Search

Abstract: For a mobile robot to operate autonomously in real-world environments, it must have an effective control system and a navigation system capable of providing robust localization, path planning and path execution. In this paper we describe work investigating synergies between mapping and control systems. We have integrated development of a control system for navigating mobile robots and a robot SLAM system. The control system is hybrid in nature and tightly coupled with the SLAM system; it uses a combination of high and low level deliberative and reactive control processes to perform obstacle avoidance, exploration, global navigation and recharging, and draws upon the map learning and localization capabilities of the SLAM system. The effectiveness of this hybrid, multi-level approach was evaluated in the context of a delivery robot scenario. Over a period of two weeks the robot performed 1143 delivery tasks to 11 different locations with only one delivery failure (from which it recovered), travelled a total distance of more than 40 km, and recharged autonomously a total of 23 times. In this paper we describe the combined control and SLAM system and discuss insights gained from its successful application in a real-world context. [Copyright &y& Elsevier]

Abstract: This paper presents a System on Chip (SoC) for the path following task of autonomous non-holonomic mobile robots. The SoC consists of a parameterized Digital Fuzzy Logic Controller (DFLC) core and a flow control algorithm that runs under the Xilinx Microblaze soft processor core. The fuzzy controller supports a fuzzy path tracking algorithm introduced by the authors. The FPGA board hosting the SoC was attached to an actual differential-drive Pioneer 3-DX8 robot, which was used in field experiments in order to assess the overall performance of the tracking scheme. Moreover, quantization problems and limitations imposed by the system configuration are also discussed. [Copyright &y& Elsevier]

Abstract: In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by a cheap wide-angle stereo camera. Our approach divides the whole map into local sub-maps identified by the so-called fingerprints (vehicle poses). At the sub-map level (low level SLAM), 3D sequential mapping of natural landmarks and the robot location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (high level SLAM) based on fingerprints has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep the local consistency of the metric sub-maps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. Some experimental results for different large-scale outdoor environments are presented, showing an almost constant processing time. [Copyright &y& Elsevier]

Abstract: Cooperative control is a key issue for multirobot systems in many practical applications. In this paper, we address the problem of coordinating a set of mobile robots in the RoboCup soccer middle-size league. We show how the coordination problem that we face can be cast as a specific coalition formation problem, and we propose a distributed algorithm to efficiently solve it. Our approach is based on the distributed computation of a measure of satisfaction (called Agent Satisfaction) that each agent computes for each task. We detail how each agent computes the Agent Satisfaction by acquiring sensor perceptions through an omnidirectional vision system, extracting aggregated information from the acquired perception, and integrating such information with that communicated by the teammates. We empirically validate our approach in a simulated scenario and within RoboCup competitions. The experiments in the simulated scenario allow us to analyse the behaviour of the algorithm in different situations, while the use of the algorithm in real competitions validates the applicability of our approach to robotic platforms involved in a dynamic and complex scenario. [Copyright &y& Elsevier]

Abstract: We have been developing MKR (Muratec Keio Robot), an autonomous omni-directional mobile transfer robot system for hospital applications. This robot has a wagon truck to transfer luggage, important specimens, and other materials. This study proposes an obstacle collision avoidance technique for the wagon truck pulling robot which uses an omni-directional wheel system as a safe movement technology. Moreover, this paper proposes a method to reach the goal along a global path computed by path planning without colliding with static and dynamic obstacles. The method is based on virtual potential fields. Several modules with different prediction times are processed in parallel to change the robot response according to its relative velocity and position with respect to the obstacles. The virtual force calculated from each potential field is used to generate the velocity command. Some experiments were carried out to verify the performance of the proposed method. From the experimental results in a hospital it was confirmed that the robot can move along its global path, and reach the goal without colliding with static and moving obstacles. [Copyright &y& Elsevier]

Abstract: The precise positioning of robotic systems is of great interest particularly in mobile robots. In this context, the use of omnidirectional vision provides many advantages thanks to its wide field of view. This paper presents an image-based visual control to drive a mobile robot to a desired location, which is specified by a target image previously acquired. It exploits the properties of omnidirectional images to preserve the bearing information by using a 1D trifocal tensor. The main contribution of the paper is that the elements of the tensor are introduced directly in the control law and neither any a priori knowledge of the scene nor any auxiliary image are required. Our approach can be applied with any visual sensor obeying approximately a central projection model, presents good robustness to image noise, and avoids the problem of a short baseline by exploiting the information of three views. A sliding mode control law in a square system ensures stability and robustness for the closed loop. The good performance of the control system is proven via simulations and real world experiments with a hypercatadioptric imaging system. [Copyright &y& Elsevier]

Abstract: Two relevant issues in vision-based navigation are the field-of-view constraints of conventional cameras and the model and structure dependency of standard approaches. A good solution of these problems is the use of the homography model with omnidirectional vision. However, a plane of the scene will cover only a small part of the omnidirectional image, missing relevant information across the wide range field of view, which is the main advantage of omnidirectional sensors. The interest of this paper is in a new approach for computing multiple homographies from virtual planes using omnidirectional images and its application in an omnidirectional vision-based homing control scheme. The multiple homographies are robustly computed, from a set of point matches across two omnidirectional views, using a method that relies on virtual planes independently of the structure of the scene. The method takes advantage of the planar motion constraint of the platform and computes virtual vertical planes from the scene. The family of homographies is also constrained to be embedded in a three-dimensional linear subspace to improve numerical consistency. Simulations and real experiments are provided to evaluate our approach. [Copyright &y& Elsevier]

Abstract: We present a novel approach to estimating depth from single omnidirectional camera images by learning the relationship between visual features and range measurements available during a training phase. Our model not only yields the most likely distance to obstacles in all directions, but also the predictive uncertainties for these estimates. This information can be utilized by a mobile robot to build an occupancy grid map of the environment or to avoid obstacles during exploration—tasks that typically require dedicated proximity sensors such as laser range finders or sonars. We show in this paper how an omnidirectional camera can be used as an alternative to such range sensors. As the learning engine, we apply Gaussian processes, a nonparametric approach to function regression, as well as a recently developed extension for dealing with input-dependent noise. In practical experiments carried out in different indoor environments with a mobile robot equipped with an omnidirectional camera system, we demonstrate that our system is able to estimate range with an accuracy comparable to that of dedicated sensors based on sonar or infrared light. [Copyright &y& Elsevier]

Abstract: In recent years, it can be observed that there is a gradual increase in the number of researchers and projects involved with the development of omnidirectional vision systems for various applications. The primary factors, which contributed towards this positive trend, are the availability of inexpensive and high resolution vision sensors, robust and fast computers and the advantages of using such systems over perspective vision systems. In this paper, a novel variable multibaseline omnidirectional stereovision system is presented. The proposed algorithm is implemented on the GPU based on the Nvidia CUDA libraries and subsequently, this paper will provide details of the automatic baseline selection process. Finally, results of the multibaseline stereovision algorithm based on voxel voting will be illustrated and discussed. In addition, possible research directions suggested by this approach will also be discussed. [Copyright &y& Elsevier]

Abstract: This paper presents a control strategy for the coordination of multiple mobile robots. A combination of the virtual structure and path following approaches is used to derive the formation architecture. A formation controller is proposed for the kinematic model of two-degree-of-freedom unicycle-type mobile robots. The approach is then extended to consider the formation controller by taking into account the physical dimensions and dynamics of the robots. The controller is designed in such a way that the path derivative is left as a free input to synchronize the robot’s motion. Simulation results with three robots are included to show the performance of our control system. Finally, the theoretical results are experimentally validated on a multi-robot platform. [Copyright &y& Elsevier]

Abstract: Recent research on mobile robots has focused on locomotion in various environments. In this paper, a gait-generation algorithm for a mobile robot that can travel from the ground to a wall and climb vertical surfaces is proposed. The algorithm was inspired by a gecko lizard. Our gait planning was based on inverse kinematics using the Jacobian of the whole body, where the redundancy was solved by defining an object function for the gecko posture to avoid collisions with the surface. The optimal scalar factor for these two objects was obtained by defining a superior object function to minimize the angular acceleration of joints. The algorithm was verified through simulation of the gecko model travelling on given task paths and avoiding abnormal joint movements and collisions. [Copyright &y& Elsevier]

Abstract: The availability of efficient mapping systems to produce accurate representations of initially unknown environments is recognized as one of the main requirements for autonomous mobile robots. In this paper, we present an efficient mapping system that has been implemented on a mobile robot equipped with a laser range scanner. The system builds geometrical point-based maps of environments employing an information-based exploration strategy that determines the best observation positions by taking into account both the distance travelled and the information gathered. Our exploration strategy, being based on solid mathematical foundations, differs from many ad hoc exploration strategies proposed in literature. We present: (a) the theoretical aspects of the criterion for determining the best observation positions for a robot building a map, (b) the implementation of a mapping system that uses the proposed criterion, and (c) the experimental validation of our approach. [Copyright &y& Elsevier]

Abstract: Autonomous robots are leaving the laboratories to master new outdoor applications, and walking robots in particular have already shown their potential advantages in these environments, especially on a natural terrain. Gait generation is the key to success in the negotiation of natural terrain with legged robots; however, most of the algorithms devised for hexapods have been tested under laboratory conditions. This paper presents the development of crab and turning gaits for hexapod robots on a natural terrain characterized by containing uneven ground and forbidden zones. The gaits we have developed rely on two empirical rules that derive three control modules that have been tested both under simulation and by experiment. The geometrical model of the SILO-6 walking robot has been used for simulation purposes, while the real SILO-6 walking robot has been used in the experiments. This robot was built as a mobile platform for a sensory system to detect and locate antipersonnel landmines in humanitarian demining missions. [Copyright &y& Elsevier]

Abstract: Multi-robot sensor-based coverage path planning requires every point given in the workspace has to be covered at least by a sensor of a robot in the robot team. In this study, a novel algorithm was proposed for the sensor-based coverage of narrow environments by considering energy capacities of the robots. For this purpose, the environment was modeled by a Generalized Voronoi diagram-based graph to guarantee complete sensor-based coverage. Then, depending on the required arc set, a complete coverage route was created by using the Chinese Postman Problem or the Rural Postman Problem, and this route was partitioned among robots by considering energy capacities. Route partitioning was realized by modifying the Ulusoy partitioning algorithm which has polynomial complexity. This modification handles two different energy consumptions of mobile robots during sensor-based coverage, which was not considered before. The developed algorithm was coded in C++ and implemented on P3-DX mobile robots both in laboratory and in MobileSim simulation environments. It was shown that the convenient routes for energy constrained multi-robots could be generated by using the proposed algorithm in less than 1 s. [Copyright &y& Elsevier]

Abstract: In this work, we describe and evaluate a grasping mechanism that does not make use of any specific object prior knowledge. The mechanism makes use of second-order relations between visually extracted multi-modal 3D features provided by an early cognitive vision system. More specifically, the algorithm is based on two relations covering geometric information in terms of a co-planarity constraint as well as appearance based information in terms of co-occurrence of colour properties. We show that our algorithm, although making use of such rather simple constraints, is able to grasp objects with a reasonable success rate in rather complex environments (i.e., cluttered scenes with multiple objects). Moreover, we have embedded the algorithm within a cognitive system that allows for autonomous exploration and learning in different contexts. First, the system is able to perform long action sequences which, although the grasping attempts not being always successful, can recover from mistakes and more importantly, is able to evaluate the success of the grasps autonomously by haptic feedback (i.e., by a force torque sensor at the wrist and proprioceptive information about the distance of the gripper after a gasping attempt). Such labelled data is then used for improving the initially hard-wired algorithm by learning. Moreover, the grasping behaviour has been used in a cognitive system to trigger higher level processes such as object learning and learning of object specific grasping. [Copyright &y& Elsevier]

Abstract: This paper focuses on the problem of grasp stability and grasp quality analysis. An elegant way to evaluate the stability of a grasp is to model its wrench space. However, classical grasp quality measures suffer from several disadvantages, the main drawback being that they are not task related. Indeed, constructive approaches for approximating the wrench space including also task information have been rarely considered. This work presents an effective method for task-oriented grasp quality evaluation based on a novel grasp quality measure. We address the general case of multifingered grasps with point contacts with friction. The proposed approach is based on the concept of programming by demonstration and interactive teaching, wherein an expert user provides in a teaching phase a set of exemplar grasps appropriate for the task. Following this phase, a representation of task-related grasps is built. During task planning and execution, a grasp could be either submitted interactively for evaluation by a non-expert user or synthesized by an automatic planning system. Grasp quality is then assessed based on the proposed measure, which takes into account grasp stability along with its suitability for the task. To enable real-time evaluation of grasps, a fast algorithm for computing an approximation of the quality measure is also proposed. Finally, a local grasp optimization technique is described which can amend uncertainties arising in supplied grasps by non-expert users or assist in planning more valuable grasps in the neighborhood of candidate ones. The paper reports experiments performed in virtual reality with both an anthropomorphic virtual hand and a three-fingered robot hand. These experiments suggest the effectiveness and task relevance of the proposed grasp quality measure. [Copyright &y& Elsevier]

Abstract: This work addresses the task of active sensing, or information-seeking control of mobile sensor platforms. Formulation of a control objective in terms of information gain allows mobile sensors to be both autonomous and easily reconfigurable to include a variety of sensor and target models. Tracking a moving target using a camera mounted on a fixed-wing unmanned aircraft is considered, but the control formulation is not specific to this choice of sensor or estimation task. A control formulation is developed which minimizes the entropy of an estimate distribution over a receding horizon subject to stochastic non-linear models for both the target motion and sensors. Previous similar work has been restricted to either a stationary target, a horizon of length one, or Gaussian estimates. The prediction of conditional entropy is shown to be inherently complex, and a computationally efficient sequential Monte Carlo method is developed. The entropy prediction depends on this Monte Carlo method as well as a novel approach for entropy calculation in the context of particle filtering. These methods are verified through simulation and post-processing of experimental flight data. [Copyright &y& Elsevier]

Abstract: This paper describes an efficient and robust localization system for indoor mobile robots and AGVs. The system utilizes a sensor that measures bearings to artificial landmarks, and an efficient triangulation method. We present a calibration method for the system components and overcome typical problems for sensors of the mentioned type, which are localization in motion and incorrect identification of landmarks. The resulting localization system was tested on a mobile robot. It consumes less than 4% of a Pentium4 3.2 GHz processing power while providing an accurate and reliable localization result every 0.5 s. The system was successfully incorporated within a real mobile robot system which performs many other computational tasks in parallel. [Copyright &y& Elsevier]

Abstract: Standardized performance evaluation is uncommon in mobile robotics. Therefore, it is difficult to compare published results and estimate their value. This work aims at providing a basis for the evaluation and comparison of the mobility performance of wheeled, all-terrain robots with respect to terrainability. Precisely defined existing and novel metrics are proposed for this purpose. The utility of these metrics is shown by applying them in a comparison to a selection of rover suspension systems known from the literature. Appropriate models for evaluation of the performance are described as well as the validation of the metrics by means of experimental testing. The simulations reveal significant differences in performance between the rovers which is confirmed by the test results. The correlation of the performance in simulation and reality is highly satisfying and supports the applicability of the proposed metrics. [Copyright &y& Elsevier]

Abstract: A novel topological map representation as well as an online map construction approach is presented in this paper. By virtue of the topological map whose nodes are represented with the free beams of the laser range finder together with the visual scale-invariant features, the mobile robot can autonomously navigate in unknown, large-scale and indoor environments. Different from the traditional navigation methods that rely on precise global localization, the robot locates itself qualitatively by location recognition rather than calculating its global pose in the world reference frame. By combining the reactive navigational method, Beam Curvature Method (BCM), with the topological map, a smooth, real-time navigation without precise localization can be realized. [Copyright &y& Elsevier]

Abstract: This paper proposes a novel multi-component information-equalized extended strong tracking filtering (MIST) method for mobile robot global localization. The main contributions of this paper come into three aspects: (1) it is the first time that a strong tracking filter (STF) is introduced into the robotics domain and is extended to be suitable for fusing observations with arbitrarily time-varying dimensionality, based on the proposed extended orthogonality principle and the equivalent space transformation; (2) the information asymmetry problem is analyzed, and an information equalization method based on extracting and equalizing the information underlying the residuals between actual and predicted observations is proposed and integrated with the extended strong tracking filter (ESTF) so as to make it to be equally sensitive to the saltation and estimation-error in any dimension of the state space; (3) a probabilistic data association mechanism and the dynamic multiple component-filters evolving mechanism are proposed and combined with the information-equalized ESTF (IESTF), which results in the final form of the proposed MIST localization method. MIST uses multiple individual IESTFs (component filters) to track multiple probable pose hypotheses. The number of IESTFs is automatically tuned through merging, splitting, deletion and generation, so as to adapt to the time-varying multimodal posterior distribution of the estimated robot’s pose. The correctness of each hypothesis (tracked by an individual IESTF) is evaluated based on a probabilistic formulation. The effectiveness of the proposed MIST method has been validated by real robot experiments and compared with the performances of popular existing methods such as MHL and MCL, which shows that MIST has a definite robustness to sensor noises, the kidnapped robot problem, nonlinearity of the system, and symmetric environments, as well as a high convergence speed and computational efficiency. [Copyright &y& Elsevier]

Abstract: In this paper a novel stereo correspondence algorithm is presented. It incorporates many biologically and psychologically inspired features to an adaptive weighted sum of absolute differences (SAD) framework in order to determine the correct depth of a scene. In addition to ideas already exploited, such as the color information utilization, gestalt laws of proximity and similarity, new ones have been adopted. The presented algorithm introduces the use of circular support regions, the gestalt law of continuity as well as the psychophysically-based logarithmic response law. All the aforementioned perceptual tools act complementarily inside a straightforward computational algorithm applicable to robotic applications. The results of the algorithm have been evaluated and compared to those of similar algorithms. [Copyright &y& Elsevier]

Abstract: This paper presents an approach for tracking multiple persons on a mobile robot with a combination of colour and thermal vision sensors, using several new techniques. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is incorporated into the tracker. The paper presents a comprehensive, quantitative evaluation of the whole system and its different components using several real world data sets. [Copyright &y& Elsevier]

Abstract: Humans and robots need to exchange information if the objective is to achieve a task collaboratively. Two questions are considered in this paper: what and when to communicate. To answer these questions, we developed a human–robot communication framework which makes use of common probabilistic robotics representations. The data stored in the representation determines what to communicate, and probabilistic inference mechanisms determine when to communicate. One application domain of the framework is collaborative human–robot decision making: robots use decision theory to select actions based on perceptual information gathered from their sensors and human operators. In this paper, operators are regarded as remotely located, valuable information sources which need to be managed carefully. Robots decide when to query operators using Value-Of-Information theory, i.e. humans are only queried if the expected benefit of their observation exceeds the cost of obtaining it. This can be seen as a mechanism for adjustable autonomy whereby adjustments are triggered at run-time based on the uncertainty in the robots’ beliefs related to their task. This semi-autonomous system is demonstrated using a navigation task and evaluated by a user study. Participants navigated a robot in simulation using the proposed system and via classical teleoperation. Results show that our system has a number of advantages over teleoperation with respect to performance, operator workload, usability, and the users’ perception of the robot. We also show that despite these advantages, teleoperation may still be a preferable driving mode depending on the mission priorities. [Copyright &y& Elsevier]

Abstract: Local obstacle avoidance is a principle capability for mobile robots in unknown or partially known environment. A series of velocity space methods including the curvature velocity method (CVM), the lane curvature method (LCM) and the beam curvature method (BCM) formulate the local obstacle avoidance problem as one of constrained optimization in the velocity space by taking the physical constraints of the environment and the dynamics of the vehicle into account. We present a new local obstacle avoidance approach that combines the prediction model of collision with the improved BCM. Not only does this method inherit the quickness of BCM and the safety of LCM, but also the proposed prediction based BCM (PBCM) can be used to avoid moving obstacles in dynamic environments. [Copyright &y& Elsevier]

Abstract: Mobile robots operating in real and populated environments usually execute tasks that require accurate knowledge on their position. Monte Carlo Localization (MCL) algorithms have been successfully applied for laser range finders. However, vision-based approaches present several problems with occlusions, real-time operation, and environment modifications. In this article, an omnivision-based MCL algorithm that solves these drawbacks is presented. The algorithm works with a variable number of particles through the use of the Kullback–Leibler divergence (KLD). The measurement model is based on an omnidirectional camera with a fish-eye lens. This model uses a feature-based map of the environment and the feature extraction process makes it robust to occlusions and changes in the environment. Moreover, the algorithm is scalable and works in real-time. Results on tracking, global localization and kidnapped robot problem show the excellent performance of the localization system in a real environment. In addition, experiments under severe and continuous occlusions reflect the ability of the algorithm to localize the robot in crowded environments. [Copyright &y& Elsevier]

Abstract: Previous research has shown that sensor–motor tasks in mobile robotics applications can be modelled automatically, using NARMAX system identification, where the sensory perception of the robot is mapped to the desired motor commands using non-linear polynomial functions, resulting in a tight coupling between sensing and acting — the robot responds directly to the sensor stimuli without having internal states or memory. However, competences such as for instance sequences of actions, where actions depend on each other, require memory and thus a representation of state. In these cases a simple direct link between sensory perception and the motor commands may not be enough to accomplish the desired tasks. The contribution of this paper to knowledge is to show how fundamental, simple NARMAX models of behaviour can be used in a bootstrapping process to generate complex behaviours that were so far beyond reach. We argue that as the complexity of the task increases, it is important to estimate the current state of the robot and integrate this information into the system identification process. To achieve this we propose a novel method which relates distinctive locations in the environment to the state of the robot, using an unsupervised clustering algorithm. Once we estimate the current state of the robot accurately, we combine the state information with the perception of the robot through a bootstrapping method to generate more complex robot tasks: We obtain a polynomial model which models the complex task as a function of predefined low level sensor–motor controllers and raw sensory data. The proposed method has been used to teach Scitos G5 mobile robots a number of complex tasks, such as advanced obstacle avoidance, or complex route learning. [Copyright &y& Elsevier]

Abstract: Mobile robots are becoming more heavily used in environments where human involvement is limited, impossible, or dangerous. These robots perform some of the more laborious human tasks on Earth and throughout the solar system, simultaneously saving resources and offering automation. Higher levels of autonomy are also being sought in these applications, such as distributed exploration and mapping of unknown areas. Smaller, less expensive mobile robots are becoming more prevalent, which introduces unique challenges in terms of limited sensing accuracy and onboard computing resources. This paper presents a novel low-cost, limited-resource approach to autonomous multi-robot mapping and exploration in unstructured environments. Design and implementation details are presented, along with results from two planetary style environments. Results demonstrate that low-cost ($ 1250) mobile robots capable of simultaneous localization and mapping can be successfully constructed. The multi-robot system presented in this paper participated in the 2008 International Conference on Robotics and Automation (ICRA) Space Robotics Challenge, receiving two awards for successfully completing the ’Onto the Surface’ and ’Map the Environment’ events in a simulated planetary environment. This work demonstrates not only that such systems are possible, but also that this direction of research is important and needs attention. [Copyright &y& Elsevier]

Abstract: We consider the problems of a wheeled mobile robot navigation and guidance towards an unknown stationary or maneuvering target using range-only measurements. We propose and study several methods for navigation and guidance termed Equiangular Navigation Guidance (ENG) laws. We give mathematically rigorous analysis of the proposed guidance laws. The performance is confirmed with computer simulations and experiments with ActivMedia Pioneer 3-DX wheeled robots. [Copyright &y& Elsevier]

Abstract: In this paper, we present an approach for directing a mobile robot under real-world conditions into a target position by means of pointing poses only. Because one important objective of our work is the development of a low-cost platform, only monocular vision at web-cam level should be employed. Our previous approach presented in Gross et al. (2006) , Richarz et al. (2007) has been improved by several additional processing steps. Finally, a background subtraction technique and a histogram equalization have been integrated in the preprocessing stage to be able to work in environments with structured backgrounds and under variable lighting conditions. Furthermore, a discriminant analysis was used to find the most relevant input features for the pointing pose estimator. The contribution of this paper is, however, not only the presentation of an approach to estimating pointing poses in a demanding real-world scenario on a mobile robot, but also the detailed and evaluative comparison between different image-preprocessing techniques, alternative feature extraction methods, and several function approximators with the same set of test- and training data. Reasonable combinations of the different methods are tested, and for each component on the processing chain the effect on the accuracy of the target estimation is quantized. The approach presented in this paper has been implemented on the mobile interaction robot Horos to determine the performance and estimation accuracy under real-world conditions. Furthermore, we compared the accuracy of our approach with that of humans performing the same estimation task, and achieved very comparable results for the best estimator. [Copyright &y& Elsevier]

The localization of mobile systems with video data is a challenging field in robotic vision research. Apart from support technologies like a GPS, a self-sufficient visual system is desirable. We introduce a new heuristic approach to outdoor localization in a scenario with sparse visual data and without odometry readings. Localization is interpreted as an optimization problem, and a swarm-based optimization method is adapted and applied, remaining independent of the specific visual feature type. The new method obtains similar or better localization results in our experiments while requiring only two-thirds of the number of image comparisons, indicating an overall speed-up by 25%. [Copyright &y& Elsevier]

Abstract: The problem of representing the environment of a mobile robot has been studied intensively in the past. The predominant approaches for geometric representations are grid-based or line-based maps. In this paper, we consider sample-based maps which use the data points obtained by range scanners to represent the environment. The main advantage of this representation over the other techniques is that it is able to represent arbitrary structures and at the same time provide an arbitrary accuracy. However, range measurements come in large amounts and not every measurement necessarily contributes to the representation in the same way. We present a novel approach for calculating maximum-likelihood subsets of the data points by sub-sampling laser range data. In particular, our method applies a variant of the fuzzy -means algorithm to find a map that maximizes the likelihood of the original data. Experimental results with real data show that the resulting maps are better suited for robot localization than maps obtained with other sub-sampling techniques. [Copyright &y& Elsevier]

Abstract: One important design decision for the development of autonomously navigating mobile robots is the choice of the representation of the environment. This includes the question of which type of features should be used, or whether a dense representation such as occupancy grid maps is more appropriate. In this paper, we present an approach which performs SLAM using multiple representations of the environment simultaneously. It uses reinforcement to learn when to switch to an alternative representation method depending on the current observation. This allows the robot to update its pose and map estimate based on the representation that models the surrounding of the robot in the best way. The approach has been implemented on a real robot and evaluated in scenarios, in which a robot has to navigate in- and outdoors and therefore switches between a landmark-based representation and a dense grid map. In practical experiments, we demonstrate that our approach allows a robot to robustly map environments which cannot be adequately modeled by either of the individual representations. [Copyright &y& Elsevier]

Abstract: In this paper, floor-cleaning coverage performances of some domestic mobile robots are measured, analyzed and modeled. Results obtained in a reduced scenario show that floor-cleaning coverage is complete in all cases if the path-planning exploration algorithm has some random dependence. Additionally, the evolution of the area cleaned by the mobile robot expressed in a distance domain has an exponential shape that can be modeled with a single exponential where the amplitude defines the maximum cleaning-coverage achieved and the time-constant defines the dynamic evolution of the coverage. Both parameters are robot dependent and can be estimated if the area of the room is known and then floor-cleaning coverage can be predicted and over-cleaning minimized. [Copyright &y& Elsevier]

Abstract: An important competence for a mobile robot system is the ability to localize and perform context interpretation. This is required to perform basic navigation and to facilitate local specific services. Recent advances in vision have made this modality a viable alternative to the traditional range sensors, and visual place recognition algorithms emerged as a useful and widely applied tool for obtaining information about robot’s position. Several place recognition methods have been proposed using vision alone or combined with sonar and/or laser. This research calls for standard benchmark datasets for development, evaluation and comparison of solutions. To this end, this paper presents two carefully designed and annotated image databases augmented with an experimental procedure and extensive baseline evaluation. The databases were gathered in an uncontrolled indoor office environment using two mobile robots and a standard camera. The acquisition spanned across a time range of several months and different illumination and weather conditions. Thus, the databases are very well suited for evaluating the robustness of algorithms with respect to a broad range of variations, often occurring in real-world settings. We thoroughly assessed the databases with a purely appearance-based place recognition method based on support vector machines and two types of rich visual features (global and local). [Copyright &y& Elsevier]

Abstract: The kinematics of some mobile robots is described through a strictly invariant Jacobian matrix . This is the case for robots with three degrees of freedom and suitable omnidirectional wheels, and that for robots with conventional wheels and differential kinematics. This article proposes a calibration technique for the matrix of such robots. It is based on four accurate configuration measurements associated with particular nominal motions where the generalized velocities maintain a constant proportional relationship. As a consequence, the nominal trajectories are arcs of circumference and may be part of the actual trajectories of the robot. An application example is presented. [Copyright &y& Elsevier]

Abstract: In this paper a new cooperative collision-avoidance method for multiple, nonholonomic robots based on Bernstein–Bézier curves is presented. The main contribution focuses on an optimal, cooperative, collision avoidance for a multi-robot system where the velocities and accelerations of the mobile robots are constrained and the start and the goal velocity are defined for each robot. The optimal path of each robot, from the start pose to the goal pose, is obtained by minimizing the penalty function, which takes into account the sum of all the path lengths subjected to the distances between the robots, which should be larger than the minimum distance defined as the safety distance, and subjected to the velocities and accelerations, which should be lower than the maximum allowed for each robot. The model-predictive trajectory tracking is used to drive the robots on the obtained reference paths. The results of the path planning, real experiments and some future work ideas are discussed. [Copyright &y& Elsevier]

Abstract: This paper presents a decentralized motion planner for a team of nonholonomic mobile robots subject to constraints imposed by sensors and the communication network. The motion planning scheme consists of decentralized receding horizon planners that reside on each vehicle to achieve coordination among flocking agents. The advantage of the proposed algorithm is that each vehicle only requires local knowledge of its neighboring vehicles. The main requirement for designing an optimal conflict-free trajectory in a decentralized way is that each robot does not deviate too far from its presumed trajectory designed without taking the coupling constraints into account. A comparative study between the proposed algorithm and other existing algorithms is provided in order to show the advantages, especially in terms of computing time. Finally, experiments are performed on a team of three mobile robots to demonstrate the validity of the proposed approach. [Copyright &y& Elsevier]

Abstract: This paper presents empirical results of the effect of the global position information on the performance of the modified local navigation algorithm (MLNA) for unknown world exploration. The results show that global position information enables the algorithm to maintain 100% success rate irrespective of initial robot position, movement speed, and environment complexity. Most mobile robot systems accrue an odometry error while moving, and hence need to use external sensors to recalibrate their position on an ongoing basis. We deal with position calibration to compensate the odometry error using the global position information provided by the Teleworkbench, which is a teleoperated platform and test bed for managing experiments using mini-robots. In this paper we demonstrate how we incorporate the global position information during and after the experiments. [Copyright &y& Elsevier]

Abstract: In order to solve most of the existing mobile robotics applications, the robot needs some information about its spatial environment encoded in what it has been commonly called a map. The knowledge contained in such a map, whatever approach is used to obtain it, will mainly be used by the robot to gain the ability to navigate in a given environment. We are describing in this paper, a method that allows a robot or team of robots to navigate in large urban areas for which an existing map in a standard human understandable fashion is available. As detailed maps of most urban areas already exist, it will be assumed that a map of the zone where the robot is supposed to work is given, which has not been constructed using the robot’s own sensors. We propose in this paper, the use of an existing Geographical Information System based map of an urban zone so that a robot or a team of robots can connect to this map and use it for navigation purposes. Details of the implemented system architecture as well as a position tracking experiment in a real outdoor environment, a University Campus, are provided. [Copyright &y& Elsevier]

Abstract: Localization is a fundamental operation for the navigation of mobile robots. The standard localization algorithms fuse external measurements of the environment with the odometric evolution of the robot pose to obtain its optimal estimation. In this work, we present a different approach to determine the pose using angular measurements discontinuously obtained in time. The presented method is based on an Extended Kalman Filter (EKF) with a state-vector composed of the external angular measurements. This algorithm keeps track of the angles between actual measurements from robot odometric information. This continuous angular estimation allows the consistent use of the triangulation methods to determine the robot pose at any time during its motion. The article reports experimental results that show the localization accuracy obtained by means of the presented approach. These results are compared to the ones obtained applying the EKF algorithm with the standard pose state-vector. For the experiments, an omnidirectional robotic platform with omnidirectional wheels is used. [Copyright &y& Elsevier]

Abstract: Reactive-based approaches are widely used in autonomous navigation. However, in complex unknown environments, pure reactive-based navigation still poses a few challenges since it can be easily trapped by a local minimum and may produce some extra manoeuvres. This paper presents the design of a reactive-based approach for navigation in complex and unknown environments called sub goal seeking, in which depth point maps of the environment are analysed to extract free spaces around the robot. These spaces are then evaluated the one that is most likely to lead to the final goal is chosen as a sub goal. The robot then drives towards these sub goals, instead of the final goal until it is visible. By analysing the environmental structure, dead-ends within robot sensory range are able to be detected thus reducing the chance of being trapped and also reducing unnecessary manoeuvres. This paper also evaluates the performance of the sub goal seeking approach using three criteria, goal achievable ability, safety and maneuvering through extensive simulation and real mobile robot experiments. [Copyright &y& Elsevier]

Abstract: This paper presents a novel design of a robust visual tracking control system, which consists of a visual tracking controller and a visual state estimator. This system facilitates human–robot interaction of a unicycle-modeled mobile robot equipped with a tilt camera. Based on a novel dual-Jacobian visual interaction model, a robust visual tracking controller is proposed to track a dynamic moving target. The proposed controller not only possesses some degree of robustness against the system model uncertainties, but also tracks the target without its 3D velocity information. The visual state estimator aims to estimate the optimal system state and target image velocity, which is used by the visual tracking controller. To achieve this, a self-tuning Kalman filter is proposed to estimate interesting parameters and to overcome the temporary occlusion problem. Furthermore, because the proposed method is fully working in the image space, the computational complexity and the sensor/camera modeling errors can be reduced. Experimental results validate the effectiveness of the proposed method, in terms of tracking performance, system convergence, and robustness. [Copyright &y& Elsevier]

Abstract: Recent developments in sensor technology have made it feasible to use mobile robots in several fields, but robots still lack the ability to accurately sense the environment. A major challenge to the widespread deployment of mobile robots is the ability to function autonomously, learning useful models of environmental features, recognizing environmental changes, and adapting the learned models in response to such changes. This article focuses on such learning and adaptation in the context of color segmentation on mobile robots in the presence of illumination changes. The main contribution of this article is a survey of vision algorithms that are potentially applicable to color-based mobile robot vision. We therefore look at algorithms for color segmentation, color learning and illumination invariance on mobile robot platforms, including approaches that tackle just the underlying vision problems. Furthermore, we investigate how the inter-dependencies between these modules and high-level action planning can be exploited to achieve autonomous learning and adaptation. The goal is to determine the suitability of the state-of-the-art vision algorithms for mobile robot domains, and to identify the challenges that still need to be addressed to enable mobile robots to learn and adapt models for color, so as to operate autonomously in natural conditions. [Copyright &y& Elsevier]

Abstract: This work establishes the reference signal conditions for zero tracking error when controlling wheeled mobile robots under the kinematic framework, that is, when the low-level dynamics is neglected. The reference characterization is based on the classical decoupled robot control and the inverse kinematics of fixed, centered orientable, castor and Swedish wheels. Procedures to avoid tracking error when a particular condition is not satisfied are also indicated. Simulations are shown to illustrate the reference conditions for each type of mobile robot and their implications. Finally, an industrial forklift is considered in a real situation to validate the previous results and to highlight the limits of the kinematic framework assumption. [Copyright &y& Elsevier]

Abstract: Localization is one of the most important basic skills of a mobile robot. Most approaches, however, still rely either on special sensors or require artificial environments. In this article, a novel approach is presented that can provide compass information for localization, purely based on the visual appearance of a room. A robot using such a visual compass can quickly learn a cylindrical map of the environment, consisting of simple statistical features that can be computed very quickly. The visual compass algorithm is efficient, scalable and can therefore be used in real-time on almost any contemporary robotic platform. Extensive experiments on a Sony Aibo robot have validated that the approach works in a vast variety of environments. [Copyright &y& Elsevier]

Abstract: Tensegrity structures can provide a new approach to the construction of mobile robots with different shapes and properties that usual robots, wheeled or legged, do not have. Tensegrity are light, deformable structures that may be able to adapt their form to unconstrained environments. The main issue of this paper is twofold, first, to derive appropriate and general dynamic equations of motion to study the movement of such structures in the space; second to demonstrate, by means of simulation, that a tensegrity structure can execute any desired trajectory path by actuating some or all of its elements. [Copyright &y& Elsevier]

Abstract: This article addresses the problem of mobile robot localization using Ultra-Wide-Band (UWB) range measurements. UWB is a radio technology widely used for communications, that is recently receiving increasing attention for positioning applications. In these cases, the position of a mobile transceiver is determined from the distances to a set of fixed, well-localized beacons. Though this is a well-known problem in the scientific literature (the trilateration problem), the peculiarities of UWB range measurements (basically, distance errors and multipath effects) demand a different treatment to other similar solutions, as for example, those based on laser. This work presents a thorough experimental characterization of UWB ranges within a variety of environments and situations. From these experiments, we derive a probabilistic model which is then used by a particle filter to combine different readings from UWB beacons as well as the vehicle odometry. To account for the possible offset error due to multipath effects, the state tracked by the particle filter includes the offset of each beacon in addition to the planar robot pose , both estimated sequentially. We show navigation results for a robot moving in indoor scenarios covered by three UWB beacons that validate our proposal. [Copyright &y& Elsevier]

Abstract: The search for a simple and accurate odometry is a main concern when working with mobile robots. This article presents a general analysis of the problem and proposes a particular solution to improve the odometry. The three crucial kinematical aspects of mobile robots (mobility, control, and positioning) are reviewed in detail for vehicles based both in conventional and in omnidirectional wheels. The latter case is more suitable from a maneuvering point of view as it provides the robot frame with the three Degrees Of Freedom (DOF) of plane motion without singular configurations. Moreover, a suitable design of the omnidirectional wheels leads to a strictly invariant Jacobian matrix and thus to a linear control equation with constant coefficients. It is shown that such vehicles may have a holonomic behavior when moving under suitable kinematical restrictions without constraining their trajectory. In that case, the odometry is algebraic (instead of integrative) and thus more accurate. An application case is presented. [Copyright &y& Elsevier]

Abstract: In this research, we focus our discussion on the discontinuous dynamic behavior transition of a walking robot. For the transition, bifurcation of potential function is utilized. We demonstrate the behavior transition of the walking robot between biped and quadruped locomotion as an adaptation to the environment depending on the gradient of a slope. The behavior transition is carried out by using bifurcation of parameters used for control. We also show the effectiveness of hysteresis in the transition. [Copyright &y& Elsevier]