In this position paper, we argue for the need for deliberation in communication for artificial agents that perform tasks together with humans. Existing works use a set of terms and concepts with different meanings, resulting in ambiguity which does not allow for a general framework. As an initial step towards such a framework, we propose the notion of deliberative communication, clarify the necessary concepts and terminology, highlight the capabilities required in using deliberation for agents that communicate with human users, and discuss the main challenges.

In many robotic applications, especially those involving humans and the environment, linguistic and visual information must be processed jointly and bound together. Existing works either encode the image or the language into a subsymbolic space, like the CLIP model, or create a symbolic space of extracted information, like the object detection models. In this paper, we propose to describe images by nouns and modifiers and introduce a new embedded binding space where the linguistic and visual cues can effectively be bound. We investigate how state-of-the-art models perform in recognizing nouns and modifiers from images, and propose our method by introducing a dataset and CLIP-like recognition techniques based on transfer learning and metric learning. We show real-world experiments that demonstrate the practical applicability of our approach to robotics applications. Our results indicate that our method can surpass the state-of-the-art in recognizing nouns and modifiers from images. Interestingly, our method exhibits a language characteristic related to context sensitivity.

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.

Autonomous agents embedded in a physical environment need the ability to correctly perceive the state of the environment from sensory data. In partially observable environments, certain properties can be perceived only in specific situations and from certain viewpoints that can be reached by the agent by planning and executing actions. For instance, to understand whether a cup is full of coffee, an agent, equipped with a camera, needs to turn on the light and look at the cup from the top. When the proper situations to perceive the desired properties are unknown, an agent needs to learn them and plan to get in such situations. In this paper, we devise a general method to solve this problem by evaluating the confidence of a neural network online and by using symbolic planning. We experimentally evaluate the proposed approach on several synthetic datasets, and show the feasibility of our approach in a real-world scenario that involves noisy perceptions and noisy actions on a real robot.

Future robots should follow human social norms to be useful and accepted in human society. In this paper, we show how prior knowledge about social norms, represented using an existing normative framework, can be used to (1) guide reinforcement learning agents towards normative policies, and (2) re-use (transfer) learned policies in novel domains. The proposed method is not dependent on a particular reinforcement learning algorithm and can be seen as a means to learn abstract procedural knowledge based on declarative domain-independent semantic specifications.

Joint artistic performance, like music, dance or acting, provides an excellent domain to observe the mechanisms of human-human collaboration. In this paper, we use this domain to study human-robot collaboration and co-creation. We propose a general model in which an AI system mediates the interaction between a human performer and a robotic performer. We then instantiate this model in a case study, implemented using fuzzy logic techniques, in which a human pianist performs jazz improvisations, and a robot dancer performs classical dancing patterns in harmony with the artistic moods expressed by the human. The resulting system has been evaluated in an extensive user study, and successfully demonstrated in public live performances.

The video describes the novel concept of “culturally competent robotics”, which is the main focus of the project CARESSES (Culturally-Aware Robots and Environmental Sensor Systems for Elderly Support). CARESSES a multidisciplinary project whose goal is to design the first socially assistive robots that can adapt to the culture of the older people they are taking care of. Socially assistive robots are required to help the users in many ways including reminding them to take their medication, encouraging them to keep active, helping them keep in touch with family and friends. The video describes a new generation of robots that will perform their actions with attention to the older person's customs, cultural practices and individual preferences.

Abstract Smart robotic environments combine traditional (ambient) sensing devices and mobile robots. This combination extends the type of applications that can be considered, reduces their complexity, and enhances the individual values of the devices involved by enabling new services that cannot be performed by a single device. To reduce the amount of preparation and preprogramming required for their deployment in real‐world applications, it is important to make these systems self‐adapting. The solution presented in this paper is based upon a type of compositional adaptation where (possibly multiple) plans of actions are created through planning and involve the activation of pre‐existing capabilities. All the devices in the smart environment participate in a pervasive learning infrastructure, which is exploited to recognize which plans of actions are most suited to the current situation. The system is evaluated in experiments run in a real domestic environment, showing its ability to proactively and smoothly adapt to subtle changes in the environment and in the habits and preferences of their user(s), in presence of appropriately defined performance measuring functions.

The way in which humans behave, speak and interact is deeply influenced by their culture. For example, greeting is done differently in France, in Sweden or in Japan; and the average interpersonal distance changes from one cultural group to the other. In order to successfully coexist with humans, robots should also adapt their behavior to the culture, customs and manners of the persons they interact with. In this paper, we deal with an important ingredient of cultural adaptation: how to generate robot plans that respect given cultural preferences, and how to execute them in a way that is sensitive to those preferences. We present initial results in this direction in the context of the CARESSES project, a joint EU-Japan effort to build culturally competent assistive robots.

Social norms are the understandings that govern the behavior of members of a society. As such, they regulate communication, cooperation and other social interactions. Robots capable of reasoning about social norms are more likely to be recognized as an extension of our human society. However, norms stated in a form of the human language are inherently vague and abstract. This allows for applying norms in a variety of situations, but if the robots are to adhere to social norms, they must be capable of translating abstract norms to the robotic language. In this paper we use a notion of institution to realize social norms in real robotic systems. We illustrate our approach in a case study, where we translate abstract norms into concrete constraints on cooperative behaviors of humans and robots. We investigate the feasibility of our approach and quantitatively evaluate the performance of our framework in 30 real experiments with user-based evaluation with 40 participants.

Cultural adaptation, i.e., the matching of a robot's behaviours to the cultural norms and preferences of its user, is a well known key requirement for the success of any assistive application. However, culture-dependent robot behaviours are often implicitly set by designers, thus not allowing for an easy and automatic adaptation to different cultures. This paper presents a method for the design of culture-aware robots, that can automatically adapt their behaviour to conform to a given culture. We propose a mapping from cultural factors to related parameters of robot behaviours which relies on linguistic variables to encode heterogeneous cultural factors in a uniform formalism, and on fuzzy rules to encode qualitative relations among multiple variables. We illustrate the approach in two practical case studies.

Cultural competence is a well known requirement for an effective healthcare, widely investigated in the nursing literature. We claim that personal assistive robots should likewise be culturally competent, aware of general cultural characteristics and of the different forms they take in different individuals, and sensitive to cultural differences while perceiving, reasoning, and acting. Drawing inspiration from existing guidelines for culturally competent healthcare and the state-of-the-art in culturally competent robotics, we identify the key robot capabilities which enable culturally competent behaviours and discuss methodologies for their development and evaluation.

Proactive cognitive agents need to be capable of both generating their own goals and enacting them. In this paper, we cast this problem as that of maintaining equilibrium, that is, seeking opportunities to act that keep the system in desirable states while avoiding undesirable ones. We characterize desirability of states as graded preferences, using mechanisms from the field of fuzzy logic. As a result, opportunities for an agent to act can also be graded, and their relative preference can be used to infer when and how to act. This paper provides a formal description of our computational framework, and illustrates how the use of degrees of desirability leads to well-informed choices of action.

Reliable autonomous navigation is still a challenging problem for robots with simple and inexpensive hardware. A key difficulty is the need to maintain an internal map of the environment and an accurate estimate of the robot's position in this map. Recently, a stigmergic approach has been proposed in which a navigation map is stored into the environment, on a grid of RFID tags, and robots use it to optimally reach predefined goal points without the need for internal maps. While effective, this approach is limited to a predefined set of goal points. In this paper, we extend this approach to enable robots to travel to any point on the RFID floor, even if it was not previously identified as a goal location, as well as to keep a safe distance from any given critical location. Our approach produces safe, repeatable and quasi-optimal trajectories without the use of internal maps, self localization, or path planning. We report experiments run in a real apartment equipped with an RFID floor, in which a service robot either reaches or avoids a user who wears slippers equipped with an RFID tag reader.

Many species in nature store information in the environment to facilitate the performance of tasks and enable cooperation. This principle is known as stigmergy. Stigmergy has been widely studied in robotic systems, but so far mostly in simulation or in laboratory proofs of concept. In this paper, we propose a stigmergic approach to goal-directed navigation that can be used for navigation of a full-scale robotic system in a real apartment. A team of small ePuck robots build a set of navigation maps directly onto an RFID floor, where each map is associated to one predefined goal. The information stored in the floor can then used by a mid-size robot or by a larger domestic robot to perform safe navigation toward the predefined goals. To navigate, robots only rely on the information read from the RFID tags: in particular, they do not need to use an internal map or to perform self-localization. This results in robust and repeatable navigation with minimal hardware and software requirements.

Robots for the elderly are a particular category of home assistive robots, helping people in the execution of daily life tasks to extend their independent life. Such robots should be able to determine the level of independence of the user and track its evolution over time, to adapt the assistance to the person capabilities and needs. Human Activity Recognition systems employ various sensing strategies, relying on environmental or wearable sensors, to recognize the daily life activities which provide insights on the health status of a person. The main contribution of the article is the design of an heterogeneous information management framework, allowing for the description of a wide variety of human activities in terms of multi-modal environmental and wearable sensing data and providing accurate knowledge about the user activity to any assistive robot.

Unexpected contingencies in robot execution may induce a cascade of effects, especially when multiple robots are involved. In order to effectively adapt to this, robots need the ability to reason along multiple dimensions at execution time. We propose an approach to closed-loop planning capable of generating configuration plans, i.e., action plans for multirobot systems which specify the causal, temporal, resource and information dependencies between individual sensing, computation, and actuation components. The key feature which enables closed loop performance is that configuration plans are represented as constraint networks, which are shared between the planner and the executor and are continuously updated during execution. We report experiments run both in simulation and on real robots, in which a fault in one robot is compensated through different types of plan modifications at run time.

In this article, we present the ongoing efforts within the newly formed IEEE-RAS Working Group named Ontologies for Robotics and Automation. We focus in particular on one of the four subgroups that compose this working group, called the Upper Ontology/Methodology (UpOM) subgroup. As the name indicates, the aim of this subgroup is to develop an upper ontology and a methodology for ontology building and evaluation. This methodology will be used to coordinate the distributed development of domain specific ontologies by the other three subgroups, and to generate a global ontology that we hope will contribute to the standardization process of robotics and automation. This paper presents the composition, the envisioned methodology, and the future work of the UpOM subgroup. It also discusses some general aspects related to ontologies for the robotics and automation field, and to the efforts in standardizing them.

The combination of task and motion planning presents us with a new problem that we call geometric backtracking. This problem arises from the fact that a single symbolic state or action may be geometrically instantiated in infinitely many ways. When a symbolic action cannot be geometrically validated, we may need to backtrack in the space of geometric configurations, which greatly increases the complexity of the whole planning process. In this paper, we address this problem using intervals to represent geometric configurations, and constraint propagation techniques to shrink these intervals according to the geometric constraints of the problem. After propagation, either (i) the intervals are shrunk, thus reducing the search space in which geometric backtracking may occur, or (ii) the constraints are inconsistent, indicating the non-feasibility of the sequence of actions without further effort. We illustrate our approach on scenarios in which a two-arm robot manipulates a set of objects, and report experiments that show how the search space is reduced.

Environmental monitoring is a rather new field in robotics. One of the main appealing tasks is gas mapping, i.e., the characterization of the chemical properties (concentration, dispersion, etc.) of the air within an environment. Current approaches rely on a robot using standard localization and mapping techniques to fuse gas measures with spatial features. These approaches require sophisticated sensors and/or high computational resources. We propose a minimalistic approach, in which one or multiple low-cost robots exploit the ability to store information in the environment, or ¿stigmergy¿, to effectively compute an artificial potential leading toward the likely location of the gas source, as indicated by a highest gas concentration or fluctuation. The potential is computed and stored directly on an array of RFID tags buried under the floor. Our approach has been validated in extensive experiments performed on real robots in a domestic environment.

Autonomous vehicles are being increasingly introduced in the mining industry. While these may offer high safety and high productivity, fully autonomous solutions are not always applicable or economically viable. Teleoperation is an attractive option, since it increases safety and comfort of the drivers. Unfortunately, the difficulty to operate the vehicle remotely often results in reduced productivity. In this paper, we show that techniques from the field of mobile robotics can be used to mitigate this problem. We extend a commercial teleoperation system for use in underground mines with a local autonomy functionality, with the main purpose to evaluate if the achieved productivity improvement motivates development of general algorithms and a fully commercial implementation. We then describe a user study performed in an underground mine with a 38 tonne articulated wheel loader, which proves that local autonomy gives a significant improvement in productivity of the teleoperation system, while retaining or even reducing the maintenance costs.

Consider a house cleaning robot planning its activities for the day. Assume that the robot expects the human inhabitant to first dress, then have breakfast, and finally go out. Then, it should plan not to clean the bedroom while the human is dressing, and to clean the kitchen after the human has had breakfast. In general, robots operating in inhabited environments, like households and future factory floors, should plan their behavior taking into account the actions that will be performed by the humans sharing the same environment. This would improve human-robot cohabitation, for example, by avoiding undesired situations for the human. Unfortunately, current task planners only consider the robot's actions and unexpected external events in the planning process, and cannot accommodate expectations about the actions of the humans. In this article, we present a human-aware planner able to address this problem. Our planner supports alternative hypotheses of the human plan, temporal duration for the actions of both the robot and the human, constraints on the interaction between robot and human, partial goal achievement and, most importantly, the possibility to use observations of human actions in the policy generated for the robot. Our planner has been tested both as a stand-alone component and within a full framework for human-robot interaction in a real environment.

Stigmergy is a mechanism that allows the coordination of actions within the same agent or across different agents by means of traces left in the environment. We propose a stigmergetic approach to robot navigation in which a robot sets values in a hexagonal grid of RFID tags buried under the floor. This approach only requires minimal resources on the robot. The RFID floor will eventually contain a distance map that can guide the robot to a given goal (or set of goals) without the use of any localization system. The same map can be used or improved by other robots or by the same robot at later times. We define algorithms for building the RFID-floor map and for navigating on this map, we prove the convergence of the map building algorithm, and we show an empirical validation of our results using a small robot in a domestic environment.

Intelligent environments are increasingly rich in ubiquitous sensing capabilities that can be leveraged to know which actions a user is engaged in at any given moment in time. The ability of an intelligent environment to recognize a high-level plan of activities performed by the user in a smart home would allow to construct proactive services, such as reminding, forecasting and providing timely physical support. This article proposes an approach to human activity recognition based on temporal planning. The approach leverages on one hand the ubiquitous sensors provided by the PEIS-Home, a sensor-rich intelligent environment, and, on the other hand, the temporal representation and reasoning capabilities of OMPS, a constraint-based temporal planning and scheduling framework.

In this paper, we address the problem of fusing information about object positions in multirobot systems. Our approach is novel in two main respects. First, it addresses the multirobot object localization problem using fuzzy logic. It uses fuzzy sets to represent uncertain position information and fuzzy intersection to fuse this information. The result of this fusion is a consensus among sources, as opposed to the compromise achieved by many other approaches. Second, our method fully propagates self-localization uncertainty to object-position estimates. We evaluate our method using systematic experiments, which describe an input-error landscape for the performance of our approach. This landscape characterizes how well our method performs when faced with various types and amounts of input errors.

We consider multi-robot systems where robots need to cooperate tightly by sharing functionalities with each other. There are methods for automatically configuring a multi-robot system for tight cooperation, but they only produce a single configuration. In this paper, we show how methods for automatic configuration can be integrated with methods for task planning in order to produce a complete plan were each step is a configuration. We also consider the issues of monitoring and replanning in this context, and we demonstrate our approach on a real multi-robot system, the PEIS-Ecology.

Highly heterogeneous robotic systems are becoming increasingly common, as are robotic systems integrated with smart environments. In such distributed systems, there are many different sources and types of information, which need to be coordinated and combined effectively. The problem of cooperative anchoring is (roughly) the problem of, in a distributed system, determining which items of information refer to the same objects, and combining these items accordingly. In this paper, we define a general computational framework for cooperative anchoring inspired by work on conceptual spaces and (single-robot) perceptual anchoring. We also discuss an implementation of this framework which uses tools from fuzzy logic, and we present an illustrative experiment.

In this paper we propose a new feature detection algorithm to enable junction recognition intended for high speed reactive navigation in tunnel like environments. We also present an extensive experimental evaluation of the algorithm based on data recorded in a real mine. The algorithm is faster and has less environmental constraints than similar algorithms that can be found in the literature.

Robotic middlewares increasingly allow the seamless integration of multiple heterogeneous robots into one distributed system. Unfortunately, very simple devices like tagged everyday objects and smart objects are left orphan in this otherwise pervasive trend. We claim that the inclusion of simple everyday objects as part of distributed robot systems would have many advantages, and propose a design pattern to allow this inclusion. We make this pattern concrete by describing an implementation of it using a specific multi-robot middleware, called PEIS-Ecology Middleware. We also show an illustrative experiment which integrates everyday objects in a smart home equipped with mobile robots as well as more advanced distributed sensor nodes.

The vision of an ecology of physically embedded intelligent systems, or PEIS-Ecology, combines insights from the fields of autonomous robotics and ambient intelligence to provide a new approach to building robotic systems in the service of people. In this paper, we present this vision, and we report the results of a four-year collaborative research project between Sweden and Korea aimed at the concrete realization of this vision.We focus in particular on three results: a robotic middleware able to cope with highly heterogeneous systems; a technique for autonomous self-configuration and reconfiguration; and a study of the problem of sharing information of both physical and digital nature.

A trend is emerging in the fields of ambient intelligence (Ami) and autonomous robotics, which points in the direction of a merger between these two fields. The inclusion of robotic devices in Ami system, sometimes named ubiquitous robotics, makes one of the hard problems in this field even harder: how can we provide a comfortable, natural interface between the everyday user and a complex system which consists of a large multitude of highly heterogeneous devices? In this paper, we address a specific, important aspect of this problem: to monitor the state of the ubiquitous system by the user of the system. The solution that we propose is based on two mechanisms: an expression-based semantics to represent in a uniform way the status of heterogeneous devices; and a common interface point to aggregate the information from all devices into a summary status presented to the user. For both mechanisms, we propose to use the tools of fuzzy logic. We justify this choice by arguments grounded in the semantics and formal properties of fuzzy logic. We also illustrate our approach on a specific type of ubiquitous robotic system called Ecology of Physically Embedded Intelligent Systems, or PEIS-Ecology.

We describe a novel intelligent execution monitoring approach for mobile robots acting in indoor environments such as offices and houses. Traditionally, monitoring execution in mobile robotics amounted to looking for discrepancies between the model-based predicted state of executing an action and the real world state as computed from sensing data. We propose to employ semantic knowledge as a source of information to monitor execution. The key idea is to compute implicit expectations, from semantic domain information, that can be observed at run time by the robot to make sure actions are executed correctly. We present the semantic knowledge representation formalism, and how semantic knowledge is used in monitoring. We also describe experiments run in an indoor environment using a real mobile robot.

We consider an ecology of robots in which robots can help each other by offering information-producing functionalities. A functional configuration of this ecology is a way to allocate and connect functionalities among the participating robots. In general, different configurations can be used to solve the same task, depending on the current situation, and some tasks require sequences of different configurations to be solved. In this paper, we propose a plan-based approach to automatically generate a preferred configuration for a given task, environment, and set of resources. We also describe how our configuration planner can be integrated with an action planner to deal with tasks that require sequences of configurations. We illustrate these ideas on a specific instance of an ecology of robots, called a PEIS Ecology. We also show an experiment run on our PEIS Ecology testbed, in which a sequence of configurations for an olfactory task is automatically generated and executed.

The fields of autonomous robotics and ambient intelligence are converging toward the vision of smart robotic environments, in which tasks are performed via the cooperation of many networked robotic devices. To enable this vision, we need a common communication and cooperation model that can be shared between robotic devices at different scales, ranging from standard mobile robots to tiny embedded devices. Unfortunately, today's robot middlewares are too heavy to run on tiny devices, and middlewares for embedded devices are too simple to support the cooperation models needed by an autonomous smart environment. In this paper, we propose a middleware model which allows the seamless integration of standard robots and simple off-the-shelf embedded devices. Our middleware is suitable for building truly ubiquitous robotics applications, in which devices of very different scales and capabilities can cooperate in a uniform way. We discuss the principles and implementation of our middleware, and show an experiment in which a mobile robot, a commercial mote, and a custom-built mote cooperate in a home service scenario.

Executing plans by mobile robots, in real world environments, faces the challenging issues of uncertainty and environment dynamics. Thus, execution monitoring is needed to verify that plan actions are executed as expected. Semantic domain-knowledge has been proposed as a source of information to derive and monitor implicit expectations of executing actions. For instance, when a robot moves into a room asserted to be an office, it would expect to see a desk and a chair. We propose to extend the semantic knowledge-based execution monitoring to take uncertainty in actions and sensing into account when verifying the expectations derived from semantic knowledge. We consider symbolic probabilistic action models, and show how semantic knowledge is used together with a probabilistic sensing model in the monitoring process of such actions. Our approach is illustrated by showing test scenarios run in an indoor environment using a mobile robot.

There is a tendency today toward the study of distributed systems consisting of many heterogeneous, networked, cooperating robotic devices. We refer to a system of this type as an ecology of robots. We call functional configuration of this ecology a way to allocate and connect functionalities among its robots. In general, the same ecology can perform different tasks by using different configuration. Moreover, the same task can often be solved using different configurations, and which is the best one depends on the available resources. This potential flexibility of a robot ecology is reduced by the fact that, in most current approaches, configurations are pre-programmed by hand. In this paper, we propose a plan-based approach to automatically generate a preferred configuration of a robot ecology given a task, environment, and set of resources. In contrast to previous approaches, the state of the ecology is automatically acquired at planning time, and it is monitored during execution in order to reconfigure if a functionality fails. We illustrate these ideas on a specific instance of an ecology of robots, called PEIS Ecology. We also show an experiment run on our PEIS Ecology testbed, in which a robot needs to reconfigure when the original configuration fails.

Robot ecologies provide a new paradigm for assistive, service, industrial, and entertainment robotics which is quickly gaining popularity. These ecologies contain a large number of robotic components pervasively embedded in the environment and interacting with each other. Human users of such systems need to be able to interface with both the system as a w hole and, if desired, which each individual component. The humans should be able to transmit, in a natural way, commands that range from basic ones, such as "turn on the lights in the bedroom", to abstract ones, such as "bring me a cup of coffee". Human users may also need to interact with task execution, especially at decision points. In this paper, we introduce an approach to interface a human user to a specific type of robot ecology, called an ecology of Physically Embedded Intelligent Systems, or PEIS-Ecology. The ecology includes simple sensors and actuators and more complicated devices such as mobile robots. The proposed interface satisfies two requirements: 1) to easily and automatically generate component interfaces, and 2) to provide a simple mechanism by which to request and monitor the execution of tasks in the ecology.

The use of a symbolic model of the spatial environment becomes crucial for a mobile robot that is intended to operate optimally and intelligently in indoor scenarios. Constructing such a model involves important problems that are not solved completely at present. One is called anchoring, which implies to maintain a correct dynamic correspondence between the real world and the symbols in the model. The other problem is adaptation: among the numerous possible models that could be constructed for representing a given environment, optimization involves the selection of one that improves as much as possible the operations of the robot. To cope with both problems, in this paper, we propose a framework that allows an indoor mobile robot to learn automatically a symbolic model of its environment and to optimize it over time with respect to changes in both the environment and the robot operational needs through an evolutionary algorithm. For coping efficiently with the large amounts of information that the real world provides, we use abstraction, which also helps in improving task planning. Our experiments demonstrate that the proposed framework is suitable for providing an indoor mobile robot with a good symbolic model and adaptation capabilities.

In the near future, autonomous mobile robots are expected to help humans by performing service tasks in many different areas, including personal assistance, transportation, cleaning, mining, or agriculture. In order to manage these tasks in a changing and partially unpredictable environment without the aid of humans, the robot must have the ability to plan its actions and to execute them robustly and safely. The robot must also have the ability to detect when the execution does not proceed as planned and to correctly identify the causes of the failure. An execution monitoring system allows the robot to detect and classify these failures. Most current approaches to execution monitoring in robotics are based on the idea of predicting the outcomes of the robot's actions by using some sort of predictive model and comparing the predicted outcomes with the observed ones. In contrary, this paper explores the use of model-free approaches to execution monitoring, that is, approaches that do not use predictive models. In this paper, we show that pattern recognition techniques can be applied to realize model-free execution monitoring by classifying observed behavioral patterns into normal or faulty execution. We investigate the use of several such techniques and verify their utility in a number of experiments involving the navigation of a mobile robot in indoor environments.

We present a new approach for odour detection and recognition based on a so-called PEIS-Ecology: a network of gas sensors and a mobile robot are integrated in an intelligent environment. The environment can provide information regarding the location of potential odour sources, which is then relayed to a mobile robot equipped with an electronic nose. The robot can then perform a more thorough analysis of the odour character. This is a novel approach which alleviates some the challenges in mobile olfaction techniques by single and embedded mobile robots. The environment also provides contextual information which can be used to constrain the learning of odours, which is shown to improve classification performance

We introduce the concept of ecology of physically embedded intelligent systems, or PEIS-ecology. This is a network of heterogeneous robotic devices (PEIS) pervasively embedded in the environment. A PEIS can be as simple as a toaster and as complex as a humanoid robot. PEIS can exchange information at different levels of abstraction, and share both physical and virtual functionalities to perform complex tasks. By putting together insights from the fields of autonomous robotics and of ambient intelligence, the PEIS-ecology approach explores a new road to building assistive, personal, and service robots. In this paper, we discuss this concept, describe a first realization of it, and show an implemented use-case scenario

The success of mobile robots, and particularly of those interfacing with humans in daily environments (e.g., assistant robots), relies on the ability to manipulate information beyond simple spatial relations. We are interested in semantic information, which gives meaning to spatial information like images or geometric maps. We present a multi-hierarchical approach to enable a mobile robot to acquire semantic information from its sensors, and to use it for navigation tasks. In our approach, the link between spatial and semantic information is established via anchoring. We show experiments on a real mobile robot that demonstrate its ability to use and infer new semantic information from its environment, improving its operation.

Typical mobile robots can be customized to perform a variety of different tasks by combining in different ways a set of basic control modules, or behaviors. By contrast, most current systems for manipulation are still designed for just one specific task. In this paper, we propose a hierarchical behavior-based system that can perform several vision-based manipulation tasks by using different combinations of the same set of basic behaviors. Behaviors can run concurrently, and they are arbitrated through "if-then" rules. We show experiments involving object tracking, grasping and placing, both with static and moving objects.

Indoor environments typically consist of sets of connected room-like spaces. We present a local technique that uses range data to detect these spaces during navigation. Our technique includes two parts: segmentation, which isolates room-like spaces and detects when the robot has entered a new one; and feature extraction, which associates each space with a set of geometric features useful for navigation or recognition. Many such features can be considered: here we propose a new method to compute width and length of a rectangular room in a way which is largely invariant with respect to the configuration of the furniture. We report experimental results that show the performance of our technique, and hint at a possible use of this technique for coarse localization on a topological map.

Behavior-based approaches to robot control are extremely popular in mobile robotics, but still rarely used for manipulation. We propose a behavior-based system that performs manipulation tasks using visual feedback. The distinctive points of our proposal are: (i) visual behavior is implemented using a new camera-based approach; (ii) reactive fuzzy rules are used to arbitrate behavior; and (iii) the outputs of concurrent behavior are fused using fuzzy logic. We show experiments on a real arm performing a pick-and-place task that illustrate our approach and demonstrate its advantages over current approaches.

An intelligent physical agent must incorporate motor and perceptual processes to interface with the physical world, and abstract cognitive processes to reason about the world and the options available. One crucial aspect of incorporating cognitive processes into a physically embedded reasoning system is the integration between the symbols used by the reasoning processes to denote physical objects, and the perceptual data corresponding to these objects. We treat this integration aspect by proposing a fuzzy computational theory of anchoring. Anchoring is the process of creating and maintaining the correspondence between symbols and percepts that refer to the same physical objects. Modeling this process using fuzzy set-theoretic notions enables dealing with perceptual data that can be affected by uncertainty/imprecision and imprecise/vague linguistic descriptions of objects.

We address the problem of enabling a mobile robot to locate a stationary odour source using an electronic nose constructed from gas sensors. On the hardware side, we use a stereo nose architecture consisting of two parallel chambers, each containing an identical set of sensors. On the software side, we use a recurrent artificial neural network to learn the direction to a stationary source from a time series of sensor readings. This contrasts with previous approaches, that rely on the existence of a model of the sensor's dynamics. The complete system is able to orient and turn towards the source. An experimental validation was carried out to evaluate the performance of the system.

The problem of combining pieces of information issued from several sources can be encountered in various fields of application. This paper aims at presenting the different aspects of information fusion in different domains, such as databases, regulations, preferences, sensor fusion, etc., at a quite general level. We first present different types of information encountered in fusion problems, and different aims of the fusion process. Then we focus on representation issues which are relevant when discussing fusion problems. An important issue is then addressed, the handling of conflicting information. We briefly review different domains where fusion is involved, and describe how the fusion problems are stated in each domain. Since the term fusion can have different, more or less broad, meanings, we specify later some terminology with respect to related problems, that might be included in a broad meaning of fusion. Finally we briefly discuss the difficult aspects of validation and evaluation. © 2001 John Wiley & Sons, Inc.

We propose topology-based maps as a new representation of the workspace of a mobile robot. These maps capture the structure of the free space in the environment in terms of the basic topological notions of connectivity and adjacency. Topology-based maps can be automatically extracted from an occupancy grid built from sensor data using techniques borrowed from the image processing field. Since these techniques can be soundly defined on fuzzy values, our approach is well suited to deal with the uncertainty inherent in the sensor data. Topology-based maps are fairly robust with respect to sensor noise and to small environmental changes, and have nice computational properties.

Perceptual anchoring is the process of linking action to the appropriate objects in the environment via perception. The pivot of anchoring is the inclusion of micromodels of the world, or anchors, into a controller. In this paper, we propose to use anchors to focus the perceptual effort according to the current needs of the controller. We describe an active gaze control strategy able to maintain anchoring of several objects in a dynamic environment, and show how we have used it in a team of legged robots in the RoboCup'99 international robot soccer competition.

We describe a new technique for landmark-based self-localization which is suitable for robots with poor odometry. This technique uses fuzzy logic to account for errors and imprecision in visual recognition, and for extreme uncertainty in the estimate of the robot's motion. It only requires an approximate model of the sensor system and a qualitative estimate of the robot's displacement, and it has a moderate computational cost. We show examples of use of our technique on a Sony AIBO legged robot in the RoboCup domain.

We present PLn[otimes], a multi-agent epistemic logic where each agent can perform uncertain (possibilistic) reasoning. The original feature of this logic is the presence of a distributed belief operator, with the purpose of merging the belief of different agents. Unlike the corresponding operator in the categorical (non-uncertain) case, our distributed belief operator accumulates support for the same fact coming from different agents. This means that opinions shared by different agents can be combined into a stronger distributed belief. This feature is useful in problems like pooling expert opinions and combining information from multiple unreliable sources. We provide a possible worlds semantics and an axiomatic calculus for our logic, and prove soundness, completeness and decidability results. We hint at some possible applications of PLn[otimes] in the conclusions. Key words: Epistemic logic, distributed belief, data fusion, possibility theory, fuzzy logic, multiple agents.

Mobile robots, if they are to perform useful tasks and become accepted in open environments, must be fully autonomous. Autonomy has many different aspects ; here the focus is on three central ones: the ability to attend to another agent, to take advice about the environment, and to carry out assigned tasks. All three involve complex sensing and planning operations on the part of the robot, including the use of visual tracking of humans, coordination of motor controls, and planning. It is shown how these capabilities are integrated in the Saphira architecture, using the concepts of coordination of behaviour, coherence of modelling, and communication with other agents.

Network-based representations of uncertain knowledge are inherently propositional, and cannot easily accommodate generic, problem independent knowledge. A tremendous effort has been devoted in the knowledge representation community to develop languages that adequately represent different types of generic knowledge. The authors propose inference-driven construction as a means to use these languages for extending the expressiveness of uncertainty networks: they let a knowledge representation system represent generic knowledge and infer solutions to specific problem instances, and then copy the resulting inference structure to an uncertainty network that models these instances. From a dual perspective, inference-driven construction is a way of extending an existing knowledge representation system by attaching an uncertainty calculus to it. In this paper, the authors focus on one particular case of inference-driven construction: building Shenoy-Shafer's valuation systems from uncertain knowledge expressed in the form of first order clauses annotated by Dempster-Shafer's measures of belief. The authors detail an automatic construction procedure for this case, discuss a sample implementation, and provide a soundness and completeness result.>