This paper presents an approach for estimating the confidence level in automatic multi-target classification performed by an imaging sensor on an unmanned vehicle. An automatic target recognition algorithm comprised of a deep convolutional neural network in series with a support vector machine classifier detects and classifies targets based on the image matrix. The joint posterior probability mass function of target class, features, and classification estimates is learned from labeled data, and recursively updated as additional images become available. Based on the learned joint probability mass function, the approach presented in this paper predicts the expected confidence level of future target classifications, prior to obtaining new images. The proposed approach is tested with a set of simulated sonar image data. The numerical results show that the estimated confidence level provides a close approximation to the actual confidence level value determined a posteriori, i.e. after the new image is obtained by the on-board sensor. Therefore, the expected confidence level function presented in this paper can be used to adaptively plan the path of the unmanned vehicle so as to optimize the expected confidence levels and ensure that all targets are classified with satisfactory confidence after the path is executed.
In this paper, we are interested in exploiting the heterogeneity of a robotic network made of ground and aerial agents to sense multiple targets in a cluttered environment. Maintaining wireless communication on this type of networks is fundamentally important specially for cooperative purposes. The proposed heterogeneous network consists of ground sensors, e.g., OctoRoACHes, and aerial routers, e.g., quadrotors. Adaptive potential field methods are used to coordinate the ground mobile sensors. Moreover, a reward function for the aerial mobile wireless routers is formulated to guarantee communication coverage among the ground sensors and a fixed base station. A sub-optimal controller is proposed based on an approximate control policy iteration technique. Simulation results of a case study are presented to illustrate the proposed methodology.
This paper presents a hybrid approximate dynamic programming (ADP) method for a hybrid dynamic system
(HDS) optimal control problem, that occurs in many complex unmanned systems which are implemented via a
hybrid architecture, regarding robot modes or the complex environment. The HDS considered in this paper is
characterized by a well-known three-layer hybrid framework, which includes a discrete event controller layer, a
discrete-continuous interface layer, and a continuous state layer. The hybrid optimal control problem (HOCP)
is to nd the optimal discrete event decisions and the optimal continuous controls subject to a deterministic
minimization of a scalar function regarding the system state and control over time. Due to the uncertainty
of environment and complexity of the HOCP, the cost-to-go cannot be evaluated before the HDS explores the
entire system state space; as a result, the optimal control, neither continuous nor discrete, is not available ahead
of time. Therefore, ADP is adopted to learn the optimal control while the HDS is exploring the environment,
because of the online advantage of ADP method. Furthermore, ADP can break the curses of dimensionality
which other optimizing methods, such as dynamic programming (DP) and Markov decision process (MDP), are
facing due to the high dimensions of HOCP.
The problem of surveilling moving targets using mobile sensor agents (MSAs) is applicable to a variety of
fields, including environmental monitoring, security, and manufacturing. Several authors have shown that the
performance of a mobile sensor can be greatly improved by planning its motion and control strategies based
on its sensing objectives. This paper presents an information potential approach for computing the MSAs'
motion plans and control inputs based on the feedback from a modified particle filter used for tracking moving
targets. The modified particle filter, as presented in this paper implements a new sampling method (based
on supporting intervals of density functions), which accounts for the latest sensor measurements and adapts,
accordingly, a mixture representation of the probability density functions (PDFs) for the target motion. It is
assumed that the target motion can be modeled as a semi-Markov jump process, and that the PDFs of the
Markov parameters can be updated based on real-time sensor measurements by a centralized processing unit
or MSAs supervisor. Subsequently, the MSAs supervisor computes an information potential function that is
communicated to the sensors, and used to determine their individual feedback control inputs, such that sensors
with bounded field-of-view (FOV) can follow and surveil the target over time.
KEYWORDS: Sensors, General packet radio service, Land mines, Infrared sensors, Target detection, Environmental sensing, Electromagnetic coupling, Sensor fusion, Data modeling, Data fusion
The performance of many multi-sensor systems can be significantly improved by using a priori environmental information and sensor data to plan the movements of sensor platforms that are later deployed with the purpose of improving the quality of the final detection and classification results. However, existing path planning algorithms and ad-hoc data processing (e.g., fusion) techniques do not allow for the systematic treatment of multiple and heterogeneous sensors and their platforms. This paper presents a method that combines Bayesian network inference with probabilistic roadmap (PRM) planners to utilize the information obtained by different sensors and their level of uncertainty. The uncertainty of prior sensed information is represented by entropy values obtained from the Bayesian network (BN) models of the respective sensor measurement processes. The PRM algorithm is modified to utilize the entropy distribution in optimizing the path of posterior sensor platforms that have the following objectives: (1) improve the quality of the sensed information, i.e., through fusion, (2) minimize the distance traveled by the platforms, and (3) avoid obstacles. This so-called Probabilistic Deployment (PD) method is applied to a demining system comprised of ground-penetrating radars (GPR), electromagnetic (EMI), and infrared sensors (IR) installed on ground platforms, to detect and classify buried mines. Numerical simulations show that PD is more efficient than path planning techniques that do not utilize a priori information, such as complete coverage, random coverage method, or PRM methods that do not utilize Bayesian inference.
Conference Committee Involvement (6)
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
8 March 2010 | San Diego, California, United States
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
9 March 2009 | San Diego, California, United States
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
10 March 2008 | San Diego, California, United States
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
19 March 2007 | San Diego, California, United States
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
27 February 2006 | San Diego, California, United States
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
7 March 2005 | San Diego, California, United States
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.