Determination of relative three-dimensional (3--D) position, orientation, and relative motion between two reference frames is an important problem in robotic guidance, manipulation, and assembly as well as in other fields such as photogrammetry. A solution to this problem that uses two-dimensional (2--D), intensity images from a single camera is desirable for real-time applications. Where the object geometry is unknown, the estimation of structure is also required. A single camera is advantageous because a standard video camera is low in cost, setup and calibration are simple, physical space requirements are small, reliability is high, and low-cost hardware is available for digitizing and processing the images. A di#culty in performing this measurement is the process of projecting 3--D object features to 2--D images, a nonlinear transformation. Noise is present in the form of perturbations to the assumed process dynamics, imperfections in system modeling, and errors in the feature locations extracted from the 2--D images. This dissertation presents solutions to the remote measurement problem for a dynamic system given a sequence of 2--D intensity images of an object where feature positions of the object are known relative to a base reference frame and where the feature positions are unknown relative to a base reference frame. The 3--D transformation is modeled as a nonlinear stochastic system with the state estimate providing six degree-of-freedom motion and position values. The stochastic model uses the iterated extended Kalman filter as an estimator and as a screw representation of the 3--D transformation based on dual quaternions. Dual quaternions provide a means to represent both rotation and translation in a unified notation. The method has been implemented and tes...

This paper describes current work at Oak Ridge National Laboratory to develop a robotic vision system capable of determining the position and orientation (pose) of designated objects from their geometry. A method has been developed that connects 2-D point features from a single image into higher-order shapes and then matches these features with corresponding features of a polyhedral model. Pose estimates are made from these matches using a closed-form point solution based on model features of four coplanar points. Rotations are represented by quaternions, which are four component numbers, that simplify the calculations in determining the least-squares solution for the coordinate transformation. This pose determination method, including image acquisition, feature extraction, feature correspondence, and pose calculation, has been implemented on a real-time system using a commercial camera and image processing hardware. Experimental results from this implementation are given for relative ...

Proximity operations between spacecraft allows for docking, inspection, and repair of a target vehicle. Very small spacecraft, under 20 kg, are wellsuited for proximity activities and are of growing interest in the aerospace community. However, due to size and power constraints, small vehicles cannot carry traditional precision navigation systems and have generally noisy sensor and actuator options. This paper presents two techniques for improved autonomous, on-board navigation that account for noisy and poorly observable states. First, an Unscented Kalman Filter is implemented for localization which incorporates orbital dynamics and quaternion rotation. Second, two online regression algorithms, Bayes Linear Regression and Gaussian Process Regression, are used to learn the timevarying thruster dynamics. These techniques have been demonstrated successfully on a simulated small inspector vehicle and are being integrated on the Washington University in St. Louis Bandit inspector spacecraft. and have a minimal mass cost for launch. However, they are constrained by the amount of power they can generate and store, and they cannot carry traditional precision navigation systems. These constraints pose a significant navigation challenge. There have been a number of recent space proximity

Close-proximity operations between spacecraft allow for docking and inspection of a target vehicle. Very small spacecraft are well-suited for proximity activities and are of growing interest in the aerospace community. However, due to size and power constraints, small vehicles cannot carry traditional precision navigation systems and generally have noisy sensor and actuator options. This paper presents two techniques for improved autonomous, on-board navigation that account for these poorly observable states. First, an Unscented Kalman Filter is implemented for pose estimation which incorporates orbital dynamics and quaternion rotation. Second, online Bayes Linear Regression (BLR) models the time-varying thruster dynamics. The BLR is then used to complement an unreliable sensor in the UKF, improving pose prediction. These techniques have been demonstrated successfully on a simulated small inspector vehicle and are being integrated in the Bandit inspector spacecraft. 1.

Abstract. This article introduces a technique for region-based pose tracking of multiple objects. Our algorithm uses surface models of the objects to be tracked and at least one calibrated camera view, but does not require color, texture, or other additional properties of the objects. By optimizing a joint energy defined on the pose parameters of all objects, the proposed algorithm can explicitly handle occlusions between different objects. Tracking results in simulated as well as real world scenes demonstrate the effects of occlusion and how they are handled by the proposed method. 1

Despite great progress achieved in 3-D pose tracking during the past years, occlusions and self-occlusions are still an open issue. This is particularly true in silhouette-based tracking where even visible parts cannot be tracked as long as they do not affect the object silhouette. Multiple cameras or motion priors can overcome this problem. However, multiple cameras or appropriate training data are not always readily available. We suggest to handle occlusions and self-occlusions by tracking multiple objects and object parts simultaneously, where each part is described by its own region. This allows to deal with occlusions explicitly, which includes self-occlusions between different parts of the same object as well as occlusions between different objects. Our tracking approach estimates the pose of 3-D models by minimising the 2-D projection error through minimisation of an energy function depending on the pose parameters. Therefore, we model different image regions by probability density functions. The results we present for

Despite great progress achieved in 3-D pose tracking during the past years, occlusions and self-occlusions are still an open issue. This is particularly true in silhouette-based tracking where even visible parts cannot be tracked as long as they do not affect the object silhouette. Multiple cameras or motion priors can overcome this problem. However, multiple cameras or appropriate training data are not always readily available. We propose a framework in which the pose of 3-D models is found by minimising the 2-D projection error through minimisation of an energy function depending on the pose parameters. This framework makes it possible to handle occlusions and self-occlusions by tracking multiple objects and object parts simultaneously. Therefore, each part is described by its own image region each of which is modeled by one probability density function. This allows to deal with occlusions explicitly, which includes self-occlusions between different parts of the same object as well as occlusions between different objects.