An intelligent swarm-based guidance and path planning algorithm for the Unmanned Arial Vehicles (UAV) provides
the ability to efficiently carry out grid surveillance, taking into account specific UAV constraints such as maximum
speed, maximum flight time and battery re-charging intervals to allow for continuous surveillance. The swarm-based
flight planning is based on enhancements of distributed computing concepts that have been developed for NASA's
launch danger zone protection. The algorithm is a modified version of an ant colony optimization theory describing ant
food foraging. Ants initially follow random paths from the nest, but if food is found, the ant deposits a pheromone
(modifying the local environment), which influences other ants to travel the same path. Once the food source is
exhausted, the pheromone decays naturally, which causes the trail to disappear. When an ant is on an established trail, it
may at any time decide to follow a new random path, allowing for new exploration. Using these concepts, in our system
for UAV, we use two units, the Rendezvous unit and the Patrol unit. The Rendezvous units will act as pheromone
deposit sites keeping a record of trails of interest (extra pheromone that decays over time), and obstacles (no
pheromone). The search area is divided into a grid of areas. Each area unit is assigned a pheromone weight. The patrol
unit picks an area unit based on a probabilistic formula consisting of parameters like the relative weight of trail
intensity, area visibility to the unit, the distance of the patrol unit from the area, and the pheromone decay factor.
Simulation of a UAV surveillance system based on the above algorithm showed that it has the ability to perform
independently and reliably without human intervention, and the emergent nature of the algorithm has the ability to
incorporate important aspects of unmanned surveillance.
A multi-sensor detection and fusion technology is described in this paper. The system consists of inputs from three
sensors, Infra Red, Doppler Motion, and Stereo Video. The technique consists of three processing parts corresponding
to each sensor data, and a fusion module, which makes the final decision based on the inputs from the three parts. The
signal processing and detection algorithms process the inputs from each sensor and provides specific information to the
fusion module. The fusion module is based on the bayes belief propagation theory. It takes the processed inputs from all
of the sensor modules and provides a final decision for the presence and absence of objects, as well as their reliability
based on the iterative belief propagation algorithm operating on decision graphs. This choice of sensors is designed to
give high reliability. The infra red and Doppler provide detection ability at night, while stereo video has the ability to
analyze depth and range information. The combination of these sensors has the ability to provide a high probability of
detection and a very low false alarm rate. A prototype system was built using this technique to study the feasibility of
intrusion detection for NASA's launch danger zone protection. The system verified the potential of the proposed
algorithms and proved the feasibility of high probability of detection and low false alarm rates compared to many
existing techniques.
In this paper, we propose a novel acoustic sensor network system that can provide road edge detection in order to prevent
rollovers. The system can work in "non-cooperative" road scenarios that do not possess any characteristic "cooperative markings," such as white lines, or pavement at the sidewalk.
A new approach to neural networks is proposed, based on wireless interconnects (synapses) and cellular neurons, both software and hardware; with the capacity of 1010 neurons, almost fully connected. The core of the system is Spatio-Temporal-Variant (STV) kernel and cellular axon with synaptic plasticity variable in time and space. The novel large neural network hardware is based on two established wireless technologies: RF-cellular and IR-wireless.
Contemporary high performance data networks carry a wide range of multimedia services (voice, video, audio, text, sensor data, etc.) that require an outstanding Quality of Service (QoS) to provide performance guarantees in priority delivery, latency, bandwidth utilization, load balancing, etc. With the advent of recent Multi-Protocol Label Switching (MPLS) network standards, the QoS has made significant progress in performance to provide these performance guarantees. Right now, attention has turned to the task of managing these QoS networks more efficiently through the handling of network traffic. We have investigated a novel Network Traffic Forecasting Assisted QoS Planner technology that will provide constantly updated forecasts of data traffic and server loads to any application that needs this information. Using source models of voice, video and data traffic based on empirical studies of TCP/IP data traffic carried out by Paxson and Floyd in the 1990's, our studies have shown that the system may provide up to 43% bandwidth savings for MPLS data streams, by predicting future traffic flows and reserving network resources to accommodate the predicted traffic. The system additionally provides a means to submit bandwidth reservation requests for those applications that need assured service guarantees for data delivery. The technology essentially increases the efficiency and effectiveness of multimedia information and communication network infrastructure that supports multiple or adaptive QoS levels for multimedia data networking and information system applications.
Theoretically it is possible for two sensors to reliably send data at rates smaller than the sum of the necessary data rates for sending the data independently, essentially taking advantage of the correlation of sensor readings to reduce the data rate. In 2001, Caltech researchers Michelle Effros and Qian Zhao developed new techniques for data compression code design for correlated sensor data, which were published in a paper at the 2001 Data Compression Conference (DCC 2001). These techniques take advantage of correlations between two or more closely positioned sensors in a distributed sensor network. Given two signals, X and Y, the X signal is sent using standard data compression. The goal is to design a partition tree for the Y signal. The Y signal is sent using a code based on the partition tree. At the receiving end, if ambiguity arises when using the partition tree to decode the Y signal, the X signal is used to resolve the ambiguity. We have extended this work to increase the efficiency of the code search algorithms. Our results have shown that development of a highly integrated sensor network protocol that takes advantage of a correlation in sensor readings can result in 20-30% sensor data transport cost savings. In contrast, the best possible compression using state-of-the-art compression techniques that did not take into account the correlation of the incoming data signals achieved only 9-10% compression at most. This work was sponsored by MDA, but has very widespread applicability to ad hoc sensor networks, hyperspectral imaging sensors and vehicle health monitoring sensors for space applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.