Engineering topics

Spirkovska, Lilly

Publications and source records attributed to Spirkovska, Lilly.

36 records · Page 2

NASA NTRS2006

Using Artificial Intelligence to Inform Pilots of Weather

An automated system to assist a General Aviation (GA) pilot in improving situational awareness of weather in flight is now undergoing development. This development is prompted by the observation that most fatal GA accidents are attributable to loss of weather awareness. Loss of weather awareness, in turn, has been attributed to the difficulty of interpreting traditional preflight weather briefings and the difficulty of both obtaining and interpreting traditional in-flight weather briefings. The developmental automated system not only improves weather awareness but also substantially reduces the time a pilot must spend in acquiring and maintaining weather awareness.

Spirkovska, Lilly↗

NASA NTRS2005

Summary of Tactile User Interfaces Techniques and Systems

Mental workload can be de.ned as the ratio of demand to allocated resources. Multiple-resource theory stresses the importance of distribution of tasks and information across various human sensory channels to reduce mental workload. One sensory channel that has been of interest since the late 1800s is touch. Unlike the more typical displays that target vision or hearing, tactile displays present information to the user s sense of touch. We present a summary of different methods for tactile display, historic and more recent systems that incorporate tactile display for information presentation, advantages and disadvantages of targeting the tactile channel, and future directions in tactile display research.

Spirkovska, Lilly↗

NASA NTRS2004

Summary of Tactile User Interfaces Techniques and Systems

Mental workload can be defined as the ratio of demand to allocated resources. Multiple- resource theory stresses the importance of distribution of tasks and information across various sensory channels of the human to reduce mental workload. One sensory channel that has been of interest since the late 1800s is touch. Unlike the more typical displays that target vision or hearing, tactile displays present information to the user s sense of touch. We present a summary of different methods for tactile display; historic and more recent systems that incorporate tactile display for information presentation; advantages and disadvantages of targeting the tactile channel; and future directions in tactile display research.

Spirkovska, Lilly↗

NASA NTRS2004

Context-Aware Intelligent Assistant Approach to Improving Pilot's Situational Awareness

Faulty decision making due to inaccurate or incomplete awareness of the situation tends to be the prevailing cause of fatal general aviation accidents. Of these accidents, loss of weather situational awareness accounts for the largest number of fatalities. We describe a method for improving weather situational awareness through the support of a contextaware,domain and task knowledgeable, personalized and adaptive assistant. The assistant automatically monitors weather reports for the pilot's route of flight and warns her of detected anomalies. When and how warnings are issued is determined by phase of flight, the pilot s definition of acceptable weather conditions, and the pilot's preferences for automatic notification. In addition to automatic warnings, the pilot is able to verbally query for weather and airport information. By noting the requests she makes during the approach phase of flight, our system learns to provide the information without explicit requests on subsequent flights with similar conditions. We show that our weather assistant decreases the effort required to maintain situational awareness by more than 5.5 times when compared to the conventional method of in-flight weather briefings.

Spirkovska, Lilly↗

NASA NTRS2004

Intelligent Automation Approach for Improving Pilot Situational Awareness

Automation in the aviation domain has been increasing for the past two decades. Pilot reaction to automation varies from highly favorable to highly critical depending on both the pilot's background and how effectively the automation is implemented. We describe a user-centered approach for automation that considers the pilot's tasks and his needs related to accomplishing those tasks. Further, we augment rather than replace how the pilot currently fulfills his goals, relying on redundant displays that offer the pilot an opportunity to build trust in the automation. Our prototype system automates the interpretation of hydraulic system faults of the UH-60 helicopter. We describe the problem with the current system and our methodology for resolving it.

Spirkovska, Lilly↗

NASA NTRS2001

AWE: Aviation Weather Data Visualization

The two official sources for aviation weather reports both require the pilot to mentally visualize the provided information. In contrast, our system, Aviation Weather Environment (AWE) presents aviation specific weather available to pilots in an easy to visualize form. We start with a computer-generated textual briefing for a specific area. We map this briefing onto a grid specific to the pilot's route that includes only information relevant to his flight route that includes only information relevant to his flight as defined by route, altitude, true airspeed, and proposed departure time. By modifying various parameters, the pilot can use AWE as a planning tool as well as a weather briefing tool.

Spirkovska, Lilly↗

NASA NTRS2001

Audio-Visual Situational Awareness for General Aviation Pilots

Weather is one of the major causes of general aviation accidents. Researchers are addressing this problem from various perspectives including improving meteorological forecasting techniques, collecting additional weather data automatically via on-board sensors and "flight" modems, and improving weather data dissemination and presentation. We approach the problem from the improved presentation perspective and propose weather visualization and interaction methods tailored for general aviation pilots. Our system, Aviation Weather Data Visualization Environment (AWE), utilizes information visualization techniques, a direct manipulation graphical interface, and a speech-based interface to improve a pilot's situational awareness of relevant weather data. The system design is based on a user study and feedback from pilots.

Spirkovska, Lilly↗

NASA NTRS2000

AWE: Aviation Weather Data Visualization Environment

The two official sources for aviation weather reports both provide weather information to a pilot in a textual format. A number of systems have recently become available to help pilots with the visualization task by providing much of the data graphically. However, two types of aviation weather data are still not being presented graphically. These are airport-specific current weather reports (known as meteorological observations, or METARs) and forecast weather reports (known as terminal area forecasts, or TAFs). Our system, Aviation Weather Environment (AWE), presents intuitive graphical displays for both METARs and TAFs, as well as winds aloft forecasts. We start with a computer-generated textual aviation weather briefing. We map this briefing onto a cartographic grid specific to the pilot's area of interest. The pilot is able to obtain aviation-specific weather for the entire area or for his specific route. The route, altitude, true airspeed, and proposed departure time can each be modified in AWE. Integral visual display of these three elements of weather reports makes AWE a useful planning tool, as well as a weather briefing tool.

Spirkovska, Lilly↗

NASA NTRS2000

AWE: Aviation Weather Data Visualization Environment

Weather is one of the major causes of aviation accidents. General aviation (GA) flights account for 92% of all the aviation accidents, In spite of all the official and unofficial sources of weather visualization tools available to pilots, there is an urgent need for visualizing several weather related data tailored for general aviation pilots. Our system, Aviation Weather Data Visualization Environment AWE), presents graphical displays of meteorological observations, terminal area forecasts, and winds aloft forecasts onto a cartographic grid specific to the pilot's area of interest. Decisions regarding the graphical display and design are made based on careful consideration of user needs. Integral visual display of these elements of weather reports is designed for the use of GA pilots as a weather briefing and route selection tool. AWE provides linking of the weather information to the flight's path and schedule. The pilot can interact with the system to obtain aviation-specific weather for the entire area or for his specific route to explore what-if scenarios and make "go/no-go" decisions. The system, as evaluated by some pilots at NASA Ames Research Center, was found to be useful.

Spirkovska, Lilly↗

NASA NTRS1996

Higher-Order Neural Networks Recognize Patterns

Networks of higher order have enhanced capabilities to distinguish between different two-dimensional patterns and to recognize those patterns. Also enhanced capabilities to "learn" patterns to be recognized: "trained" with far fewer examples and, therefore, in less time than necessary to train comparable first-order neural networks.

Reid, Max B.↗

NASA NTRS1994

Higher-Order Neural Networks Applied to 2D and 3D Object Recognition

A Higher-Order Neural Network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous scaled, translated, and rotated views. Because the 2D object recognition task is a component of the 3D object recognition task, built-in 2D invariance also decreases the size of the training set required for 3D object recognition. We present results for 2D object recognition both in simulation and within a robotic vision experiment and for 3D object recognition in simulation. We also compare our method to other approaches and show that HONNs have distinct advantages for position, scale, and rotation-invariant object recognition. The major drawback of HONNs is that the size of the input field is limited due to the memory required for the large number of interconnections in a fully connected network. We present partial connectivity strategies and a coarse-coding technique for overcoming this limitation and increasing the input field to that required by practical object recognition problems.

Spirkovska, Lilly↗

NASA NTRS1993

A summary of image segmentation techniques

Machine vision systems are often considered to be composed of two subsystems: low-level vision and high-level vision. Low level vision consists primarily of image processing operations performed on the input image to produce another image with more favorable characteristics. These operations may yield images with reduced noise or cause certain features of the image to be emphasized (such as edges). High-level vision includes object recognition and, at the highest level, scene interpretation. The bridge between these two subsystems is the segmentation system. Through segmentation, the enhanced input image is mapped into a description involving regions with common features which can be used by the higher level vision tasks. There is no theory on image segmentation. Instead, image segmentation techniques are basically ad hoc and differ mostly in the way they emphasize one or more of the desired properties of an ideal segmenter and in the way they balance and compromise one desired property against another. These techniques can be categorized in a number of different groups including local vs. global, parallel vs. sequential, contextual vs. noncontextual, interactive vs. automatic. In this paper, we categorize the schemes into three main groups: pixel-based, edge-based, and region-based. Pixel-based segmentation schemes classify pixels based solely on their gray levels. Edge-based schemes first detect local discontinuities (edges) and then use that information to separate the image into regions. Finally, region-based schemes start with a seed pixel (or group of pixels) and then grow or split the seed until the original image is composed of only homogeneous regions. Because there are a number of survey papers available, we will not discuss all segmentation schemes. Rather than a survey, we take the approach of a detailed overview. We focus only on the more common approaches in order to give the reader a flavor for the variety of techniques available yet present enough details to facilitate implementation and experimentation.

Spirkovska, Lilly↗

NASA NTRS1993

Coarse-coded higher-order neural networks for PSRI object recognition

A higher-order neural network (HONN) can be designed to be invariant to changes in scale, translation, and inplane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Consequently, fewer training passes and a smaller training set are required to learn to distinguish between objects. The size of the input field is limited, however, because of the memory required for the large number of interconnections in a fully connected HONN. By coarse coding the input image, the input field size can be increased to allow the larger input scenes required for practical object recognition problems. We describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Our simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096 x 4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten passes through the training set. Furthermore, we empirically determine the limits of the coarse coding technique in the object recognition domain.

Spirkovska, Lilly↗

NASA NTRS1993

Three-dimensional object recognition using similar triangles and decision trees

A system, TRIDEC, that is capable of distinguishing between a set of objects despite changes in the objects' positions in the input field, their size, or their rotational orientation in 3D space is described. TRIDEC combines very simple yet effective features with the classification capabilities of inductive decision tree methods. The feature vector is a list of all similar triangles defined by connecting all combinations of three pixels in a coarse coded 127 x 127 pixel input field. The classification is accomplished by building a decision tree using the information provided from a limited number of translated, scaled, and rotated samples. Simulation results are presented which show that TRIDEC achieves 94 percent recognition accuracy in the 2D invariant object recognition domain and 98 percent recognition accuracy in the 3D invariant object recognition domain after training on only a small sample of transformed views of the objects.

Spirkovska, Lilly↗

NASA NTRS1993

Optical information processing at NASA Ames Research Center

The combination of analog optical processors with digital electronic systems offers the potential of tera-OPS computational performance, while often requiring less power and weight relative to all-digital systems. NASA is working to develop and demonstrate optical processing techniques for on-board, real time science and mission applications. Current research areas and applications under investigation include optical matrix processing for space structure vibration control and the analysis of Space Shuttle Main Engine plume spectra, optical correlation-based autonomous vision for robotic vehicles, analog computation for robotic path planning, free-space optical interconnections for information transfer within digital electronic computers, and multiplexed arrays of fiber optic interferometric sensors for acoustic and vibration measurements.

Reid, Max B.↗

NASA NTRS1991

Higher-order neural network software for distortion invariant object recognition

The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.

Reid, Max B.↗

NASA NTRS1991

Optical computing at NASA Ames Research Center

Optical computing research at NASA Ames Research Center seeks to utilize the capability of analog optical processing, involving free-space propagation between components, to produce natural implementations of algorithms requiring large degrees of parallel computation. Potential applications being investigated include robotic vision, planetary lander guidance, aircraft engine exhaust analysis, analysis of remote sensing satellite multispectral images, control of space structures, and autonomous aircraft inspection.

Reid, Max B.↗

NASA NTRS1990

Connectivity strategies for higher-order neural networks applied to pattern recognition

Different strategies for non-fully connected HONNs (higher-order neural networks) are discussed, showing that by using such strategies an input field of 128 x 128 pixels can be attained while still achieving in-plane rotation and translation-invariant recognition. These techniques allow HONNs to be used with the larger input scenes required for practical pattern-recognition applications. The number of interconnections that must be stored has been reduced by a factor of approximately 200,000 in a T/C case and about 2000 in a Space Shuttle/F-18 case by using regional connectivity. Third-order networks have been simulated using several connection strategies. The method found to work best is regional connectivity. The main advantages of this strategy are the following: (1) it considers features of various scales within the image and thus gets a better sample of what the image looks like; (2) it is invariant to shape-preserving geometric transformations, such as translation and rotation; (3) the connections are predetermined so that no extra computations are necessary during run time; and (4) it does not require any extra storage for recording which connections were formed.

Spirkovska, Lilly↗