Fredrik Lantz

On platform-based sensor management

The design of a generic mechanism for platform-based data fusion and sensor management is described. It is based on the duality between two types of agents, task agents and sensor agents. Task agents buy information from sensor agents that sell it, and sensors produce information that tasks consume. These buy and sell interactions occur very frequently for systems involving sensors that work with small action durations. When several sensors are available, the sell/buy interaction involve selection and scheduling of sensors. The task concept is similar to the old decision or OODA (observe/orient/decide/act) loop that has since long been used for understanding human participation in complex command and control problems. A task might be described as a tiny OODA loop, with predefined purpose and processing capability. There are numerous task types, each dedicated to a certain skill or sensor process. The design is evaluated in single and multiplatform applications.

An information system for target recognition

We present an approach to a general decision support system. The aim is to cover the complete process for automatic target recognition, from sensor data to the user interface. The approach is based on a query-based information system, and include tasks like feature extraction from sensor data, data association, data fusion and situation analysis. Currently, we are working with data from laser radar, infrared cameras, and visual cameras, studying target recognition from cooperating sensors on one or several platforms. The sensors are typically airborne and at low altitude. The processing of sensor data is performed in two steps. First, several attributes are estimated from the (unknown but detected) target. The attributes include orientation, size, speed, temperature etc. These estimates are used to select the models of interest in the matching step, where the target is matched with a number of target models, returning a likelihood value for each model. Several methods and sensor data types are used in both steps. The user communicates with the system via a visual user interface, where, for instance, the user can mark an area on a map and ask for hostile vehicles in the chosen area. The user input is converted to a query in ΣQL, a query language developed for this type of applications, and an ontological system decides which algorithms should be invoked and which sensor data should be used. The output from the sensors is fused by a fusion module and answers are given back to the user. The user does not need to have any detailed technical knowledge about the sensors (or which sensors that are available), and new sensors and algorithms can easily be plugged into the system.

Dual aspects of a multi-resolution grid-based terrain data model with supplementary irregular data points

Digital terrain data models in high resolution are required in applications for visualization but also, e.g. for identification of various types of terrain features. These two aspects are in a way contradictory since the former application require a large number of data points to represent the high resolution, while the latter cannot deal with such a large number of data points without high demands for heavy computational powers. A solution to this problem is a structure that includes quantitative characteristics for visualization and a qualitative representation for feature analysis. A digital terrain data model characterized with these dual aspects has been designed and is presented in this work.

Generation of high-resolution terrain elevation models for synthetic environments using laser-radar data

In this paper, a technique for generation of terrain elevation data for synthetic environments from laser-radar images will be demonstrated. The method is characterized by maintaining the high resolution that is available in source data without too much loss of significant information in its data reduction process. Separation of forest information as well as other types of outstanding objects from the ground is another important step in the process of generating a reliable terrain elevation model. As a consequence, it is possible to generate terrain models with a resolution of less than 0.5 m and where data have been highly reduced.

Task management in sensor-provided operator platforms

An agent architecture for modelling of operator controlled platform interaction is presented. The approach accounts for distributed decision making in autonomous but cooperating operator guided mobile platforms. Each platform has a kernel which interacts with operators, sensors and other platforms. In platform-operator interaction, the agent model facilitates task management and automation control. For platform-platform interaction, a solution is proposed concerning the conflict between resource control and resource sharing in a network. In platform-sensor interaction, a buy & sell model is applied. The agent architecture concept is based on well-established theories for operator situation awareness, cognitive systems engineering and data fusion.

Context fusion for driveability analysis

Driveability analysis is a quite complex problem that for its solution depends on several factors. One of these factors concerns the type of vehicle for which a drive-way should be determined. Besides this, the terrain structure, the type of vegetation but also the ground type and its conditions play important roles. Driveability analysis will consequently include analysis of primarily geographical information and the outcome of this analysis can be used to support decision making in command and control systems. However, quite often the required geographical information is represented in a resolution that is either too low and/or is represented with a high degree of uncertainty that cannot be neglected. In this work, an approach to driveability analysis is presented in which geographical information is regarded as context information that eventually is fused to generate paths, that may be drivable for certain types of vehicles. This information is fused by means of a knowledge-based technique that determines the driveability from a set of qualitative driveability impact factors.

Symbolic Tile Categories for Spatial Reasoning on Objects Represented in Multiple-Resolution

Methods for symbolic spatial reasoning requires quite often a representation of the objects in multiple resolutions. The traditional methods are in such cases less useful since the objects are either represented in a resolution of an order that is too low or they are based on a structure that does not easily allow the representation of the object in a symbolic or a qualitative way. The approach taken here has been to develop an approach that shares some of the characteristics found in resolution pyramids and quad-trees resulting in a structure represented in terms of symbolic tiles. This symbolic structure can be used for spatial reasoning in applications where, among other things, the purpose is to reason about object shape and relationships where the objects need to be represented in multiple resolutions.