A basic agent

A basic agent has been constructed which integrates limited natural language understanding and generation, temporal planning and reasoning, plan execution, simulated symbolic perception, episodic memory, and some general world knowledge. The agent is cast as a robot submarine operating in a two‐dimensional simulated “Seaworld” about which it has only partial knowledge. It can communicate with people in a vocabulary of about 800 common English words using a medium coverage grammar. The agent maintains an episodic memory of events in its life and has a limited ability to reflect on those events. A person can make statements to the agent, ask it questions, and give it commands. In response to commands, a temporal task planner is invoked to synthesize a plan, which is then executed at an appropriate future time. A large variety of temporal references in natural language are interpreted with respect to agent time. The agent can form and retain compound future plans, and replan in response to new information or new commands. Natural language verbs are represented in a state transition semantics for compatibility with the planner. The agent is able to give terse answers to questions about its past experiences, present activities and perceptions, future intentions, and general knowledge. No other artificial intelligence artifact with this range of capabilities has previously been constructed.

[1]  Guy Lapalme,et al.  Text generation , 1990 .

[2]  Kathleen McKeown,et al.  Text generation: using discourse strategies and focus constraints to generate natural language text , 1985 .

[3]  Nils J. Nilsson,et al.  Artificial Intelligence Prepares for 2001 , 1983, AI Mag..

[4]  P. Johnson-Laird.  Formal Semantics and the Psychology of Meaning , 1982 .

[5]  Robert Wilensky.  Some Problems and Proposals for Knowledge Representation , 1987 .

[6]  R. Schank,et al.  Inside Computer Understanding: Five Programs Plus Miniatures , 1982 .

[7]  Warren Teitelman.  Automated programmering: the programmer's assistant , 1972, AFIPS '72 (Fall, part II).

[8]  David L. Waltz.  The State-of-the-Art in Natural Language Understanding. , 1981 .

[9]  Lenhart K. Schubert,et al.  Toward a State Based Conceptual Representation , 1975, IJCAI.

[10]  L. Cermak.  Human memory and amnesia , 1982 .

[11]  C. Ogden.  The system of Basic English , 1932 .

[12]  Timothy W. Bickmore.  An Object-Oriented Approach To Tactical Text Generation , 1989, Defense, Security, and Sensing.

[13]  Yorick Wilks,et al.  Transfer Semantics in an Operating System Consultant: The Formalization of Actions Involving Object Transfer , 1987, IJCAI.

[14]  Stephen A. Vere.  Splicing Plans to Achieve Misordered Goals , 1985, IJCAI.

[15]  E. Tulving,et al.  Episodic and semantic memory , 1972 .

[16]  Terry Winograd,et al.  Understanding natural language , 1974 .

[17]  Roger C. Schank,et al.  The Current State of AI: One Man's Opinion , 1983, AI Mag..

[18]  David L. Waltz,et al.  A Knowledge-Based Approach to Language Processing : A Progress Report , 2002 .

[19]  Janet L. Kolodner,et al.  Knowledge-based self-organizing memory for events , 1984 .

[20]  Steven Vere.  Temporal Scope of Assertions and Window Cutoff , 1985, IJCAI.

[21]  Paul Morris,et al.  Don't Be Stupid , 1981, IJCAI.

[22]  G. Miller,et al.  Language and Perception , 1976 .

[23]  Laurence Danlos,et al.  A French and English Syntactic Component for Generation , 1987 .

[24]  Gary Conrad Borchardt,et al.  A Computer Model for the Representation and Identification of Physical Events , 1984 .