This paper surveys the developments of the last 20 years in the area of vision for mobile robot navigation. Two major components of the paper deal with indoor navigation and outdoor navigation. For each component, we have further subdivided our treatment of the subject on the basis of structured and unstructured environments. For indoor robots in structured environments, we have dealt separately with the cases of geometrical and topological models of space. For unstructured environments, we have discussed the cases of navigation using optical flows, using methods from the appearance-based paradigm, and by recognition of specific objects in the environment.

This paper proposes a method for the visual-based navigation of a mobile robot in indoor environments, using a single omni-directional (catadioptric) camera. The geometry of the catadioptric sensor and the method used to obtain a bird's eye (orthographic) view of the ground plane are presented. This representation significantly simplifies the so to navigation protiok by eliminating any perspective effects. The nature of each navigation task is taken into account when designing the required navigation skills and environmental representation. We propose two main navigation mo dalities: Topological Navigation and Visual Path Following. To po lok Navigatio is used fo traveling lo distances and do es no require knowledge of the exact position of the robot but rather, a qualitative position of the took map. The navigation process combines appearance based methods and visual servorv up oso environmental features. Visual Path Following is required for local, very precise navigation fo e.g.do o traversal,do cking. The robot is contro to fo w a pre-specified p...

. This paper presents fundamental theory and design of central panoramic cameras. Panoramic cameras combine a convex hyperbolic or parabolic mirror with a perspective camera to obtain a large field of view. We show how to design a panoramic camera with a tractable geometry and we propose a simple calibration method. We derive the image formation function for such a camera. The main contribution of the paper is the derivation of the epipolar geometry between a pair of panoramic cameras. We show that the mathematical model of a central panoramic camera can be decomposed into two central projections and therefore allows an epipolar geometry formulation. It is shown that epipolar curves are conics and their equations are derived. The theory is tested in experiments with real data. Keywords: omnidirectional vision, epipolar geometry, panoramic cameras, hyperbolic mirror, stereo, catadioptric sensors. 1 Introduction It is well known that egomotion estimation algorithms in some cases cannot ...

In homing tasks, the goal is often not marked by visible objects but must be inferred from the spatial relation to the visual cues in the surrounding scene. The exact computation of the goal direction would require knowledge about the distances to visible landmarks, information, which is not directly available to passive vision systems. However, if prior assumptions about typical distance distributions are used, a snapshot taken at the goal suffices to compute the goal direction from the current view. We show that most existing approaches to scene-based homing implicitly assume an isotropic landmark distribution. As an alternative, we propose a homing scheme that uses parameterized displacement fields. These are obtained from an approximation that incorporates prior knowledge about perspective distortions of the visual environment. A mathematical analysis proves that both approximations do not prevent the schemes from approaching the goal with arbitrary accuracy, but lead to different...

We present a purely vision-based scheme for learning a parsimonious representation of an open environment. Using simple exploration behaviours, our system constructs a graph of appropriately chosen views. To navigate between views connected in the graph, we employ a homing strategy inspired by findings of insect ethology. Simulations and robot experiments demonstrate the feasibility of the proposed approach. Introduction 1 To survive in unpredictable and sometimes hostile environments animals have developed powerful strategies to find back to their shelter or to a previously visited food source. Successful navigation can already be achieved using simple mechanisms such as association of landmarks with movements (Wehner et al. 1996) or tracking of environmental features (Collett 1996). To understand more complex forms of spatial behaviour like finding shortcuts, however, we have to go beyond reactive control strategies, towards systems with internal states. In as far as they ...

Abstract not found

In this paper, we present the two-dimensional (2-D) version of the symmetries and perturbation model (SPmodel), a probabilistic representation model and an EKF integration mechanism for uncertain geometric information that is suitable for sensor fusion and integration in multisensor systems. We apply the SPmodel to the problem of location estimation in indoor mobile robotics, experimenting with the mobile robot MACROBE. We have chosen two types of complementary sensory information: 1) range images; 2) intensity images; obtained from a laser sensor. Results of these experiments show that fusing simple and computationally inexpensive sensory information can allow a mobile robot to precisely locate itself. They also demonstrate the generality of the proposed fusion and integration mechanism.

We present a family of reflective surfaces that will provide a wide field of view while preserving the geometry of a plane perpendicular to their axis of symmetry. Used in conjunction with a conventional imaging device, these surfaces act as computational sensors, capable of providing unwarped images automatically, eliminating the need for further processing. These surfaces arise as solutions to a differential equation that contain a function which controls the planar distortion. We demonstrate how the differential equation can be altered to accommodate different models of imaging devices with which the surfaces may be coupled. Such sensors could be potentially useful in mobile robotics, with applications such as control and range estimation. 1 Introduction Recently, many researchers in the robotics and vision community have begun to consider visual sensors that are able to obtain panoramic and omnidirectional views. 1 Such devices are the natural solution to various difficulties e...

This contribution gives the foundations of the useful panoramic cameras for stereo vision. The approach to a perspective camera-hyperbolic mirror system design is presented. The model of image formation by a central panoramic camera is defined. The analysis of epipolar geometry for panoramic cameras is the main growth of this paper. We show that the panoramic cameras with convex hyperbolic or parabolic mirrors, central panoramic cameras, allow the epipolar geometry as perspective cameras do. It is shown that the epipolar curves in central panoramic images are conics and their equation is derived. A simple adjustment procedure of a perspective camera and a hyperbolic mirror in order to form a proper central panoramic camera is proposed. This research was primarily motivated by looking for an improvement of the motion estimation from a pair of images but the results are also applicable for structure reconstruction from panoramic stereo images. The theory is demonstrated by a...

Omnidirectional video cameras are becoming increasingly popular in computer vision. One family of these cameras uses a catadioptric system with a paraboloidal mirror and an orthographic lens to produce an omnidirectional image with a single center-ofprojection. In this paper, we develop a novel calibration model that we combine with a beacon-based pose estimation algorithm. Our approach relaxes the assumption of an ideal paraboloidal catadioptric system and achieves an order of magnitude improvement in pose estimation accuracy compared to calibration with an ideal camera model. Our complete standalone system, placed on a radio-controlled motorized cart, moves in a room-size environment, capturing high-resolution frames to disk and recovering camera pose with an average error of 0.56% in a region 15 feet in diameter.