The cross-country navigation approach presented in this paper relies on two simplification ideas: obstacles are defected by scanning columns of a range image and motion steps are single straight-line trajectories. The resulting system is fast and only prohibits steep slopes or cluttered terrains. It also features a sophisticated planning criterion that yields good global performances. Its reliability has been demonstrated by successful outdoor traverses 70 meters long on a representative test site.

Statistical modeling and evaluation of the performance of obstacle detection systems for unmanned ground vehicles (UGV's) is essential for the design, evaluation and comparison of sensor systems. In this report, we address this issue for imaging range sensors by dividing the evaluation problem into two levels: quality of the range data itself and quality of the obstacle detection algorithms applied to the range data. We review existing models of the quality of range data from stereo vision and AM-CW LADAR, then use these to derive a new model for the quality of a simple obstacle detection algorithm. This model predicts the probability of detecting obstacles and the probability of false alarms, as a function of the size and distance of the obstacle, the resolution of the sensor, and the level of noise in the range data. We evaluate these models experimentally using range data from stereo image pairs of a gravel road with known obstacles at several distances. The results show that the approach is a promising tool for predicting and evaluating the performance of obstacle detection with imaging range.>

Statistical modeling and evaluation of the performance of obstacle detection systems for unmanned ground vehicles (UGVs) is essential for the design, evaluation, and comparison of sensor systems. This issue is addressed for imaging range sensors by dividing the valuation problem into two levels, i.e., the quality of the range data itself and the quality of the obstacle detection algorithms applied to the range data. Existing models of the quality of range data from stereo vision and AM-CW laser range-finders (LADAR) are reviewed. These are used to derive a new model for the quality of a simple obstacle detection algorithm. This model predicts the probability of detecting obstacles and the probability of false alarms, as functions of the size and distance of the obstacle, the resolution of the sensor, and the level of noise in the range data. These models are evaluated experimentally using range data from stereo image pairs of a gravel road with known obstacles at several distances. The results show that the approach is a promising tool for predicting and evaluating the performance of obstacle detection with imaging range sensors.>

The authors present a method for selecting viewpoints and sensing tasks to confirm by a multisensory perception machine, an identification hypothesis previously generated. The determination relies on the use of a compiled knowledge base that links object and sensor models, and defines a priori the best sensing tasks to be performed. The method is fully detailed, and its use under dynamic constraints due to a real environment is explained, along with a control strategy to activate the search. Result of experiments integrating other modules for environment modeling, path planning and execution control, and object recognition are presented.>

This paper proposes an approach for designing and implementing an interpretation system for a multi-sensory perception machine. Integrating multiple heterogeneous recognition and perception processes seems useful to efficiently obtain a reliable interpretation of a real complex dynamic environment. After tackling the problems of modelling objects and sensors, we propose a generic multi-sensory recognition and fusion approach and then present how are controlled and organized the perception tasks through a flexible distributed architecture. The work is validated by experimental results in real situations

The authors propose an approach to generalize the hypothesis and test recognition paradigm for multisensory environments and fairly generic object models. Matching, prediction and localization procedures are based on a generic representation of feature accuracy. This generic approach performs fusion both at the numeric (geometric) and at the symbolic (recognition) levels. Its reliability is illustrated by several real-world examples demonstrating recognition of real objects in complex cluttered environments using four types of sensory data: contour images (two viewpoints), stereovision 3-D line segments, range 3-D faces, and color images.>

The authors present a method that merges and fuses two kinds of 3-D data, surface data obtained with a laser rangefinder and photometric data produced by a stereovision system. It describes indoor scenes with a set of planar faces, a first step toward polyhedral modeling. Noisy geometrical features are represented by random variables whose variance is known. Extended Kalman filtering techniques are used for numeric fusion of features into higher level ones (from points or pixels to 3-D lines, from 3-D lines to planes) and for identification of the transformation linking the sensors' reference frames (calibration). This latter issue receives particular attention, and a methodology is presented for iterative and automatic relative calibration. Experimental results show that this description is sufficiently accurate and reliable for feeding higher level processes, such as mobile robot localization or scene interpretation.>