This technical definition will only make sense toe reader by Ch. 4, once goals and management processes have been described. All that matters forrs section is that a difference between goals and perturbance be noted by the reader. Astate perturbance is not a goal, but it arises out of the processing of goals. In Ch. 7, arelation00 perturbance and "emotion" is discussed. 43 . Sloman says of certain moods that they are "persistent states with dispositional power to color and modify a host of other states and processes. Such moodscan39061-6 be caused by cognitive events with semantic content, though they need not be.[...]0-64000 their control function does not require specific semantic content, though theycan0371-62 cognitive processes that do involve semantic content." (Sloman, 1992b Section 6).A 39642 view is taken in (Oatley, 1992). To be more precise, moods are temporary control stateswhich9881-5 the prominence of some motivators while decreasing others. In particular, they affectthe 41330-5 that certain "goal generators" are triggered. Moreover, moods affect the valenceofce 39476 evaluations, and the likelihood of affective evaluations (perhaps by modifying thresholdsofsholds 42 that trigger evaluations). It is not yet clear whether moods as defined here are9531 - or whether they merely emerge as side-effects of functional processes. . A reflex is a ballistic form of behaviour that can be specified by a narrow setw rules based on input integration and a narrow amount of internal state. There aretwo0981 of reflexes: simple reflexes and fixed action patterns. A simple reflex involves oneaction,-43000 a fixed action pattern involves a collection of actions. Usually, at most only asmall-4120 of perceptual feedback influences reflex action. This would require a definit...

A good software architecture facilitates application system development, promotes achievement of functional requirements, and supports system reconfiguration. We present a domain-specific software architecture (DSSA) that we have developed for a large application domain of adaptive intelligent systems (AISs). The DSSA provides: (a) an AIS reference architecture designed to meet the functional requirements shared by applications in this domain, (b) principles for decomposing expertise into highly reusable components, and (c) an application configuration method for selecting relevant components from a library and automatically configuring instances of those components in an instance of the architecture. The AIS reference architecture incorporates features of layered, pipe and filter, and blackboard style architectures. We describe three studies demonstrating the utility of our architecture in the sub-domain of mobile office robots and identify software engineering principles embodied in ...

We present an autonomous agent architecture and its component subsystems that integrate important abilities needed for robust, flexible performance in dynamic environments. These abilities involve appropriate reaction to environmental situations given the agent's goals; selective attention to multiple, competing goals; planning new action routines when innovation beyond designer-provided routines is necessary; and learning the effects of actions so that the planner can use them to build ever more reliable plans. The teleo-reactive format allows actions to be closely coupled to continuous environmental feedback and is also especially compatible with conventional AI planning and learning mechanisms. The workings of the proposed architecture and its subsystems are illustrated in a simulated robot domain. We conclude by noting areas where future work is needed.

We present a framework for active agents, that integrates both the goal achievement desire of traditional A.I. and the survival instinct of new A.I. This framework is based on motivations as (1) a control mechanism for internal and external goal selection and (2) a generative mechanism for internal goal generation (usually resulting in one-action plans). We then present an architecture and an implementation of the framework, that enables the agent designer to preset the motivational profile of the agent, or the agent itself to change its own motivations on the fly (if it is able to recognize certains features of its environment). 3 1. Introduction The paper addresses the problem of acting in an environment: Given an environment (with its opportunities) and an autonomous agent (with its intellectual and physical capabilities), why should the agent act at all? Many approaches have be proposed to tackle with this problem. A first approach ("traditional A.I.") suggests that the main ac...

We present a new method, called motivation, for guiding the behavior of deliberative & reactive agents in various unpredictable environments. Psychology-inspired knowledge is used to orient the reasoning and behavior of the agent, eventually leading to spontaneous action. We provide an architecture in which motivations can be configured so as to make the agent adaptable to different kinds of environments. We describe a specific implementation of this method for the task of driving a mobile robot. Experimental results validate the approach by correlating motivations with the environment type, to get optimal performances of the agent. Keywords: planning and reasoning about action, agent architecture, plan use. 3 1. A Psychology Model of Agent Motivation In a classical article, Maslow [1954] identified an ordered list of the motivational factors that apparently drive human behavior. As summarized in the left column of Table 1, Maslow observed that people first seek to meet their phys...

The success of every mobile robot application hinges on the ability to navigate robustly in the real world. The problem of robust navigation is separable from the challenges faced by any particular robot application. We offer the Real-World Navigator as a solution architecture that includes a path planner, a map-based localizer, and a motion control loop that combines reactive avoidance modules with deliberate goal-based motion. Our architecture achieves a high degree of reliability by maintaining and reasoning about an explicit description of positional uncertainty. We provide two implementations of real-world robot systems that incorporate the Real-World Navigator. The Vagabond Project culminated in a robot that successfully navigated a portion of the Stanford University campus. The Scimmer project developed successful entries for the AAAI 1993 Robotics Competition, placing first in one of the two contests entered. 1 Introduction Current research on autonomous mobile robots has high...