A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense 3-D maps obtained by using a correlation-based stereo system. Geometric matching in general is a difficult unsolved problem in computer vision. Fortunately, in many practical applications, some a priori knowledge exists which considerably simplifies the problem. In visual navigation, for example, the motion between successive positions is usually approximately known. From this initial estimate, our algorithm computes observer motion with very good precision, which is required for environment modeling (e.g., building a Digital Elevation Map). Objects are represented by a set of 3-D points, which are considered as the samples of a surface. No constraint is imposed on the form of the objects. The proposed algorithm is based on iteratively matching points in one set to the closest points in the other. A statistical method based on the distance distribution is used to deal with outliers, occlusion, appearance and disappearance, which allows us to do subset-subset matching. A least-squares technique is used to estimate 3-D motion from the point correspondences, which reduces the average distance between points in the two sets. Both synthetic and real data have been used to test the algorithm, and the results show that it is efficient and robust, and yields an accurate motion estimate.

A robot exploring an unknown environmentmay need to build a world model from sensor measurements. In order to integrate all the frames of sensor data, it is essential to align the data properly. An incremental approach has been typically used in the past, in which each local frame of data is aligned to a cumulative global model, and then merged to the model. Because different parts of the model are updated independently while there are errors in the registration, such an approachmay result in an inconsistent model. In this paper, we study the problem of consistent registration of multiple frames of measurements (range scans), together with the related issues of representation and manipulation of spatial uncertainties. Our approachistomaintain all the local frames of data as well as the relative spatial relationships between local frames. These spatial relationships are modeled as random variables and are derived from matching pairwise scans or from odometry. Then we formulat...

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.

Optical flow provides a constraint on the motion of a deformable model. We derive and solve a dynamic system incorporating flow as a hard constraint, producing a model-based least-squares optical flow solution. Our solution also ensures the constraint remains satisfied when combined with edge information, which helps combat tracking error accumulation. Constraint enforcement can be relaxed using a Kalman filter, which permits controlled constraint violations based on the noise present in the optical flow information, and enables optical flow and edge information to be combined more robustly and efficiently. We apply this framework to the estimation of face shape and motion using a 3D deformable face model. This model uses a small number of parameters to describe a rich variety of face shapes and facial expressions. We present experiments in extracting the shape and motion of a face from image sequences which validate the accuracy of the method. They also demonstrate that our treatment of optical flow as a hard constraint, as well as our use of a Kalman filter to reconcile these constraints with the uncertainty in the optical flow, are vital for improving the performance of our system. 1

We present a system that estimates the motion of a stereo head or a single moving camera based on video input. The system operates in real-time with low delay and the motion estimates are used for navigational purposes. The front end of the system is a feature tracker. Point features are matched between pairs of frames and linked into image trajectories at video rate. Robust estimates of the camera motion are then produced from the feature tracks using a geometric hypothesize-and-test architecture. This generates motion estimates from visual input alone. No prior knowledge of the scene nor the motion is necessary. The visual estimates can also be used in conjunction with information from other sources such as GPS, inertia sensors, wheel encoders, etc. The pose estimation method has been applied successfully to video from aerial, automotive and handheld platforms. We focus on results obtained with a stereo-head mounted on an autonomous ground vehicle. We give examples of camera trajectories estimated in real-time purely from images over previously unseen distances (600 meters) and periods of time. 1.

We describe a method for visual based robot navigation with a single omni-directional (catadioptric) camera. We show how omni-directional images can be used to generate the representations needed for two main navigation modalities: Topological Navigation and Visual Path Following. Topological Navigation relies on the robot’s qualitative global position, estimated from a set of omni-directional images obtained during a training stage (compressed using PCA). To deal with illumination changes, an eigenspace approximation to the Hausdorff measure is exploited. We present a method to transform omni-directional images to Bird’s Eye Views that correspond to scaled orthographic views of the ground plane. These images are used to locally control the orientation of the robot, through visual servoing. Visual Path Following is used to accurately control the robot along a prescribed trajectory, by using bird’s eye views to track landmarks on the ground plane. Due to the simplified geometry of these images, the robot’s pose can be estimated easily and used for accurate trajectory following. Omni-directional images facilitate landmark based navigation, since landmarks remain visible in all images, as opposed to a small field-of-view standard camera. Also, omni-directional images provide the means of having adequate representations to support both accurate or qualitative navigation. Results are described in the paper. 1.

This paper considers the problem of systematically exploring an unfamiliar environment in search of one or more recognizable targets. The proposed exploration algorithm is based on a novel representation of environments containing visual landmarks called the boundary place graph. This representation records the set of recognizable objects (landmarks) that are visible from the boundary of each configuration space obstacle. No metric information about the scene geometry is recorded nor are explicit prescriptions for moving between places stored. The exploration algorithm constructs the boundary place graph incrementally from sensor data. Once the robot has completely explored an environment, it can use the constructed representation to carry out further navigation tasks. In order to precisely characterize the set of environments in which this algorithm is expected to succeed, weprovide a necessary and sufficient condition under which the algorithm is guaranteed to discover all landmarks. This algorithm has been implemented on our mobile robot platform RJ, and results from these experiments are presented. Importantly, this research demonstrates that it is possible to design and implementprovably correct exploration and navigation algorithms that do not require global positioning systems or metric representations of the environment. Keywords--- exploration, navigation, mobile robots, landmarks I.

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.

This paper describes an integrated mobile robotic system dubbed the intelligent observer (IO). The IO is a mobile robot which moves through an environment (such as an office building or a factory) while autonomously observing moving targets selected by a human operator. The robot carries one or more cameras which allow it to track objects while at the same time sensing its own location. It interacts with a human user who issues task-level commands, such as indicating a target to track by clicking in a camera image. The user could be located far away from the observer itself, communicating with the robot over a network. As the IO performs its tasks, the system provides real-time visual feedback to the user. We have implemented a prototype of the IO which integrates basic versions of five major components: landmark detection, target tracking, motion planning, motion control, and user interface. We have performed initial experiments using this prototype, which demonstrate the successful i...

This paper deals with the problem of computing the motions of one or more robot observers in order to maintain visibility of one or several moving targets. The targets are assumed to move unpredictably, and the distribution of obstacles in the workspace is assumed to be known in advance. Our algorithm computes a motion strategy by maximizing the shortest distance to escape ---the shortest distance the target needs to move in order to escape the observer's visibility region. Three main points are discussed: 1) The design and implementation of a reactive planner; 2) the integration and testing of such a planner in a robot system which includes perceptual and control capabilities; 3) The design and simulation of a motion planner for the task of maintaining visibility of two targets using two mobile observers.