This paper describes maximum likelihood estimation techniques for performing rover localization in natural terrain by matching range maps. An occupancy map of the local terrain is first generated using stereo vision. The position of the rover with respect to a previously generated occupancy map is then computed by comparing the maps using a probabilistic formulation of image matching techniques. Our motivation for this work is the desire for greater autonomy in Mars rovers. These techniques have been applied to data obtained from the Sojourner Mars rover and run on-board the Rocky 7 Mars rover prototype. 1 Introduction Visual sensors can be used to reduce the positional uncertainty in mobile robots that is accumulated due to dead-reckoning error [14]. This paper describes a method for performing self-localization in natural terrain by matching a range map generated from the robot cameras (the local map) to a range map encompassing the same terrain that has been previously generated (t...

Localization is a critical issue in mobile robotics. If the robot does not know where it is, it, cannot effectively plan movements, locate objects, or reach goals. In this paper, we describe probabilistic self-localization techniques for mobile robots that are based on the principal of maximum-likelihood estimation. The basic method is to compare a map generated at the current robot position to a previously generated map of the environment to prohabilistically maximize the agreement between the maps. This method is able to operate in both indoor and outdoor environments using either discrete features or an occupancy grid to represent the world map. The map may be generated using any method to detect features in the robot's surroundings, including vision, sonar, a d laser range-finder. A global search of the pose space is performed that guarantees that the best position in a discretized pose space is found according to the probabilistic: map agreement measure. In addition, fitting the likelihood function with a parameterized smface allows both subpixel localization and uncertainty estimation to be performed. The application of these techniques in several experiments is described, including experimental localization results for the Sojourner Mars rover. 1

Abstract—This paper presents a novel probabilistic approach to hierarchical, exemplar-based shape matching. No feature correspondence is needed among exemplars, just a suitable pairwise similarity measure. The approach uses a template tree to efficiently represent and match the variety of shape exemplars. The tree is generated offline by a bottom-up clustering approach using stochastic optimization. Online matching involves a simultaneous coarse-to-fine approach over the template tree and over the transformation parameters. The main contribution of this paper is a Bayesian model to estimate the a posteriori probability of the object class, after a certain match at a node of the tree. This model takes into account object scale and saliency and allows for a principled setting of the matching thresholds such that unpromising paths in the tree traversal process are eliminated early on. The proposed approach was tested in a variety of application domains. Here, results are presented on one of the more challenging domains: real-time pedestrian detection from a moving vehicle. A significant speed-up is obtained when comparing the proposed probabilistic matching approach with a manually tuned nonprobabilistic variant, both utilizing the same template tree structure. Index Terms—Hierarchical shape matching, chamfer distance, Bayesian models. 1

This paper addresses the problem of capturing the dynamics for exemplar-based recognition systems. Traditional HMM provides a probabilistic tool to capture system dynamics and in exemplar paradigm, HMM states are typically coupled with the exemplars. Alternatively, we propose a non-parametric HMM approach that uses a discrete HMM with arbitrary states (decoupled from exemplars) to capture the dynamics over a large exemplar space where a nonparametric estimation approach is used to model the exemplar distribution. This reduces the need for lengthy and non-optimal training of the HMM observation model. We used the proposed approach for view-based recognition of gestures. The approach is based on representing each gesture as a sequence of learned body poses (exemplars). The gestures are recognized through a probabilistic framework for matching these body poses and for imposing temporal constraints between different poses using the proposed nonparametric HMM.

We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an object is represented in terms of a model shape. A new shape is classified as being an instance of the object when the Hausdorff distance between the model and the new shape is small. We show that such object concepts can be seen as halfspaces (linear threshold functions) in a transformed input space. This makes it possible to use a number of standard algorithms to learn object models from training examples. When a good model exists, we are guaranteed to find one that provides (with high probability) a recognition rule that is accurate. Our approach provides a measure which generalizes the Hausdorff distance in a number of interesting ways. To demonstrate our method we trained a system to detect people in images using a single shape model. The learning techniques can be extended to represent objects using multiple model shapes. In this way, we might be able to automatically learn a small set of canonical shapes that characterize the appearance of an object. 1.

We describe a new approach to feature-based object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. The main advantage of this approach is that it allows explicit modeling of dependencies between individual features of an object model. For instance, it can capture the fact that unmatched features due to partial occlusion are generally spatially coherent rather than independent. Efficient computation of the MAP estimate in our framework can be accomplished by finding a minimum cut on an appropriately defined graph. A special case of our framework yields even more efficient method, that does not use graph cuts. We call this technique spatially coherent matching. Our framework can also be seen as providing a probabilistic understanding of Hausdorff matching. We present ROC curves from Monte Carlo experiments that illustrate the improvement of the new spatially coherent matching technique over Hausdorff matching. 1 Introduction In this pap...

We describe techniques for performing mobile robot localization using occupancy grids that enable both sub-pixel localization to be performed and uncertainty es-timates to be computed. The uncertainty is addressed with respect to both the standard deviation of the lo-calization estimate and the probability of a qualita-tive failure. The techniques are based on a localiza-tion method that performs matching between the visible landmarks at the current robot position and a previ-ously generated map of the environment. We first es-timate the probability distribution of the distance from each feature in the local map to the closest feature an the larger map. Subpixel localization and uncertainty estimation are then perform by fitting the likelihood function over the space of possible robot positions with a parameterized surface. Synthetic experiments are described and an example of the performance of this method is given using the Rocky 7 Mars rover proto-type. 1

This paper describes matchlist-based branch-and-bound techniques and presents a number of new applications of branch-and-bound methods, among them, a method for globally optimal partial line segment matching under bounded or Gaussian error, point matching under a Gaussian error model with subpixel accuracy and precise orientation models, and a simple and robust technique for finding multiple distinct object instances. It also contains extensive reference information for the implementation of such matching methods under a wide variety of error bounds and transformations. In addition, the paper contains a number of benchmarks and evaluations that provide new information about the runtime behavior of branch-and-bound matching algorithms in general, and that help choose among different implementation strategies, such as the use of point location data structures and space/time tradeoffs involving depth-first search

iii Preface Needless to say, this work would not have been possible without the continuing support of Robert Hummel and Benjamin Goldberg. To them goes my deepest gratitude. iv Table of Contents Acknowledgements............................................................................. iii

SUMMARY: This paper presents a preliminary crash avoidance framework for heavy equipment control systems. Safe equipment operation is a major concern on construction sites since fatal on-site injuries are an industry-wide problem. The proposed framework has potential for effecting active safety for equipment operation. The framework contains algorithms for spatial modeling, object tracking, and path planning. Beyond generating spatial models in fractions of seconds, these algorithms can successfully track objects in an environment and produce a collision-free 3D motion trajectory for equipment.