Self-Preservation Mechanisms for Cognitive Software Agents

Fabrizio Morbini received a Laurea in Electronic Engineering from Università degli Studi di Brescia in 2002, with a thesis on extensions to the DISCOPLAN system supervised by Prof. Alfonso Gerevini. He began graduate studies at the University of Rochester in the fall of 2003. He pursued his research on the EPILOG reasoner, revising and extending it to support his work towards a self-aware agent, under the guidance of Prof. Lenhart Schubert. He received his MS from the University of Rochester in 2005.

ACM SIGPLAN Notices, 2006

Software needs to grow up and become responsible for itself and its own future by participating in its own installation and customization, maintaining its own health, and adapting itself to new circumstances, new users, and new uses. To create such software will require us to change some of our underlying assumptions about how we write programs. A promising approach seems to be to separate software that does the work (allopoietic)from software that keeps the system alive (autopoietic).

2011 Fifth IEEE Conference on Self-Adaptive and Self-Organizing Systems Workshops, 2011

Novel computing systems are increasingly being composed of large numbers of heterogeneous components, each with potentially different goals or local perspectives, and connected in networks which change over time. Management of such systems quickly becomes infeasible for humans. As such, future computing systems should be able to achieve advanced levels of autonomous behaviour. In this context, the system's ability to be self-aware and be able to self-express becomes important. This paper surveys definitions and current understanding of self-awareness and self-expression in biology and cognitive science. Subsequently, previous efforts to apply these concepts to computing systems are described. This has enabled the development of novel working definitions for selfawareness and self-expression within the context of computing systems.

The use of computing systems is nowadays something that is taken for granted. One just needs to look around and will easily see that there is a computation process going on in almost every direction. Moreover, now such processes are not just restricted to personal computers but to devices such as cellular phones, PDAs, laptops, etc. Furthermore, these devices are not isolated units of processes but are interconnected and can send and receive information at any time, anywhere. The demands that now people and current business models place on computing systems go from running a simple application, where the hardware was not built specifically for such application, to a cooperative network where all constituents are using a variety of systems and commands. Managing all these networked devices as a whole in a robust, safe, secure and transparent manner demands a lot of resources and time. This article presents the steps that have been taken in order to propose a new system architecture that ensures the well-being of an IT infrastructure by providing a self-protection and self-healing autonomic computing features. The model is a combination of a multiagent design and learning techniques. The main idea is to mold each component that a typical operating system manages as an agent, incorporate performance criterion evaluators to select the best candidate to perform a task and implement specialized agents to supervise and learn from threats and normal program executions in order to keep the system running (self-protection and self-healing). The system was evaluated using a multiagent simulation. Consequently, a programming language was created, named HAL, which allowed the simulation of applications, both benign and harmful, running in the multiagent environment. Thus, the simulated prototype is very close to a computer that runs applications, allowing a proper evaluation of the proposed design.

2000

Here we will briefly describe action selection and language generation mechanisms in two'life-like'software agents, CMattie and IDA, and discuss issues that bear on the topics of architectures for behavior control, interdependencies between emotions and goal-based behaviors, and coordination of scripted and improvised behaviors. These agents are life-like in the sense of interacting with humans via email in natural language. They are'conscious' only in the sense of implementing a psychological theory of consciousness [3, 4].

Neural Network World, 2000

Here we describe mechanisms for a half-dozen or so different types of learning to be implemented in “conscious” software agents, and speculate briefly on their implications for human learning and development. In particular, we're concerned with conceptual learning and behavioral learning in two “conscious” software agents, namely, CMattie and IDA. We offer computational mechanisms for such learning.

We present a model for error recovery and interrupt handling by a reasoning, acting, and linguistically-competent cognitive agent. Faced with an emergency situation, the agent reasons about what it needs to do and what it is currently doing to decide what to do next. Its reasoning is based on general context-sensitive domain knowledge about the priority of acts. Such knowledge may be provided to the agent in natural language while it is acting, rather than being hardwired into the agent's knowledge base as is the case with most existing systems.

Computer, 2015

A dvanced computing systems generally contain many heterogeneous subsystems, each with a local perspective and goal set, which interconnect in changing network topologies. The subsystems must interact with each other and with humans in ways that are difficult to understand and predict while robustly maintaining performance, reliability, and security even with unforeseen dynamics, such as system failures or changing goals. To meet these stringent requirements, computational systemsranging from robot swarms and personal music devices to Web services and sensor networks-must achieve sophisticated autonomous behavior by adapting themselves at runtime and through learning processes that enable ongoing self-change. Managing tradeoffs among conflicting local and global goals at runtime requires considerable awareness of both the system's current state and its environment. Yet researchers have only recently begun to understand the implications of selfawareness principles and how to translate them into system engineering. Consequently, there is no general methodology for architecting self-aware systems or for comparing their self-awareness capabilities. To address this need, we examined how human selfawareness can serve as a source of inspiration for a new notion of computational self-awareness and associated self-expression, and we developed a general framework for describing a computing system's self-awareness properties. As part of this work, we created a reference architecture, which we used to derive architectural patterns for

Cognitive Science Quarterly, 2002