Posted on

Applications for Intelligent Information Agents (I2As): Learning Agents for Autonomous Space Asset Management (LAASAM)

Authors:
Dr. James Crowder, Raytheon Intelligence and Information Systems
Dr. Lawrence Scally, President and CTO, Colorado Engineering Inc.
Michael Bonato, VP of Program Management, Colorado Engineering Inc.

Abstract:
Current and future space, air, and ground systems will continue to grow in complexity and capability, creating a serious challenge to monitor, maintain, and utilize systems in an ever growing network of assets. The push toward autonomous systems makes this problem doubly hard, requiring that the on-board system contain cognitive skills that can monitor, analyze, diagnose, and
predict behaviors real-time as the system encounters its environment. Described here is a cognitive system of Learning Agents for Autonomous Space Asset Management (LAASAM) that consists of Intelligent Information Agents (I2A) that provide an autonomous Artificially Intelligent System (AIS) with the ability to mimic human reasoning in the way it processes information and develops knowledge [Crowder 2010a, 2010b]. This knowledge takes the form of answering questions and explaining situations that the AIS might encounter. The I2As are persistent software
components, called Cognitive Perceptrons, which perceive, reason, act, and communicate. Presented will be the description, methods, and framework required forCognitive Perceptrons to provide the following abilities to the AIS:

1. Allows the AIS to act on its own behalf;
2. Allows autonomous reasoning, control, and analysis;
3. Allows the Cognitive Perceptrons to filter information and communicate and collaborate with other Cognitive Perceptrons;
4. Allows autonomous control to find and fix problems within the AIS; and
5. Allows the AIS to predict a situation and offer recommend actions, providing automated complex procedures.

A Cognitive Perceptron Upper Ontology will be provided, along with detailed descriptions of the I2A framework required to construct a hybrid system of Cognitive Perceptrons, as well as the Cognitive Perception processing infrastructure and rules architecture. In particular, this paper will present an application of Cognitive Perceptrons to Integrated System Health Management (ISHM), and in particular Condition-Based Health Management (CBHM), to provide the ability to manage and maintain an AIS in utilizing real-time data to prioritize, optimize, maintain, and allocate resources.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Applications for Intelligent Information Agents (I2As): Learning Agents for Autonomous Space Asset Management (LAASAM) (69 downloads)

Posted on

Implicit Learning in Artificial Intelligent Systems: The Coming Problem of Real, Cognitive AI

Authors:
Dr. James Crowder, Systems Fellow, Colorado Engineering Inc.
Dr. Shelli Friess, LPC, NCC, ACS, School of Counseling, Walden University
Dr. John Carbone, Electrical and Computer Eng., Southern Methodist University

Abstract:
There has been much discussion and research over the last few decades on the differences between implicit and explicit learning and subsequently, the difference between explicit and implicit memories that result from implicit vs. explicit learning. Implicit learning differs from explicit learning in that implicit learning happens through unconscious acquisition of knowledge. Implicit learning represents a fundamental process in overall cognition, stemming from unconscious acquisition of knowledge and skills as a result of an entity interacting with its environment. One of the issues or consequences of implicit learning is the notion of how do we recognize that implicit learning has occurred, how will it affect the overall cognitive functions of the entity, and how do we measure and affect implicit learning within an entity? Here we discuss the notion of self adapting, cognitive, artificial intelligent entities and the notion of implicit learning within the artificial intelligent entity; how this will lead to implicit memories and how they might affect an overall artificial intelligent entity, for better or worse.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Implicit Learning in Artificial Intelligent Systems: The Coming Problem of Real, Cognitive AI (72 downloads)

Posted on

Anytime Learning: A Step Toward Life-Long AI Machine Learning

Authors:
Dr. James Crowder, Systems Fellow, Colorado Engineering Inc.
Dr. Shelli Friess, LPC, NCC, ACS, School of Counseling, Walden University
Dr. John Carbone, Department of Electrical and Computer Eng., Southern Methodist University

Abstract:
Current machine learning architectures, strategies, and methods are typically static and non-interactive, making them incapable of adapting to changing and/or heterogeneous data environments, either in real-time, or in near-real-time. Typically, in real-time applications, large amounts of disparate data must be processed, learned from, and actionable intelligence provided in terms of recognition of evolving activities. Applications like Rapid Situational Awareness (RSA) used for support of critical systems (e.g., Battlefield Management and Control) require critical analytical assessment and decision support by automatically processing massive and increasingly amounts of data to provide recognition of evolving events, alerts, and providing actionable intelligence to operators and analysts.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Anytime Learning: A Step Toward Life-Long AI Machine Learning (73 downloads)

Posted on

Systems Level Thinking for Artificial Intelligent Systems

Authors:
Dr. James Crowder, Systems Fellow, Colorado Engineering Inc.
Dr. Shelli Friess, LPC, NCC, ACS, School of Counseling, Walden University

Abstract:
Systems thinking and its perspective have become more and more prevalent in engineering, business, and management. Systems thinking enables systems, people, and/or organizations to study and understand interaction between individuals (or subsystems), departments (or system elements), and/or business units (or legacy systems) within an organization or overall system-of-systems design. The elements considered in systems thinking, then, predict and produce behaviors that are fed back into the overall systems thinking process to produce necessary changes within the organization or system to produce the desired behavior or results. In short, systems thinking seeks to understand how different parts of the system influence one another and influence the entire system. Unlike critical thinking, systems thinking requires many skills to create a holistic view of an entire system and its current and predicted behavior. The purpose of this paper is to begin the discussion and lay out the concepts for systems-level thinking for artificial intelligence.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Systems Level Thinking for Artificial Intelligent Systems (57 downloads)

Posted on

Surveillance Mission Planning: Model, Performance Measure, Bi-Objective Analysis, Partial Surveils

Authors:
Ryan Friese, Pacific Northwest National Laboratory (PNNL)
Dr. James Crowder, Colorado Engineering Inc.
Howard Jay Siegel, Elect. and Computer Engineering and Computer Science Depts., Colorado State University
John Carbone, Computer Science Dept., Southern Methodist University

Abstract:
We examine the trade-offs between energy and performance when conducting surveillance mission planning in a multi-vehicle, multi-target, multi-sensor environment. The vehicles are heterogeneous UAVs (unmanned aerial vehicles) that must surveil heterogeneous targets across a geographically distributed area within a given period of time (here, 24 hours). We design a new model for surveilling heterogeneous targets by heterogeneous UAVs. Based on this new model, we define a new system-wide surveillance performance measure that includes the targets surveilled, the number of times each target is surveilled, the UAV used for each surveil, the sensor type on the UAV that is used for each surveil, the priority of each target, and the allowance of partial surveil times. Then we implemented a genetic algorithm (GA) for a bi-objective analysis of energy versus surveillance performance for a set of realistic system parameters. The fitness function for this GA is based on our new model and our new performance measure. We construct a Pareto front of mappings of UAVs and sensors to targets to use to study trade-offs between the two conflicting objectives of maximizing surveillance performance and minimizing energy consumed. We also examine how allowing partial surveils of targets can impact system performance.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Surveillance Mission Planning: Model, Performance Measure, Bi-Objective Analysis, Partial Surveils (76 downloads)

Posted on

Fuzzy Collision Avoidance Algorithm for UAVs

Authors:
Dr. James A. Crowder, Systems Fellow, Colorado Engineering Inc.
Dr. John Carbone, Department of Electrical and Computer Engineering, Southern Methodist University

Abstract:
Multi-vehicle, multi-route conflict (collision) avoidance is an issue that will become prevalent over the next decade. With the dramatic increase in the number of UAV drones and number of separate companies planning to employ UAVs for everything from aerial reconnaissance to delivery to search and rescue operations, understanding how to simply and effectively keep UAVs from coming in conflict with each other is a major concern. One of the issues associated with conflict avoidance is to not have to tax the computational, memory, and energy usage of the UAV to employ a conflict resolution strategy. Here we present a fuzzy-based algorithm for detection and implementation of conflict avoidance for UAVs/ drones that will not adversely affect the power, weight, or size of the individual units.

What we propose is a simple, fuzzy logic-driven algorithm for collision/conflict avoidance for UAVs or small drones. The use of a random, fuzzy-based algorithm allows for fast, efficient computation. There would be a software agent on the drones/UAVs that would manage the collision/conflict avoidance system and send information to the flight control system for speed/directional change, depending on the output of the collision/conflict avoidance algorithms. Included will be a discussion of the ISCAN© radar system capable of implanting these algorithms on small drones.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Fuzzy Collision Avoidance Algorithm for UAVs (73 downloads)

Posted on

Artificial Intelligence Profiles for Foundational Counselor Training Sessions

Authors:
Dr. James Crowder, Systems Fellow, Colorado Engineering Inc.
Dr. Shelli Friess, LPC, NCC, ACS, School of Counseling, Walden University

Abstract:
Training for practicing counselors involves training to help people learn to cope more effectively with mental health issues and developmental issues, along with life issues in general. Counselors are trained in a variety of techniques, based on the best available research and minimal standards based on professional accreditation. However, live training in the beginning, with actual patients is difficult since it is not practical to have counselors “practice” on people with actual psychological issues. Presented here is a proposed training system, called the “Cognitive, Interactive, Psychological Training System (CIPTS), which provides artificially intelligent profiles instantiated as “avatars for interaction with counselors,” based on a set of different personality profiles created by a team of leading counselor educators and represent a variety of psychological, social, and biopsychosocial health issues that can be used to help train counselors in a non-live, non-threatening environment, but yet valuable.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Artificial Intelligence Profiles for Foundational Counselor Training Sessions (83 downloads)

Posted on

Human Cognition and Artificial Intelligence: The Artificial Prefrontal Cortex Revisited

Authors:
Dr. James A. Crowder, Systems Fellow, Colorado Engineering Inc.
Dr. Shelli Friess, LPC, NCC, ACS, School of Counseling, Walden University

Abstract:
Many researchers have postulated that human cognition is implemented by a multitude of relatively small, special purpose processes, almost always unconscious communication between them is rare and over a narrow bandwidth. Coalitions of such processes find their way into consciousness. This limited capacity work space available for our cognition serves to broadcast the message of the coalition to all the unconscious processors within the human brain, to recruit other processors to join in handling the current novel situation, or in solving the current problem. Therefore, consciousness in this theory allows us to deal with novelty or problematic situations that can’t be dealt with efficiently, or at all, by habituated unconscious processes. It provides access to appropriately useful resources, thereby solving the relevance problem. Here we present the design and testing of and Artificial Prefrontal Cortex (APC) model for use cognitive state transition and management in artificial cognition systems.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Human Cognition and Artificial Intelligence: The Artificial Prefrontal Cortex Revisited (4 downloads)

Posted on

Methodologies for Continuous Life-long Machine Learning for AI Systems

Authors:
Dr. James A. Crowder, Systems Fellow, Colorado Engineering Inc.
John N. Carbone, Electrical and Computer Engineering Department, Southern Methodist University

Abstract:
Current machine learning architectures, strategies, and methods are typically static and non-interactive, making them incapable of adapting to changing and/or heterogeneous data environments, either in real-time, or in near-real-time. Typically, in real-time applications, large amounts of disparate data must be processed, learned from, and actionable
intelligence provided in terms of recognition of evolving activities….

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Methodologies for Continuous Life-long Machine Learning for AI Systems (9 downloads)

Posted on

Enhancing Prosthetic Musculotendinous Proprioception Utilizing Multidisciplinary Artificially Intelligent Learning Approach

Authors:
John N. Carbone, Electrical and Computer Engineering Department, Southern Methodist University
Ryan A. Carbone, Biological Sciences, Baylor University
Dr. James A. Crowder, Systems Fellow, Colorado Engineering Inc.

Abstract:
Historically, research shows analysis, characterization, and classification of complex heterogeneous non-linear systems and interactions have been difficult to accurately understand and effectively model. Advanced biophysical and biomechanical prosthesis research shows that development of patient specific physiologically meaningful musculotendinous proprioception would generate a marked impact on reflex control, fine volitional motor control, and overall user experience.

Full access to this whitepaper requires submitting the form on the following page. Click the link below to continue.

Enhancing Prosthetic Musculotendinous Proprioception utilizing Multidisciplinary Artificially Intelligent Learning Approach (5 downloads)