This paper describes a system for structure-from-motion using vanishing points and three-dimensional lines extracted from omni-directional video sequences. Two novel aspects of this work are its deferred initialization of features using noisy observations from multiple, uncertain vantage points, and its use of dynamic programming for efficient 3D line tracking. We show preliminary results from the system for both indoor and outdoor sequences.

One of the most challenging aspects of concurrent mapping and localization (CML) is the problem of data association. Because of uncertainty in the origins of sensor measurements, it is difficult to determine the correspondence between measured data and features of the scene or object being observed, while rejecting spurious measurements. However, there are many important applications of mobile robots where maps need to be built of complex environments, consisting of composite features, from noisy sensor data. This paper reviews several new approaches to data association and feature modeling for CML that share the common theme of combining information from multiple uncertain vantage points while rejecting spurious data. Our results include: (1) feature-based mapping from laser data using robust segmentation, (2) map-building with sonar data using a novel application of the Hough transform for perception grouping, and (3) a new stochastic framework for making delayed decisions for combination of data from multiple uncertain vantage points. Experimental results are shown for CML using laser and sonar data from a B21 mobile robot.

This paper presents an algorithm for feature-based exploration of a priori unknown environments. We aim to build a robot that, unsupervised, plans its motion such that it continually increases both the spatial extent and detail of its world model - its map. We present a method by which the planned motion at any instant is motivated by the geometric, spatial and stochastic characteristics of the current map. In particular each feature within the map is responsible for determining nearby unexplored areas that if visited are likely to constitute exploration. We assume that the location of the features is uncertain and represented by a set of probability distribution functions (pdfs). These distributions are used in conjunction with the robot path history to determine a robot trajectory suited to exploration. We show results that demonstrate the algorithm providing real-time exploration of a mobile robot in an unknown environ- ment.

This paper reports on the development of a domestic user-interface robot that is able to have natural human interaction by speech and emotional feedback. Natural interaction with the user is achieved by means of a mechanical head able to express emotions. Additionally, our robot is aware not only of its position in the environment but also of the position and intentions of the users. The localization of the robot is achieved with an appearance-based localization method. To get information about the users, the robot is designed to operate in (and to cooperate with) an intelligent ambient that takes care of monitoring the users. The result is a service robot that departs from existing developments in the fields of interface and service robots that are mainly reactive and, thus, limited in functionality.

Reviewing the important problem of simultaneous localisation and map-building, we emphasise its genericity and in particular draw parallels between the often divided fields of computer vision and robot navigation. We compare sequential techniques with the batch methodologies currently prevalent in computer vision, and explain the additional challenges presented by real-time constraints which mean that there is still much work to be done in the sequential case, which when solved will lead to impressive and useful applications. In a detailed tutorial on map-building using first-order error propagation, particular attention is drawn to the roles of modelling and an active methodology. Finally, recognising the critical role of software in tackling a generic problem such as this, we announce the distribution of a proven and carefully designed open-source software framework which is intended for use in a wide range of robot and vision applications. 2001 Elsevier Science B.V. All rights reserved.

Abstract. Recent efforts in robust estimation of the two-view relation have focused on uncalibrated cameras with no prior knowledge of pose. However, in practice robotic vehicles that perform image-based navigation and mapping typically do carry a calibrated camera and pose sensors; this additional knowledge is currently not being exploited. This paper presents three contributions in using vision with instrumented and calibrated platforms. First, we improve the performace of the correspondence stage by using uncertain measurements from egomotion sensors to constrain possible matches. Second, we assume wide-baseline conditions and propose Zernike moments to describe affine invariant features. Third, we robustly estimate the essential matrix with a new 6-point algorithm. Our solution is simpler than the minimal 5-point one and, unlike the linear 6-point solution, does not fail on planar scenes. While the contributions are general, we present structure and motion results from an underwater robotic survey. 1

Abstract—In this paper we describe a system that can carry out SLAM in large indoor and outdoor environments using a stereo pair moving with 6DOF as the only sensor. Unlike current visual SLAM systems that use either bearing-only monocular information or 3D stereo information, our system accommodates both monocular and stereo. Textured point features are extracted from the images and stored as 3D points if seen in both images with sufficient disparity, or stored as inverse depth points otherwise. This allows the system to map both near and far features: the first provide distance and orientation, and the second orientation information. Unlike other vision only SLAM systems, stereo does not suffer from ’scale drift ’ because of unobservability problems, and thus no other information such as gyroscopes or accelerometers is required in our system. Our SLAM algorithm generates sequences of conditionally independent local maps that can share information related to the camera motion and common features being tracked. The system computes the full map using the novel Conditionally Independent Divide and Conquer algorithm, which allows constant time operation most of the time, with linear time updates to compute the full map. To demonstrate the robustness and scalability of our system, we show experimental results in indoor and outdoor urban environments of 210m and 140m loop trajectories, with the stereo camera being carried in hand by a person walking at normal walking speeds of 4 − 5km/hour.

Zoom lenses appear to fit very naturally into the framework of active vision --- controlling a zoom lens allows an adjustment of the image, enabling either an analysis of a wide scene or a close look at a region or object of particular interest. However, their integration into vision systems is not without difficulty since zoom interacts insidiously with both low and high level processes. This thesis concerns developing and analyzing algorithms that function in spite of zoom; algorithms for visual tracking, camera calibration and Euclidean reconstruction. An approach grounded in visual geometry is adopted, motivated by the notion that the geometric descriptions of point (corner) and line (straight edge) features are zoom-invariant.

A vision-based robot localization system must be robust: able to keep track of the position of the robot at any time even if illumination conditions change and, in the extreme case of a failure, able to efficiently recover the correct position of the robot. With this objective in mind, we enhance the existing appearance-based robot localization framework in two directions by exploiting the use of a stereo camera mounted on a pan-and-tilt device. First, we move from the classical passive appearance-based localization framework to an active one where the robot sometimes executes actions with the only purpose of gaining information about its location in the environment. Along this line, we introduce an entropy-based criterion for action selection that can be efficiently evaluated in our probabilistic localization system. The execution of the actions selected using this criterion allows the robot to quickly find out its position in case it gets lost. Secondly, we introduce the use of depth maps obtained with the stereo cameras. The information provided by depth maps is less sensitive to changes of illumination than that provided by plain images. The main drawback of depth maps is that they include missing values: points for which it is not possible to reliably determine depth information. The presence of missing values makes Principal Component Analysis (the standard method used to compress images in the appearance-based framework) unfeasible. We describe a novel Expectation-Maximization algorithm to determine the principal components of a data set including missing values and we apply it to depth maps. The experiments we present show that the combination of the active localization with the use of depth maps gives an efficient and robust appearance-based robot localization system.

o the requirements or the egre1!1 P 1 '1 r P l 1 r 1 1