and we describe some systems, which we consider representative in our taxonomy. We finally discuss the outcomes of our analysis and try to highlight future trends of the research on MRS.

The activities of search and rescue of victims in large-scale disasters are very relevant social problems, and from a scientific viewpoint raise many different technical problems in the fields of artificial intelligence, robotics and multi agent systems. In this paper we describe the development of a multi agent system based on the RoboCup Rescue simulator to allow monitoring and decision support, that are needed in a rescue operation. Two significant accomplishments are reported in this paper: the first is a framework for cognitive agent development that provides for the capabilities of information fusion, planning and coordination; the second one is a methodology for evaluation of multi-agent systems in this scenario that aims at measuring not only the efficiency of a system, but also its robustness when conditions in the environment change.

Multi-Robot Systems (MRS) are, nowadays, an important research area within Robotics and Artificial Intelligence and a growing number of systems have been recently presented in the literature. In this paper we present an analysis of the most relevant works on MRS by specifically examining their cooperative aspects. In particular, we propose a new taxonomy for a fine and precise analysis of the recent works on MRS and we describe some approaches which we consider representative in our taxonomy. We finally discuss the outcome of our analysis and try to highlight future trends of the research on MRS.

Knowing the position of a mobile robot in the environment in which it operates is an important element for effectively accomplishing complex tasks requiring autonomous navigation. Among several existing techniques for robot self-localization, a new approach called Hough localization was proposed for map matching in the Hough domain, that turned out to be reliable and efficient for position tracking in polygonal environments. In this paper we present an extension of Hough localization which is able to deal with the global localization problem, in which the robot does not know its initial position in the environment.

Autonomous navigation for mobile robots performing complex tasks over long periods of time requires effec-tive and robust self-localization techniques. In this paper we describe a probabilistic approach to self-localization that integrates Kalman filtering with map matching based on the Hough Transform. Several sys-tematic experiments for evaluating the approach have been performed both on a simulator and on soccer robots embedded in the RoboCup environment. 1

Coordination among multiple robots has been extensively studied, since a number of practical tasks can be performed in a more effective way by employing a fleet of coordinated robotic bases. In particular, distributed coordination among robotic agents has been considered within the framework offered by the robotic soccer competitions. We describe the methods and the results achieved in coordinating the players of the ART team participating in the RoboCup F-2000 league. The team is formed by several heterogeneous robots having different mechanics, different sensors, different control software, and, in general, different abilities for playing soccer. The coordination framework we have developed has been successfully applied during the 1999 official competitions allowing both for a significant improvement of the overall team performance and for a complete interchangeability of all the robots.

We describe an approach to reasoning agents which is based on a formal theory of actions and is actually implemented on a mobile robot working in an office environment. From an epistemiological viewpoint, our proposal is originated by the correspondence between Dynamic Logics and Description Logics, Specifically, we consider an epistemic extension of Description Logics to provide a new theoretical framework for the representation of dynamic systems, where the agent's reasoning is based on its knowledge about the world. In this setting, we obtain a weaker notion of logical inference, thus simplifying the reasoning task. From a practical viewpoint, we use a general purpose knowledge representation system based on Description Logics and its associated reasoning tools, in order to plan the actions of the mobile robot 'Tino', starting from the knowledge about the environment and the action specification. In addition, we exploit the robot's capabilities in order to integrate the execution of the plan with reactive behaviours, thus enabling the agent to accomplish its tasks in the real world.

In this paper we present a novel approach to accessing the Web, that enables automatically acquiring data from Web sites and making them accessible to the user through a database query paradigm. The basic idea is to build, once the user has specified a generic domain of interest, the domain conceptual representation, to instantiate it with data extracted from Web sites (so to build a materialized view over the Web), and to query such a conceptual representation through an easy-to-use visual interface. Knowledge representation techniques are used for both the internal modeling of the conceptual representation and for supporting the automatic extraction of data from Web sites to feed the materialized view. We describe a prototype implementation, focusing on the internal representation of information and on the process for analysing Web sites and acquiring data from them. Our preliminary results support our intuition that, at least for certain kinds of queries, the proposed approach can effectively provide the desired information.