Search

International audience; Most of recent researches on the automotive field focus on autonomous vehicles. These vehicles are equipped with conventional chassis systems. The goal is to control the vehicle's traction, brakes, and front steering. This paper discusses the importance of advanced chassis systems, as driving/braking torque vectoring, for both autonomous and non-autonomous vehicles, especially in a race mode. Reliable co-simulation results show that expanding the vehicle's potential leads to high performances and safety with respect to severe situations when optimal control allocation is ensured. Therefore, future passenger cars shall not only be equipped with additional sensors, but also by advanced systems along with adequate control algorithms.

International audience; This special issue aims at examining and promoting recent developments in the Assistive/Social Robotics field and future directions including the related challenges and how these can be overcome with particular focus on computational intelligence methodologies. With robots being integrated more and more in our environments and daily activities, the effectiveness of robotics applications has to rely on robots' ability to perceive, reason, and adapt on-the-fly to the users' behavior and needs. In particular, the development of personal robots, as assistive technological tools, challenges researchers to develop socially intelligent and adaptive robots that can collaborate with people in real environment. This special issue is comprised of 14 papers, fostering discussions and investigations in robot behavior adaptation and learning, in socially assistive robotics, and in developing reliable systems for natural interactions between humans and robots. Several aspects and perspectives are taken into consideration by the authors covering various topics such as adaptability during real-world human-robot interactions ; new reinforcement learning and learning by teaching techniques especially used in the context of child-robot interaction ; social robot responses, perception and adaptation by means of a semantic representation; robots acceptability and security. Furthermore, several assistive applications for the elderly, children, and people are presented. B Mariacarla Staffa

Robotic systems are becoming more safety critical systems as they are deployed in unstructured human-centered environments. These software intensive systems are composed of distributed, heterogeneous software components interacting in a highly dynamic, uncertain environment. However, no systematic software development process is followed in robotics research. This is a real barrier for system level performance analysis and reasoning, which are in turn required for scalable bench-marking methods and reusing existing software. This chapter provides an end-to-end overview on how robotic software systems can be formally specified from requirement modeling, through solution space exploration, and architecture modeling, and finally to generate executable code. The process is based on SafeRobots framework—a model-driven toolchain for designing software for robotics. Several domain-specific modeling languages that are developed as a part of this integrated approach are also discussed.

International audience; Many research projects are focusing on automated vehicles and reinventing the automotive industry. New technologies are introduced, and the pillars of the ground vehicle are revisited and new challenges appeared. This paper focuses on the chassis systems and their control strategies. While assistance strategies use to manage specific operations, autonomous vehicles need to handle simultaneous operations. Optimal solutions for systems coordination are discussed in this paper. Results show that the more we get closer to full autonomous driving where an important number of embedded systems is needed, the more optimal coordination strategies are relevant. These strategies should be considered in the upcoming automotive industrial standards.

Several modern vehicles provide the option to select a driving mode. However, the literature contains no empirical studies that investigate how driving modes affect the vehicle's dynamic behaviour in regular on-road driving. We examined for which CAN-bus signals the differences between Renault's Multi-Sense® comfort and sport modes are most apparent. We gathered data on a 26.3 km route containing a rural and highway section. A single person drove the route four times in comfort mode and four times in sport mode. By statistically analysing and ordering 887 CAN-bus signals, we found strong differences between the two modes for rear-wheel angle, engine torque, longitudinal acceleration, and vertical motion. Parameter identification of a quarter car model identified a 3.5 times higher damping coefficient for the sport mode compared to the comfort mode. Due to four wheel steering, compared to the comfort mode, the sport mode yielded a higher lateral acceleration and yaw rate for a given steering wheel angle and driving speed. In conclusion, this study provides quantitative insight into the extent to which the Multi-Sense driving modes impact the vehicle's lateral, longitudinal, and vertical dynamic behaviour. The results and the analysis methods help guide future driving mode designs.

Our previous work in detecting deception in HRI was based on research findings from the psychology of inter-human interactions. Nonetheless, these conclusions may or may not be directly applied in HRI, as humans may not behave similarly when deceiving a robot. This paper studies the differences between human physiological manifestations during a deception card game scenario when playing it with a human or a robot partner. Our results show the existence of significant differences between the participants’ skin conductance, eye openness, and head pose when playing the game with a robot partner compared to when playing the game with a human partner. These results will then be used to improve the ability of robots to detect deception in HRI.

For socially assistive robots, being able to recognize basic human actions is an important capability. The sensors, which are frequently mounted on most recent robots, such as RGB-D and thermal cameras, as well as the advances in deep learning have enabled the research on activity recognition to grow. In this paper, we collected our own dataset of actions in a home-like scenario, which contains thermal imagery in addition to RGB-D data and we proposed a method based on Long-term Recurrent Convolutional Networks (LRCN). We showed that our method has an accuracy comparable with the state-of-the-art. We also proved that thermal information can improve the recognition accuracy. Furthermore, we tested the real-time capability of our system and conducted a real-time experiment with a robot (Pepper robot from Softbank Robotics) so as to investigate the effect of a robot enabled with action recognition capability in a human-robot interaction.

International audience; In this paper, we describe the elaboration and the validation of a body and face database of 96 videos of 1 to 2 seconds of duration, expressing 4 emotions (i.e., anger, happiness, fear, and sadness) elicited through 4 platforms of increased visual complexity and level of embodiment. The final aim of this database is to develop an individualized training program designed for individuals suffering of autism in order to help them recognize various emotions on different test platforms: two robots, a virtual agent, and a human. Before assessing the recognition capabilities of individuals with ASD, we validated our video database on typically developed individuals (TD). Moreover, we also looked at the relationship between the recognition rate and their personality traits (extroverted (EX) vs. introverted (IN)). We found that the personality of our TD participants didn’t lead to a different recognition behavior. However, introverted individuals better recognized emotions from less visually complex characters than extroverted individuals.

International audience; Most of automotive researches focus on autonomous vehicles. Studies regarding trajectory planning and trajectory tracking became preponderant. As in case of commercial ground vehicles there is a driver in the loop, one should raise the important question of how the trajectory should be tracked. In this paper, we investigate the influence of controlling integrated chassis systems on the vehicle's behavior. A fixed Model Predictive Control is used to track the trajectory. Tunable vehicle motion control is however used to provide different motion feelings. Results show that a specific trajectory could be followed in different manners. Therefore, vehicle dynamics can be and should be controlled in such a way to generate adaptive trust feelings to passengers in case of autonomous driving.

International audience; Most of the chassis systems are developed by automotive suppliers to improve a specific vehicle performance. Drivers, and consequently vehicle manufacturers, are more concerned by the overall behaviour of the Vehicle. Many coordination architectures have been proposed in the literature in order to integrate different chassis systems in a single vehicle. In this paper , these architectures are compared and discussed. Two major classes are proposed: Downstream and Upstream Coordination. The purpose of this classification is to help car manufacturers and suppliers standardize an Integrated Vehicle Dynamics Control architecture for faster and more flexible designs.

International audience; —A large interest has recently been given to global chassis control. This requires a tire model adapted to control synthesis that can represent combined slip. In this paper, a new suitable tire model for vehicle coupled operations control is proposed. The existing models are either too simple to represent coupled behaviors or too complex to allow control synthesis. This new tire model takes benefits from both approaches, as it is linear with varying parameters. Simulations of coupled operations proved the model accuracy in the tire stable range and its promising potential for global chassis control synthesis.

In order to promote reuse of software in robotics, standardization, benchmarking, and formalization activities in robotics are being undertaken by many technical working groups and independent agencies. Absence of integrated tools is the real barrier that exists between early adopters of such efforts and early majority of research and industrial community. In this paper, we provide a detailed discussion on how frameworks for designing robotic systems can be formally specified and developed using our meta-framework - SafeRobots. We have demonstrated this process using a mobile robot case study.

This workshop aims at advancing the topic of the relationships between robotics science and experiments in HRI. The full-day workshop follows on previous events in interdisciplinary venues focusing on efforts to establish reproducible, standardized experiments in order to adequately benchmark and evaluate human-robot interaction, scientific achievements and results in the areas of industrial, medical, social, service and personal-care robots. The words "standard" and "standardized" sometimes are misunderstood as fixing and blocking the freedom of the researcher to create new experiments and therefore to advance the scientific knowledge. As per this workshop, the words must be intended as a "way of experimenting temporarily agreed by the community, that is evolving and tracking the scientific progress through continuous revision by the community itself".

Our work aims at developing a behavioral model enabling customized and natural interaction between a robot and an elderly individual in the context of the EU H2020 ENRICHME Project - Grant Agreement 643691. The main idea of the project is to make the robot able to learn from past experiences and to adapt its behavior to the profile (i.e., personality, cognitive disability level, emotional internal states) and preferences of the person it interacts with. In this paper the robot will try to determine if the person it interacts with is trying to deceive it or not. Some first preliminary experiments and results are presented.

In social HRI context, the robot’s usefulness and appropriate behavior plays an important role. A robot should be able to understand the human’s internal state (i.e., physiological and psychological states) so as to provide an adaptive and thus efficient assistance within daily life activities. Measuring stress and frustration of an individual while performing a certain task is a critical element that can help the robot adapt its behavior so as to improve user’s interest and task performance and to reduce his/her frustration. In this paper, we designed an experiment called “Stress Game”. In our work, stress is measured in terms of heart rate signal. The robot displays different behaviors as a function of user’s personality and game condition. We conducted our experiments with the NAO robot. The experimental results support our hypotheses that the robot has a positive effect on stress relief.

International audience; Robots have increasingly been used for improving the quality of life of people with special needs, such as people suffering from Mild Cognitive Impairment, elderly, people with different physical and cognitive abilities. In this paper, we propose a method for extracting and analyzing physiological data by using contactless sensors (i.e., RGB and thermal cameras). The physiological parameters that can be analyzed are: the respiration rate, blinking rate, and the temperature variation across different regions on the face (i.e., the forehead, the nose, the peri-nasal region, the left and right periorbital regions, and the entire face). These parameters, together with the action units (AUs) can be indicators of the current internal state of an user. We analyze data from three different scenarios and report the results obtained.

In order to appear as natural as possible during social interaction, robots need either the ability to express or to measure emotions. Touch can be a very powerful communication modality but is very little exploited. Our paper aims to create a model of the tactile features activated during a handshake act, that can discriminate intrinsic characteristics of a person such as gender or extroversion. First, we construct a model of handshaking based on the human-human styles of handshaking. This model is thereafter compared with a human-robot handshaking interaction. The Meka robot is used in our experiments. A method is proposed to manage the modeling using feature selection with ANOVA and linear discriminant analysis (LDA). The first preliminary results show that it is possible to recognize gender and extroversion personality trait based on the firmness and movement of the style of handshaking. For instance, smaller pressure and frequency were found to describe female handshakes and higher speed amplitude describe introverted handshakes. Consistency was also found when comparing human-human handshaking with human-robot ones. These are encouraging results that will allow us to develop personalized interactions.

In Human-Robot Interaction (HRI), an important quantity of work has been done to investigate the reaction of people toward expressive robots. However, the large variability of available expression modalities (e.g., gaze, gestures, speech modulation) can make comparison between results difficult. We believe that developing a common taxonomy to describe these modalities would contribute to the standardization of HRI experiments. This paper proposes the first version of a classification system based on an analysis of humanoid robots commonly seen and used in HRI studies. Features from the face of robots are discussed in terms of functional and non-functional dimensions, and a short-hand notation is developed to describe these features.

Socially intelligent robotics is the pursuit of creating robots capable of exhibiting natural-appearing social qualities. Beyond the basic capabilities of moving and acting autonomously, the field has focused on the use of the robot's physical embodiment to communicate and interact with users in a social and engaging manner. One of its components, socially assistive robotics, focuses on helping human users through social rather than physical interaction. Early results already demonstrate the promises of socially assistive robotics, a new interdisciplinary research area with large horizons of fascinating and much needed research. Even as socially assistive robotic technology is still in its early stages of development, the next decade promises systems that will be used in hospitals, schools, and homes in therapeutic programs that monitor, encourage, and assist their users. This is an important time in the development of the field, when the board technical community and the beneficiary populations must work together to shape the field toward its intended impact on improved human quality of life

For companion robots to properly interact with people, they should be able to gain awareness of their effect on the person's state and learn to behave accordingly. Advances in physiological monitoring sensors, such as infrared cameras, may enable robots to get an insight on a person's emotional state, which has a strong correlation with the physiological parameters. Performing this monitoring in a contact-free, user transparent manner is an important requirement. In this paper, we used a thermal imaging sensor mounted on the Meka humanoid robot, to remotely measure temperature variations on the face of the person while interacting with it. The scenario was a card-based quiz with the robot, which was aimed to induce a stressful state and 16 participants took part in the experiment. Several conditions with variations in the distance, height, and gaze of the robot were tested. A statistically significant variation in temperature in the nasal area of the face was measured while the robot was standing in the personal space of the participant. The first preliminary results encourage us to believe that temperature variations across various areas of people's faces can hint companion robots to adjust their behavior in human interactions.

A typical feature of robotic architectures are its reactivity and self-adaptivity. In practice, this is achieved by context-dependent dynamic invocation of software components in robotic architectures. In this paper, we specifically address how this self-adaptation capability can be formally defined and modeled in an architecture-independent way. We propose a probabilistic approach that facilitates system design and dynamic runtime adaptation satisfying the quality requirements. We also show how such techniques are incorporated in our model-driven framework: Self Adaptive Framework for Robotic Systems.

A common goal of robot control architecture designers is to create systems that are sufficiently generic to be adapted to different robot hardware. Beyond code re-use from a software engineering standpoint, having a common architecture could lead to long-term experiments spanning multiple robots and research groups. This paper presents a first step toward this goal with HBBA, a Hybrid Behavior-Based Architecture first developed on the IRL-1 humanoid robot and integrating an Adaptive Resonance Theory-based episodic memory (EM-ART). This paper presents the first step of the adaptation of this architecture to two different robots, a Meka M-1 and a NAO from Aldebaran, with a simple scenario involving learning and sharing objects' information between both robots. The experiment shows that episodes recorded as sequences of people and objects presented to one robot can be recalled in the future on either robot, enabling event anticipation and sharing of past experiences.

International audience; An intelligent robot needs to be able to understand human emotions, and to understand and generate actions through cognitive systems that operate in a similar way to human cognition. In this chapter, we mainly focus on developing an online incremental learning system of emotions using Takagi-Sugeno (TS) fuzzy model. Additionally, we present a general overview for understanding and generating multimodal actions from the cognitive point of view. The main objective of this system is to detect whether the observed emotion needs a new corresponding multi-modal action to be generated in case it constitutes a new emotion cluster not learnt before, or it can be attributed to one of the existing actions in memory in case it belongs to an existing cluster.

In recent times, researchers in robotics have arrived at a consensus that there is no single efficient architecture or framework that satisfies all aspects of robotic system design. A majority of robotic architectures currently in use are developed in-house to meet the specific objectives of the research group. However, these frameworks have been designed in an ad-hoc manner and thus restricts reusability and scalability. In this paper, we propose an architecture description language ‘Architecture Modeling and Analysis Language (AMAL)’ that homogenizes the framework development process in a formal way. AMAL is a radical approach that enables framework development based on custom requirements or by integrating existing heterogeneous architectural paradigms. The Open Semantics Framework in AMAL facilitates domain knowledge integration and promotes separation of concerns to build complex systems. We also position our approach in the SafeRobots framework, a model-driven software development tool-chain for robotics.

In a typical Human-Machine Interaction (HMI) system, a task is performed by cooperation of the human and the automation component. The system adopts a cognitive architecture to model human psychology and makes optimum decisions on dynamic task allocation between human and the machine counterpart depending on the context. However, such architectures do not define how those systems are implemented in software. Various models involved in Model Driven Software Development (MDSD) approach in developing HMI systems is presented. This paper proposes a metamodel for modeling Non-Functional Properties (NFP) in HMI systems and provides a case study on assistive lane keeping in automobiles to demonstrate the approach.Categories and Subject DescriptorsI.6 [SIMULATION AND MODELING]: Model Development— Modeling methodologies; H.1.2 [User/Machine Systems]: Human factors

Robotics is moving towards real world applications, beyond the well-structured environment of industrial robotics. In the world of assistant robots and medical robots, Human-Robot Interaction is essential. Also in emerging industrial scenarios there is a need of the human to be closely included in the loop. The companies are confronted with the lack of guidelines and of standards on how the higher features of HRI may be safely incorporated. Although the scientific research is burgeoning and worthy of praise, it is clear that its results are scattered and not capable of giving a clear input to be easily taken up by companies and standardization organizations like ISO and IEC. The workshop aims at the integration of empirical findings into complex real world robot systems by focusing on three typical sectors (industrial, service and medical) to develop systematic approaches to benchmark and evaluate experimental systems so that normative results can be realized rapidly. The present workshop focuses on bringing together scientists, representative of robotics companies and of standardization working groups to foster discussion in the definition of experimental scenarios and protocols in HRI, so to be able to prime real world set-ups and help realize the robotic products of the future.

The recent trend toward developing a new generation of robots that are capable of moving and acting in human-centered environments, interacting with people, and participating in our daily lives has introduced the need for building robotic systems able to learn how to use their bodies to communicate and to react to their users in a social and engaging way. Social robots that interact with humans have thus become an important focus of robotics research.

International audience; Recently, there is an encouraging trend in adopting model-driven engineering approaches for software development in robotics research. In this paper, currently available model-driven techniques in robotics are analyzed with respect to the domain-specific requirements. A conceptual overview of our software development approach called 'Self Adaptive Framework for Robotic Systems (SafeRobots)' is explained and we also try to position our approach within this model ecosystem.

International audience; In human-human interaction, the process of communication can be established through three modalities: verbal, non-verbal (i.e., gestures), and/or para-verbal (i.e., prosody). The linguistic literature shows that the para-verbal and non-verbal cues are naturally aligned and synchronized, however the natural mechanism of this synchronization is still unexplored. The difficulty encountered during the coordination between prosody and metaphoric head-arm gestures concerns the conveyed meaning , the way of performing gestures with respect to prosodic characteristics, their relative temporal arrangement, and their coordinated organization in the phrasal structure of utterance. In this research, we focus on the mechanism of mapping between head-arm gestures and speech prosodic characteristics in order to generate an adaptive robot behavior to the interacting human's emotional state. Prosody patterns and the motion curves of head-arm gestures are aligned separately into parallel Hidden Markov Models (HMM). The mapping between speech and head-arm gestures is based on the Coupled Hidden Markov Models (CHMM), which could be seen as a multi-stream collection of HMM, characterizing the segmented prosody and head-arm gestures' data. An emotional state based audio-video database has been created for the validation of this study. The obtained results show the effectiveness of the proposed methodology.

International audience; Several decision making algorithms that are developed in robotics domain are found to be useful in automotive industrial applications. In order to use these algorithms in safety critical embedded systems one has to ensure a minimum confidence level, quality assurance, and reliability. In addition, decision algorithms are designed and developed by domain experts and system integrators do not have control over the performance of low level components. Hence, there is a compelling need for a scalable framework, which accelerates the system integration and at the same time is conform to safety levels. This position paper presents a Quality of Service (QoS) based component architecture so as to address this problem. Our approach introduces a component model that segregates the functional and non-functional aspects of decision making.

International audience; A good adjustable control system is a system that can adapt its behaviors according to the user's state over time. While most researches in Human-Robot Cooperation focus on making the robotic system more efficient and effective in task accomplishment, we argue that very few works tried to model the human operator. In this paper, we discuss several aspects related to the human operator that we consider important for an efficient Human-Robot Cooperation. Furthermore, we present a tentative architecture of an adjustable control system, where these aspects are emphasized.

International audience; In human-robot interaction, a social intelligent robot should be capable of understanding the emotional internal state of the interacting human so as to behave in a proper manner. The main problem towards this approach is that human internal states can't be totally trained on, so the robot should be able to learn and classify emotional states online. This research paper focuses on developing a novel online incremental learning of human emotional states using Takagi-Sugeno (TS) fuzzy model. When new data is present, a decisive criterion decides if the new elements constitute a new cluster or if they confirm one of the previously existing clusters. If the new data is attributed to an existing cluster, the evolving fuzzy rules of the TS model may be updated whether by adding a new rule or by modifying existing rules according to the descriptive potential of the new data elements with respect to the entire existing cluster centers. However, if a new cluster is formed, a corresponding new TS fuzzy model is created and then updated when new data elements get attributed to it. The subtractive clustering algorithm is used to calculate the cluster centers that present the rules of the TS models. Experimental results show the effectiveness of the proposed method.

International audience; We present a mobile robot whose goal is to autonomously explore an unknown indoor environment and to build a semantic map containing high-level information similar to those extracted by humans. This information includes the rooms, their connectivity, the objects they contain and the material of the walls and ground. This robot was developed in order to participate in a French exploration and mapping contest called CAROTTE whose goal is to produce easily interpretable maps of an unknown environment. In particular we present our object detection approach based on a color+depth camera that fuse 3D, color and texture information through a neural network for robust object recognition. We also present the material recognition approach based on machine learning applied to vision. We demonstrate the performances of these modules on image databases and provide examples on the full system working in real environments.

International audience; The human perception of the external world appears as a natural, immediate and effortless task. It is achieved through a number of "low-level" sensory-motor processes that provide a high-level representation adapted to complex reasoning and decision. Compared to these representations, mobile robots usually provide only low-level obstacle maps that lack such high- level information. We present a mobile robot whose goal is to autonomously explore an unknown indoor environment and to build a semantic map containing high-level information similar to those extracted by humans and that will be rapidly and easily interpreted by users to assess the situation. This robot was developed under the1 Panoramic and Active Camera for Object Mapping (PACOM) project whose goal is to participate2 in a French exploration and mapping contest called CAROTTE . We will detail in particular how we integrated visual object recognition, room detection, semantic mapping, and exploration. We demonstrate the performances of our system in an indoor environment.

In human-robot interaction, gender and internal state detection play an important role in making the robot reacting in an appropriate manner. This research focuses on the important features to extract from a voice signal in order to construct successful gender and internal state detection systems, and shows the benefits of combining both systems together on the total average recognition score. Moreover, it consists a foundation on an ongoing approach to estimate the human internal state online via unsupervised clustering algorithms.

In this paper, we present the first steps towards a new concept of robot self-awareness that can be implemented into embodied robot systems. Our concept of "the self" is inspired by already existing approaches and aims to provide a cognitive system with meta-cognitive capabilities. We believe that robot self-awareness is a crucial factor in the improvement of HRI.

This paper addresses gait analysis for a mobility assistance robot designed for the elderly people. Six patients and ten healthy peoples were invited to be part of our first pilot experiment. We designed two experiments so as to firstly detect gait parameters and secondly to identify a change of speed. For the first trial, we compared the temporal-distance parameters of the healthy people and of individuals suffering of mobility problems. The percentages of the gait cycle for duration of stance are higher for people with mobility impairment than for healthy people. In the second experiment, we detected the change in walking speed from the ten healthy peoples. Two different metrics derived from the Kullback-Leibler (KL) divergence and from the Generalized Likelihood Ratio (GLR) were employed for walking change detection. The Receiver Operating Characteristic (ROC) curves show a better performance for the signal obtained with the accelerometer sensor than that obtained with the infrared distance sensor. Nevertheless, the results of our experiments demonstrated that both methodologies (KL and GLR) can be used to detect the change points during walking at high or slow speed.

International audience; Human-robot interaction (HRI) takes place espe-cially through interfaces. The design of such interfaces is avery delicate and crucial phase because it influences the robotaccessibility and usability by the user. In this paper, we describeand analyze the results of 2 tests conducted so as to understandsome of the optimal features that should characterize the robotvoice and graphical-based user interfaces. Our test platform isan assistive robot developed for the elderly with mild cognitiveimpairments. Therefore, the user interfaces must be clear andsimple. The ambiguities must be eliminated so as to facilitatethe use of the robot and hence not to discourage the elderlypopulation to use new technologies.

Currently the 2 percent growth rate for the world's older population exceeds the 1.2 rate for the world's population as a whole. By 2050, the number of individuals over the age 85 is projected to be three times more than there is today. Most of these individuals will need physical, emotional, and cognitive assistance. In this paper, we present a new adaptive robotic system based on the socially assistive robotics (SAR) technology that tries to provide a customized help protocol through motivation, encouragements, and companionship to users suffering from cognitive changes related to aging and/or Alzheimer's disease. Our results show that this approach can engage the patients and keep them interested in interacting with the robot, which, in turn, increases their positive behavior.

Currently the 2 percent growth rate for the world's older population exceeds the 1.2 percent rate for the world's population as a whole. This difference is expected to increase rather than diminish so that by 2050, the number of individuals over the age 85 is projected to be three times what it is today. Most of these individuals will need physical, emotional, and cognitive assistance. In this paper, we present a new system based on the socially assistive robotics (SAR) technology that will play the role of a music therapist and will try to provide a customized help protocol through motivation, encouragements, and companionship to users suffering from cognitive changes related to aging and/or Alzheimer's disease.

This paper presents a vision-based approach for mobile robot localization. The model of the environment is topological. The new approach characterize a place using a signature. This signature consists of a constellation of descriptors computed over different types of local affine covariant regions extracted from an omnidirectional image acquired rotating a standard camera with a pan-tilt unit. This type of representation permits a reliable and distinctive environment modeling. Our objectives were to validate the proposed method in indoor environments and, also, to find out if the combination of complementary local feature region detectors improves the localization versus using a single region detector. Our experimental results show that if false matches are efectively rejected, the combination of different covariant affine region detectors increases notably the performance of the approach by combining the different strengths of the individual detectors. In order to reduce the localization time, two strategies are evaluated: re-ranking the map nodes using a global similarity measure and using standard perspective view eld of 45 º. In order to systematically test topological localization methods, another contribution proposed in this work is a novel method to see the degradation in localization performance as the robot moves away from the point where the original signature was acquired. This allows to know the robustness of the proposed signature. In order for this to be effective, it must be done in several, variated, environments that test all the possible situations in which the robot may have to perform localization., This work was partially supported by the FI grant from the Generalitat de Catalunya, the European Social Fund, and the MID-CBR project grant TIN2006-15140- C03-01 and FEDER funds and the grant 2005-SGR-00093 and the MIPRCV Consolider Imagennio 2010.

IEEE International Conference on Robotics and Automation (ICRA 2008, Pasadena, California, May 19-23, 2008), pp. 538-543., This paper presents a vision-based approach for mobile robot localization. The environmental model is topological. The new approach uses a constellation of different types of affine covariant regions to characterize a place. This type of representation permits a reliable and distinctive environment modeling. The performance of the proposed approach is evaluated using a database of panoramic images from different rooms. Additionally, we compare different combinations of complementary feature region detectors to find the one that achieves the best results. Our experimental results show promising results for this new localization method. Additionally, similarly to what happens with single detectors, different combinations exhibit different strengths and weaknesses depending on the situation, suggesting that a context-aware method to combine the different detectors would improve the localization results., This work was partially supported by USC Women in Science and Engineering (WiSE), the FI grant from the Generalitat de Catalunya, the European Social Fund, and the MID-CBR project grant TIN2006-15140-C03-01 and FEDER funds and the grant 2005-SGR-00093.

Environment representation and situation awareness are key issue for personal and service robotics. Recent research in mobile robotics mainly concentrated on environment representations for efficient and robust navigation (e.g. Simultaneous Localization and Mapping). However, personal robots need competences that go beyond navigation and thus environment representations that include relationships and semantics of objects. Only this will enable personal robots to reason about the environment and develop cognitive competencies.

Proceedings. 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), October 27-31, 2003, Las Vegas, Nevada, ISBN:0-7803-7861-X, ISBN:0-7803-7860-1

Navigation in unknown or partially unknown environments remains one of the biggest challenges in today\'s mobile robotics. Environmental modeling, perception, localization and mapping are all needed for a successful approach. The contribution of this paper resides in the extension of the fingerprint concept (circular list of features around the robot) with uncertainty modeling, in order to improve localization and allow for automatic map building. The uncertainty is defined as the probability of a feature of being present in the environment when the robot perceives it. The whole approach is presented in details and viewed in a topological optic. Experimental results of the perception and localization capabilities with a mobile robot equipped with two 180° laser range finders and an omni-directional camera are reported.

In visual-based robot navigation, panoramic vision emerges as a very attractive candidate for solving the localization task. Unfortunately, current systems rely on specific feature selection processes that do not cover the requirements of general purpose robots. In order to fulfill new requirements of robot versatility and robustness to environmental changes, we propose in this paper to perform the feature selection of a panoramic vision system by means of the saliency-based model of visual attention, a model known for its universality. The first part of the paper describes a localization system combining panoramic vision and visual attention. The second part presents a series of indoor localization experiments using panoramic vision and attention guided feature detection. The results show the feasibility of the approach and illustrate some of its capabilities.

Even today, robot mapping is one of the biggest challenges in mobile robotics. Geometric or topological maps can be used by a robot to navigate in the environment. Automatic creation of such maps is still problematic if the robot tries to map large environments. This paper presents a new method for incremental mapping using fingerprints of places. This type of representation permits a reliable, compact, and distinctive environment-modeling and makes navigation and localization easier for the robot. Experimental results for incremental mapping using a mobile robot equipped with a multi-sensor system composed of two 180/spl deg/ laser range finders and an omni-directional camera are also reported.

This paper addresses the problem of perception and representation of space for a mobile agent. A probabilistic hierarchical framework is suggested as a solution to this problem. The method proposed is a combination of probabilistic belief with “Object Graph Models” (OGM). The world is viewed from a topological optic, in terms of objects and relationships between them. The hierarchical representation that we propose permits an efficient and reliable modeling of the information that the mobile agent would perceive from its environment. The integration of both navigational and interactional capabilities through efficient representation is also addressed. Experiments on a set of images taken from the real world that validate the approach are reported. This framework draws on the general understanding of human cognition and perception and contributes towards the overall efforts to build cognitive robot companions.