For mobile robots to operate in an autonomous and safe manner they must be able to adequately perceive their environment despite challenging or unpredictable conditions in their sensory apparatus. Usually, this is addressed through ad-hoc, not easily generalizable Fault Detection and Diagnosis (FDD) approaches. In this work, we leverage Bayesian Networks (BNs) to propose a novel probabilistic inference architecture that provides generality, rigorous inferences and real-time performance for the detection, diagnosis and recovery of diverse and multiple sensory failures in robotic systems. Our proposal achieves all these goals by structuring a BN in a multidimensional setting that up to our knowledge deals coherently and rigorously for the first time with the following issues: modeling of complex interactions among the components of the system, including sensors, anomaly detection and recovery; representation of sensory information and other kinds of knowledge at different levels of cognitive abstraction; and management of the temporal evolution of sensory behavior. Real-time performance is achieved through the compilation of these BNs into feedforward neural networks. Our proposal has been implemented and tested for mobile robot navigation in environments with human presence, a complex task that involves diverse sensor anomalies. The results obtained from both simulated and real experiments prove that our architecture enhances the safety and robustness of robotic operation: among others, the minimum distance to pedestrians, the tracking time and the navigation time all improve statistically in the presence of anomalies, with a diversity of changes in medians ranging from ≃20% to ≃500%.

In this paper we defend the superior scalability of the Relative Bundle Adjustment (RBA) framework for tackling with the SLAM problem. Although such a statement was already done with the introduction of the sliding window (SW) solution to RBA [16], we claim that the map extension that can be maintained locally consistent for some fixed computational cost critically depends on the specific pattern in which new keyframes are connected to previous ones. By rethinking from scratch what we call loop closures in relative coordinates we will show the unexploited flexibility of the RBA framework, which allows us a continuum of strategies from pure relative BA to hybrid submapping with local maps. In this work we derive a systematic way of constructing the problem graph which lies close to submapping and which generates graphs that can be solved more efficiently than those built as previously reported in the literature. As a necessary tool we also present an algorithm for incrementally updating all the spanning-trees demanded by any efficient solution to RBA. Under weak assumptions on the map, and implemented on carefully designed data structures, it is demonstrated to run in bounded time, no matter how large the map becomes. We also present experiments with a synthetic dataset of 55K keyframes in a world of 4.3M landmarks. Our C++ implementation has been released as open source.

The most common criteria to determine data association rely on minimizing the squared Mahalanobis distance (SMD) between observations and predictions. We hold that the SMD is just a heuristic, while the alternative matching likelihood is the optimal statistic to be maximized. Thorough experiments undoubtedly confirm this idea, with false positive reductions of up to 16%.

Small computers used for assisting drivers (mostly in finding routes) have been growing in popularity in the past years. These systems are inherently interactive, but up to now this interaction is tackled under rather simple approaches. For example, current routing computer assistants consider only the shortest or the quickest route to a destination, although in certain situations it could be interesting for the driver to take into consideration other factors, such as the criminal rate, land value, or the beauty of the areas to be traversed. On the other hand, the interactive processes between the driver and the routing assistant are still very limited: They only enable the user to discard (or suggest) particular locations through a fixed set of names, i.e. street's names. This paper proposes a novel interactive mechanism for in-vehicle routing that uses topological information at different levels of detail and a multihierarchical representation of urban maps. These hierarchical representations permit the system not only to plan routes efficiently but also to report them at different levels in detail in a human-like set of symbols adapted to each user. This enhances the human–computer interaction during the routing process, increasing driver satisfaction. We illustrate our technique through a case of study in the city of Málaga (Spain). © 2010 Wiley Periodicals, Inc.

The lack of a parameterized observation model in robot localization using occupancy grids requires the application of sampling-based methods, or particle filters. This work addresses the problem of optimal Bayesian filtering for dynamic systems with observation models that cannot be approximated properly as any parameterized distribution, which includes localization and SLAM with occupancy grids. By integrating ideas from previous works on adaptive sample size, auxiliary particle filters, and rejection sampling, we derive a new particle filter algorithm that enables the usage of the optimal proposal distribution to estimate the true posterior density of a non-parametric dynamic system. Our solution avoids approximations adopted in previous approaches at the cost of a higher computational burden. We present simulations and experimental results for a real robot showing the suitability of the method for localization.

Range-only SLAM (RO-SLAM) represents a difficult problem due to the inherent ambiguity of localizing either the robot or the beacons from distance measurements only. Most previous approaches to this problem employ non-probabilistic batch optimizations or delay the initialization of new beacons within a probabilistic filter until a good estimate is available. The contribution of this work is the formulation of RO-SLAM as an online Bayesian estimation process based on a Rao-Blackwellized particle filter. The conditional distribution for each beacon is initialized using an additional particle filter which, eventually, is transformed into an extended Kalman filter when the uncertainty becomes sufficiently small. This approach allows the introduction of new beacons without either delay or any special non-probabilistic processing. We validate our proposal with experiments for both simulated and real datasets.

This work addresses range-only SLAM (RO-SLAM) as the Bayesian inference problem of sequentially tracking a vehicle while estimating the location of a set of beacons without any prior information. The only assumptions are the availability of odometry and a range sensor able of identifying the different beacons. We propose exploiting the conditional independence between the position distributions of each beacon within a Rao-Blackwellized Particle Filter (RBPF) for maintaining independent Sum of Gaussians (SOGs) for each beacon. Unlike other approaches, it is shown then that a proper probabilistic observation model can be derived for online operation with no need for delayed initializations. We provide a rigorous statistical comparison of this proposal with previous work of the authors where a Monte-Carlo approximation was employed instead for the conditional densities. As verified experimentally, this new proposal represents a significant improvement in accuracy, computation time, and robustness against outliers.

This paper introduces a new approach to simultaneous localization and mapping (SLAM) that pursues robustness and accuracy in large-scale environments. Like most successful works on SLAM, we use Bayesian filtering to provide a probabilistic estimation that can cope with uncertainty in the measurements, the robot pose, and the map. Our approach is based on the reconstruction of the robot path in a hybrid discrete-continuous state space, which naturally combines metric and topological maps. There are two fundamental characteristics that set this paper apart from previous ones: 1) the use of a unified Bayesian inference approach both for the metrical and the topological parts of the problem and 2) the analytical formulation of belief distributions over hybrid maps, which allows us to maintain the spatial uncertainty in large spaces more accurately and efficiently than in previous works. We also describe a practical implementation that aims for real-time operation. Our ideas have been validated by promising experimental results in large environments (up to 30 000 m$^2$, a 2 km robot path) with multiple nested loops, which could hardly be managed appropriately by other approaches.

To date, no solution has been proposed to human-machine interactive task planning that deals simultaneously with two important issues: 1) the capability of processing large amounts of information in planning (as it is needed in any real application) and 2) being efficient in human-machine communication (a proper set of symbols for human-machine interaction may not be suitable for efficient automatic planning and vice versa). In this paper, we formalize a symbolic model of the environment to solve these issues in a natural form through a human-inspired mechanism that structures knowledge in multiple hierarchies. Planning with a hierarchical model may be efficient even in cases where the lack of hierarchical information would make it intractable. However, in addition, our multihierarchical model is able to use the symbols that are most familiar to each human user for interaction, thus achieving efficiency in human-machine communication without compromising the task-planning performance. We formalize here a general interactive task-planning process which is then particularized to be applied to a mobile robotic application. The suitability of our approach has been demonstrated with examples and experiments.

Most successful works in simultaneous localization and mapping (SLAM) aim to build a metric map under a probabilistic viewpoint employing Bayesian filtering techniques. This work introduces a new hybrid metric-topological approach, where the aim is to reconstruct the path of the robot in a hybrid continuous-discrete state space which naturally combines metric and topological maps. Our fundamental contributions are: (i) the estimation of the topological path, an improvement similar to that of Rao-Blackwellized particle filters (RBPF) and FastSLAM in the field of metric map building; and (ii) the application of grounded methods to the abstraction of topology (including loop closure) from raw sensor readings. It is remarkable that our approach could be still represented as a Bayesian inference problem, becoming an extension of purely metric SLAM. Besides providing the formal definitions and the basics for our approach, we also describe a practical implementation aimed to real-time operation. Promising experimental results mapping large environments with multiple nested loops (~30.000 m2, ~2Km robot path) validate our work.

One of the main elements of probabilistic localization and SLAM is the probabilistic sensor model (also known as the observation likelihood function). However, when dealing with very accurate sensors like laser range scanners, most approaches artificially inflate the uncertainty in the range measurements and assume conditional independence between the individual ranges of the scan to compute this likelihood function. In this paper we propose an alternative method where each sample in the scan can contribute an accurate estimation according to both its real uncertainty and its compatible correspondences with a given map. These likelihood values of individual measurements are fused via a linear opinion pool (LOP), a method from consensus theory. Our approach results in a more precise likelihood function than others and excels in robustness in dynamic environments. To validate our research we provide systematic comparisons with other proposals in the context of localization with particle filters.

The use of the World Wide Web for robot teleoperation is growing in the last years due mainly to the pervasiveness of Internet and Web browsers, although Web interfaces usually use Ethernet networks that exhibit time unpredictability. Most recent research in the area has been focused on improving time predictability of the network under delays, jitter, and no guaranteed bandwidth. However, we believe that: i) not only the network, but every component in the interfaced system exhibit time unpredictability; and ii) improving time predictability is not the only solution: adapting the interfaced system to unpredictable conditions is also a possibility. In this paper we consider a Web interfaced robot as a set of control loops and describe and implement a hysteresis controller for regulating the flow of information through the loops as a method to satisfy the system time requirements under some unpredictable and varying conditions. For demonstrating the goodness of our algorithm, we: a) compare it with a near-optimal one automatically generated through reinforcement learning, and b) show an implementation of the algorithm for the direct teleoperation of a service mobile robot, obtaining a better behavior than the same system without flow regulation.

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.

Recently, hybrid maps that combine metric and topological world information have been proposed as a powerful representation of mobile robot environments. Among others, these maps are of special interest for efficiently managing large-scale environments, and for accurate localization. For achieving that, local geometric maps are stored in the nodes of a graph-based global map. In this paper we present a novel approach for automatically obtaining those local maps from observations. The method considers the space sensed in each observation as a node of a graph with arcs representing the space overlap between observations. The recursive partition (cut) of this graph produces groups of strongly connected nodes from which consistent local maps for accurate localization are derived. The proposed partition technique is well-grounded in the spectral graph theory of, and it is formulated for any type of sensor observation. We depict an implementation for grouping 2D laser scans, and show experimental results with real data that demonstrate the performance of the method

In Bayesian based approaches to mobile robot simultaneous localization and mapping, Rao-Blackwellized particle filters (RBPF) enable the efficient estimation of the posterior belief over robot poses and the map. These particle filters have been recently adopted by many exploration approaches, to whom a central issue is measuring the certainty inherent to a given estimation in order to be able to select robot actions that increase it. In this paper we propose a new certainty measurement grounded in information theory that unifies the two kinds of uncertainty which are intrinsic to SLAM: in the robot pose and in the map content. Most previous works have considered only one of them or a weighted average. Our method combines them more appropriately by first building an expected map (EM) which condenses all the current map hypotheses and then computing its mean information (MI) - an entropy derived measurement that quantifies the inconsistencies in the EM. Experimental results comparing our method (EMMI) with others verify its correctness and its better behavior for detecting the decrease in certainty when the robot enters unexplored areas and its increase after closing a loop

The reactive navigation of a non-holonomic mobile robot implies selecting at each instant of time a motion command satisfying two conditions: to avoid collisions and to comply with the robot non-holonomic constraints. Most proposed reactive navigation approaches deal with these requirements simultaneously in an indivisible way. This paper proposes a clear separation of these problems by introducing a representation space where a robot losses its kinematics restrictions and can be dealt as a "free-flying-point." The collision avoidance can therefore be solved by existing holonomic methods, which are able to steer non-holonomic, any-shaped robots when applied in this space, named the trajectory parameter space (TP-space). We also formalize the transformation between this space and the robot physical space introducing the parameterized trajectory generator (PTG), a translation between both spaces by means of a family of parameterized trajectories. This formalization is addressed in a generalized form to allow us deriving any number of different transformations. Unlike previous non-holonomic approaches that use just one single transformation, the proposed method considers a variety of them simultaneously which becomes an obvious improvement to reactive approaches: each one can detect a collision-free path that the others can not. We present some experimental results to show the suitability of our method and its advantages compared with traditional approaches

Completely autonomous performance of a mobile robot within noncontrolled and dynamic environments is not possible yet due to different reasons including environment uncertainty, sensor/software robustness, limited robotic abilities, etc. But in assistant applications in which a human is always present, she/he can make up for the lack of robot autonomy by helping it when needed. In this paper, the authors propose human-robot integration as a mechanism to augment/improve the robot autonomy in daily scenarios. Through the human-robot-integration concept, the authors take a further step in the typical human-robot relation, since they consider her/him as a constituent part of the human-robot system, which takes full advantage of the sum of their abilities. In order to materialize this human integration into the system, they present a control architecture, called architecture for human-robot integration, which enables her/him from a high decisional level, i.e., deliberating a plan, to a physical low level, i.e., opening a door. The presented control architecture has been implemented to test the human-robot integration on a real robotic application. In particular, several real experiences have been conducted on a robotic wheelchair aimed to provide mobility to elderly people.

Most research in networked robots that use Web interfaces for robot control has been focused recently on the network part, since Ethernet involves poor (unpredictable) time performance. However, we believe that the problem to be addressed is more general and should not be restricted only to communication engineering: the interfaced system as a whole should adapt to get the most from the user, from the connection, and from the robot, even when no strict performance is possible. For that purpose, this paper introduces a new architecture for Web remote operation of robots that exhibits a high degree of flexibility in its adaptation to each particular user (through modular, configurable JAVA applets), to the system time-varying performance (through probability-guided, run-time adaptation of control loops), and to the robot software architecture (the standard CORBA is assumed as its middleware). Our approach constitutes an initial step for adapting comprehensively to all the mentioned issues, hence permitting to be employed in very different scenarios: realtime control, telecare, remote surveillance, etc.

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.

Task planning in mobile robotics should be performed efficiently, due to real-time requirements of robot-environment interaction. Its computational efficiency depends both on the number of operators (actions the robot can perform without planning) and the size of the world states (descriptions of the world before and after the application of operators). Thus, in real robotic applications, where both components can be large, planning may turn inefficient, and even unsolvable. In the artificial intelligence (AI) literature on planning, little attention has been put into efficient management of large-scale world descriptions. In real large-scale situations, conventional AI planners (in spite of the most modern improvements) may consume intractable amounts of storage and computing time, due to the huge amount of information. This paper proposes a new approach to task planning called "hierarchical task planning through world abstraction" that, by hierarchically arranging the world representation, becomes a good complement of Stanford Research Institute Problem Solver-style planners, significantly improving their computational efficiency. Broadly speaking, our approach works by first solving the task-planning problem in a highly abstracted model of the environment of the robot, and then refines the solution under more detailed models, where irrelevant world elements can be ignored, due to the results previously obtained at abstracted levels. Among the different implementations that can be made with our general strategy, we describe two that use a graph-based hierarchical world representation named the "annotated and hierarchical" graph. We show experiments, as well as results of a mobile robot operating in a large-scale environment, that demonstrate an important improvement in the efficiency of our algorithms with respect to conventional (both hierarchical and nonhierarchical) planning and their nice integration with existing planners.

The use of hierarchical graph searching for finding paths in graphs is well known in the literature, providing better results than plain graph searching, with respect to computational costs, in many cases. This paper offers a step forward by including multiple hierarchies in a graph-based model. Such a multi-hierarchical model has the following advantages: First, a multiple hierarchy permits us to choose the best hierarchy to solve each search problem; second, when several search problems have to be solved, a multiple hierarchy provides the possibility of solving some of them simultaneously; and third, solutions to the search problems can be expressed in any of the hierarchies of the multiple hierarchy, which allows us to represent the information in the most suitable way for each specific purpose. In general, multiple hierarchies have proven to be a more adaptable model than single-hierarchy or non-hierarchical models. This paper formalizes the multi-hierarchical model, describes the techniques that have been designed for taking advantage of multiple hierarchies in a hierarchical path search, and presents some experiments and results on the performance of these techniques.