A methodology has been conceived for efficient synthesis of dynamical models that simulate common-sense decision-making processes. This methodology is intended to contribute to the design of artificial-intelligence systems that could imitate human commonsense decision making or assist humans in making correct decisions in unanticipated circumstances. This methodology is a product of continuing research on mathematical models of the behaviors of single- and multi-agent systems known in biology, economics, and sociology, ranging from a single-cell organism at one extreme to the whole of human society at the other extreme. Earlier results of this research were reported in several prior NASA Tech Briefs articles, the three most recent and relevant being “Characteristics of Dynamics of Intelligent Systems” (NPO-21037), NASA Tech Briefs, Vol. 26, No. 12 (December 2002), page 48; “Self-Supervised Dynamical Systems” (NPO-30634), NASA Tech Briefs, Vol. 27, No. 3 (March 2003), page 72; and “Complexity for Survival of Living Systems” (NPO-43302), NASA Tech Briefs, Vol. 33, No. 7 (July 2009), page 62.
The methodology involves the concepts reported previously, albeit viewed from a different perspective. One of the main underlying ideas is to extend the application of physical first principles to the behaviors of living systems. Models of motor dynamics are used to simulate the observable behaviors of systems or objects of interest, and models of mental dynamics are used to represent the evolution of the corresponding knowledge bases. For a given system, the knowledge base is modeled in the form of probability distributions and the mental dynamics is represented by models of the evolution of the probability densities or, equivalently, models of flows of information.
Autonomy is imparted to the decision-making process by feedback from mental to motor dynamics. This feedback replaces unavailable external information by information stored in the internal knowledge base. Representation of the dynamical models in a parameterized form reduces the task of commonsense-based decision making to a solution of the following hetero-associated-memory problem: store a set of m predetermined stochastic processes given by their probability distributions in such a way that when presented with an unexpected change in the form of an input out of the set of M inputs, the coupled motor-mental dynamics converges to the corresponding one of the m pre-assigned stochastic process, and a sample of this process represents the decision.
This work was done by Michail Zak of Caltech for NASA’s Jet Propulsion Laboratory. For more information, download the Technical Support Package (free white paper) at www.techbriefs.com/tsp under the Information Sciences category. NPO-44114
This Brief includes a Technical Support Package (TSP).
Modeling Common-Sense Decisions in Artificial Intelligence
(reference NPO-44114) is currently available for download from the TSP library.
Don't have an account?
Overview
The document titled "Modeling Common-Sense Decisions in Artificial Intelligence" (NPO-44114) from NASA's Jet Propulsion Laboratory addresses the critical issue of human errors leading to miscommunications in NASA missions. To mitigate these errors, the document presents the development of an artificial assistant designed to enhance decision-making processes through a sophisticated knowledge base.
The core of the solution lies in a novel architecture that integrates motor dynamics, which simulate the actual behavior of objects, with mental dynamics that represent the evolution of a knowledge base. This dual approach allows the system to incorporate information flows into the motor dynamics, enabling autonomous decision-making. The feedback mechanism from mental to motor dynamics is crucial, as it allows the system to replace unavailable external information with an internal knowledge base, represented as probability distributions.
The methodology proposed in the document reduces the complexity of common-sense decision-making to a hetero-associated memory problem. This involves storing a set of stochastic processes defined by their probability distributions. When the system encounters an unexpected input, it can effectively converge to the corresponding pre-assigned stochastic process, thereby generating a decision based on a sample of that process.
The document emphasizes the novelty of this approach, highlighting its potential for efficient synthesis of dynamical models that simulate common-sense decision-making processes. This advancement is particularly relevant in the context of aerospace applications, where the stakes are high, and the need for reliable decision-making tools is paramount.
In addition to the technical details, the document serves as a part of NASA's Commercial Technology Program, aiming to disseminate aerospace-related developments with broader technological, scientific, or commercial implications. It encourages further exploration and collaboration through the NASA Innovative Partnerships Program.
For additional inquiries or information, the document provides contact details for the Innovative Technology Assets Management at JPL, emphasizing the commitment to advancing research and technology in this field.
Overall, this document represents a significant step forward in the integration of artificial intelligence with common-sense reasoning, aiming to enhance the reliability and efficiency of decision-making in critical aerospace missions.
