This paper introduces novel methods for terrain classification and characterization with a mobile robot. In the context of this paper, terrain classification aims at associating terrains with one of a few predefined, commonly known categories, such as gravel, sand, or asphalt. Terrain characterization, on the other hand, aims at determining key parameters of the terrain that affect its ability to support vehicular traffic. Such properties are collectively called “trafficability.” The proposed terrain classification and characterization system comprises a skid‐steer mobile robot, as well as some common and some uncommon but optional onboard sensors. Using these components, our system can characterize and classify terrain in real time and during the robot's actual mission. The paper presents experimental results for both the terrain classification and characterization methods. The methods proposed in this paper can likely also be implemented on tracked robots, although we did not test this option in our work.

We present, in this paper, a wavelet-based acoustic signal analysis to remotely recognize military vehicles using their sound intercepted by acoustic sensors. Since expedited signal recognition is imperative in many military and industrial situations, we developed an algorithm that provides an automated, fast signal recognition once implemented in a real-time hardware system. This algorithm consists of wavelet preprocessing, feature extraction and compact signal representation, and a simple but effective statistical pattern matching. The current status of the algorithm does not require any training. The training is replaced by human selection of reference signals (e.g. , squeak or engine exhaust sound) distinctive to each individual vehicle based on human perception. This allows a fast archiving of any new vehicle type in the database once the signal is collected. The wavelet preprocessing provides time-frequency multiresolution analysis using discrete wavelet transform (DWT). Within each resolution level, feature vectors are generated from statistical parameters and energy content of the wavelet coefficients. After applying our algorithm on the intercepted acoustic signals , the resultant feature vectors are compared with the reference vehicle feature vectors in the database using statistical pattern matching to determine the type of vehicle from where the signal originated. Certainly, statistical pattern matching can be replaced by an artificial neural network (ANN); however, the ANN would require training data sets and time to train the net. Unfortunately, this is not always possible for many real world situations, especially collecting data sets from unfriendly ground vehicles to train the ANN. Our methodology using wavelet preprocessing and statistical pattern matching provides robust acoustic signal recognition.We also present an example of vehicle recognition using acoustic signals collected from two different military ground vehicles. In this paper, we will not present the mathematics involved in this research. Instead, the focus of this paper will be on the application of various techniques used to achieve our goal of successful recognition.

Today the great majority of target acquisition models within the Department of Defense (DoD) originate from two primary sources of empirical human observer data: the Blackwell-Tiffany visual perception experiments begun in World War II and the Army Night Vision Electrooptic Sensors Directorate (NVESD) field test trials with military observers. An extensive sensitivity analysis that compares the performance of several DoD acquisition models derived from these two extensive sets of data was carried out. A comprehensive analysis of each method and a detailed comparison of these different methodologies shows that they are in remarkably good agreement throughout their ranges of applicability. The authors show when the various modeling methodologies are applicable for a variety of military sensor and countermeasure scenarios.

A large number of terrain images were taken at Aberdeen Proving Grounds, some containing ground vehicles. Is it possible to screen the images for possible targets in a short amount of time using the fractal dimension to detect texture variations? The fractal dimension is determined using the wavelet transform for these visual images. The vehicles are positioned within the grass and in different locations. Since it has been established that natural terrain exhibits a statistical 1/f self-similarity property and the psychophysical perception of roughness can be quantified by the same self-similarity, fractal dimension estimates should vary only at texture boundaries and breaks in the tree and grass patterns. Breaks in the patterns are found using contour plots of the dimension estimates and are considered as perceptual texture variations. Variation in the dimension estimate is considered more important than the accuracy of the actual dimension number. Accurate variation estimates are found even with low resolution images. Mandelbrot defmed a fractal as a set whose Hausdorff-Besicovitch dimension strictly exceeds the topological dimension. This defmition of dimension has no application to fmite sets. There have been many other defmitions applied to the dimension to incorporate the idea of self-similar sets but their relationships are not always clear. For example, the Minkowski dimension is an upper bound for the Hausdorff dimension and the Box dimension is an upper bound for the Minkowski dimension. But when fmite sampling occurs, these inequalities may no longer hold.2 To avoid these difficulties, we will turn to a statistical defmition of a fractal defmed below.'We defme a statistically self-similar fractal function, y(t) as: y(t)=ay(at) witha>O. The equality is defined in terms of second order finite-dimensional statistics. The function y(t) is a zeromean Gaussian. It has been shown that these fractals are successful at modeling a number of natural phenomenon like texture variation in natural terrain.' These fractal textures and signals can be classified and segmented using both fractal dimension and lacunarity.