We address the problem of label assignment in computer vision: given a novel 3D or 2D scene, we wish to assign a unique label to every site (voxel, pixel, superpixel, etc.). To this end, the Markov Random Field framework has proven to be a model of choice as it uses contextual information to yield improved classification results over locally independent classifiers. In this work we adapt a functional gradient approach for learning high-dimensional parameters of random fields in order to perform discrete, multi-label classification. With this approach we can learn robust models involving high-order interactions better than the previously used learning method. We validate the approach in the context of point cloud classification and improve the state of the art. In addition, we successfully demonstrate the generality of the approach on the challenging vision problem of recovering 3-D geometric surfaces from images.

Contextual reasoning through graphical models such as Markov random fields often show superior performance against local classifiers in many domains. Unfortunately, this performance increase is often at the cost of time consuming, memory intensive learning and slow inference at testing time. Structured prediction for 3-D point cloud classification is one example of such an application. In this paper we present two contributions. First we show how efficient learning of a random field with higher-order cliques can be achieved using subgradient optimization. Second, we present a context approximation using random fields with high-order cliques designed to make this model usable online, onboard a mobile vehicle for environment modeling. We obtained results with the mobile vehicle on a variety of terrains, at 1/3 Hz for a map 25 times 50 meters and a vehicle speed of 1-2 m/s.

In this paper, we present an approach for potential negative obstacle detection, based on missing data interpretation that extends traditional techniques driven by data only, which capture the occupancy of the scene. The approach is decomposed into three steps: three-dimensional (3D) data accumulation and low level classification, 3D occluder propagation, and context-based occlusion labeling. The approach is validated using logged laser data collected in various outdoor natural terrains and also demonstrated live on-board the Demo-III experimental unmanned vehicle (XUV).

Long range navigation by unmanned ground vehicles continues to challenge the robotics community. Efficient navigation requires not only intelligent on-board perception and planning systems, but also the effective use of prior knowledge of the vehicle's environment. This paper describes a system for supporting unmanned ground vehicle navigation through the use of heterogeneous overhead data. Semantic information is obtained through supervised classification, and vehicle mobility is predicted from available geometric data. This approach is demonstrated and validated through over 50 kilometers of autonomous traversal through complex natural environments

Errors in laser based range measurements can be divided into two categories: intrinsic sensor errors (range drift with temperature, systematic and random errors), and errors due to the interaction of the laser beam with the environment. The former have traditionally received attention and can be modeled. The latter in contrast have long been observed but not well characterized. We propose to do so in this paper. In addition, we present a sensor independent method to remove such artifacts. The objective is to improve the overall quality of 3-D scene reconstruction to perform terrain classification of scenes with vegetation.

In this paper, we explore the problem of three-dimensional motion planning in highly cluttered and unstructured outdoor environments. Because accurate sensing and modeling of obstacles is notoriously difficult in such environments, we aim to build computational tools that can handle large point data sets (e.g. LADAR data). Using a priori aerial data scans of forested environments, we compute a network of free space bubbles forming safe paths within environments cluttered with tree trunks, branches and dense foliage. The network (roadmap) of paths is used for efficiently planning paths that consider obstacle clearance information. We present experimental results on large point data sets typical of those faced by Unmanned Aerial Vehicles, but also applicable to ground-based robots navigating through forested environments.

This paper presents a real-time implementation of a topological localization method based on matching image features. This work is supported by a unique sensor pod design that provides stand-alone sensing and computing for localizing a vehicle on a previously traveled road. We report extensive field test results from outdoor environments, with the sensor pod mounted on both a small and a large all-terrain vehicle. Off-line analysis of the approach is also presented to evaluate the robustness of the various image features tested against different weather and lighting conditions.

This work describes an approach for using several levels of data fusion in the domain of autonomous off-road navigation. We are focusing on outdoor obstacle detection, and we present techniques that leverage on data fusion and machine learning for increasing the reliability of obstacle detection systems. We are combining color and infrared (IR) imagery with range information from a laser range finder. We show that in addition to fusing data at the pixel level, performing high level classifier fusion is beneficial in our domain. Our general approach is to use machine learning techniques for automatically deriving effective models of the classes of interest (obstacle and non-obstacle for example). We train classifiers on different subsets of the features we extract from our sensor suite and show how different classifier fusion schemes can be applied for obtaining a multiple classifier system that is more robust than any of the classifiers presented as input. We present experimental results we obtained on data collected with both the experimental unmanned vehicle (XUV) and a CMU developed robotic tractor.

Laser based sensing for scene interpretation and obstacle detection is challenged by partially viewed targets, wiry structures, and porous objects. We propose to address such problems by looking at the laser pulse waveform. We designed a new laser sensor with off-the-shelf components. We report on the design and the evaluation of this low cost and compact sensor, suitable for mobile robot application. We determine classical parameters such as operation range, repeatability, accuracy, resolution, but we also analyze laser pulse waveforms modes and mode shape in order to extract additional information on the scene.

Because of the difficulty of interpreting laser data in a meaningful way, safe navigation in vegetated terrain is still a daunting challenge. In this paper, we focus on the segmentation of ladar data using local 3-D point statistics into three classes: clutter to capture grass and tree canopy, linear to capture thin objects like wires or tree branches, and finally surface to capture solid objects like ground terrain surface, rocks or tree trunks. We present the details of the method proposed, the modifications we made to implement it on-board an autonomous ground vehicle. Finally, we present results from field tests using this rover and results produced from different stationary laser sensors.

In this paper, we address the problem of finding organized thin structures in three-dimensional (3-D) data. Linear and planar structures segmentation received much attention but thin structures organized in complex patterns remain a challenge for segmentation algorithms. We are interested especially in the problems posed by repetitive and symmetric structures acquired with a laser range finder. The method relies on 3-D data projections along specific directions and 2-D histograms comparison. The sensitivity of the classification algorithm to the parameter settings is evaluated and a segmentation method proposed. We illustrate our approach with data from a concertina wire in terrain with vegetation.

In this paper we address the problem of assessing quantitatively the quality of traversability maps computed from data collected by an airborne laser range finder. Such data is used to plan paths for an unmanned ground vehicle (UGV) prior to the execution of long range traverses. Little attention has been devoted to the problem we address in this paper. We use a unique data set of geodetic control points, real robot navigation data, ground LIDAR (light detection and ranging) data and aerial imagery, collected during a week long demonstration to support our work.

In this article we propose a method for landmark selection and tracking in natural environments. Landmarks are not specific 3D objects, but an image area that can be tracked over a sequence of monocular images. No assumption is made a priori on landmarks. The algorithm selects areas in a monocular black and white image sequence that have an affine trackability property. A measure of affine trackability is proposed for selection and affine tracking. Initial experimental results are presented.

This paper deals with the development of the use of visual function in order to add useful information for tasks of a mobile robot roving in natural environments. We have proposed and implemented the nominative region model which indicates every region's nature in an image. A color segmentation algorithm provides a synthetic description of the scene. Regions obtained from the segmentation stage are then characterized by their color and texture and afterwards identified in order to obtain their nature (grass, rocks, ...). Probabilistic methods are used to determine the nature of current elements in the environment. Then, one specific landmark is chosen according to its nature and shape and this representation is tracked through an image sequence.