The Impact of Perception on Agent Architectures

The advanced state of agent software and computing hardware makes it possible to construct complex agents and robots with multiple streams of input such as vision, speech, gestures and data. Such agents, like people (who also have access to multiple input streams), need to effectively manage the input in order to process important information within useful time bounds. This paper discusses processes and architectural components that are used to manage input data. In addition to reduced processing load, input management may also enable symbol grounding. However, some effects are not beneficial. For example, the agent will lack a full accounting of all input data, which means that standard explanation techniques will not function correctly. We propose several techniques for overcoming the disadvantages of input management.

[1]  Stanley J. Rosenschein,et al.  An architecture for adaptive intelligent systems , 1996 .

[2]  M. Potter.  Very short-term conceptual memory , 1993, Memory & cognition.

[3]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[4]  Richard C. Atkinson,et al.  Search and retrieval processes in long-term memory , 1968 .

[5]  J. Deutsch.  Perception and Communication , 1958, Nature.

[6]  A. Treisman.  Strategies and models of selective attention. , 1969, Psychological review.

[7]  Subutai Ahmad,et al.  Visit: an efficient computational model of human visual attention , 1992 .

[8]  R. Klatzky.  Human Memory: Structures And Processes , 1975 .

[9]  Randall W. Hill,et al.  Intelligent Agents for the Synthetic Battlefield: A Company of Rotary Wing Aircraft , 1997, AAAI/IAAI.

[10]  S. Harnad.  Symbol Grounding is an Empirical Problem: Neural Nets are Just a Candidate Component , 1993 .

[11]  Alonzo Kelly.  Adaptive Perception for Autonomous Vehicles , 1994 .

[12]  Alan D. Baddeley,et al.  Working memory or working attention , 1993 .

[13]  C. Mozer.  A connectionist m o d e l of selective attention in visual perception , 2020 .

[14]  Thierry Pun,et al.  A Bottom-Up Attention System for Active Vision , 1992, ECAI.

[15]  G. A. Miller.  THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1 , 1956 .

[16]  Christopher K. Riesbeck,et al.  Inside Case-Based Reasoning , 1989 .

[17]  Sharon Oviatt,et al.  Multimodal interactive maps: designing for human performance , 1997 .

[18]  Dean A. Pomerleau,et al.  RALPH: rapidly adapting lateral position handler , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[19]  Michael H. Coen,et al.  Design Principles for Intelligent Environments , 1998, AAAI/IAAI.

[20]  Nancy Martin,et al.  Programming Expert Systems in OPS5 - An Introduction to Rule-Based Programming(1) , 1985, Int. CMG Conference.

[21]  J. H. Neely.  Semantic priming and retrieval from lexical memory: Roles of inhibitionless spreading activation and limited-capacity attention. , 1977 .

[22]  P. A. Sandon.  Simulating Visual Attention , 1990, Journal of Cognitive Neuroscience.