New Challenges for Character-Based AI for Games
Published 1 January 2002
Bruce Blumberg
Citations37
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is believed that character-based AI systems can draw from and contribute to the state of the art in such areas as pattern recognition and planning.
Abstract
Based on the recent surge in interest in both academia and the games industry in character-based AI, and in-spired by work from a range of literature from animal learning and psychology to classic AI, we suggest some potential “next steps ” towards the creation of virtual autonomous characters that are lifelike, intelligent and convey empathy. We believe that character-based AI systems can draw from and contribute to the state of the art in such areas as pattern recognition and planning. Introduction: AI’s Next Steps First things first: what is meant by character-based AI? It is a category that is especially meaningful in games, to distinguish systems that seek to simulate the behavior of a single agent as opposed to strategic AIs or turn-based game-
Keywords
Computer ScienceEngineering
Cognition & EmotionAn argument for basic emotions
9,365 Citations1992Paul Ekman
This work has shown that not only the intensity of an emotion but also its direction may vary greatly both in the amygdala and in the brain during the course of emotion regulation.
The Intentional Stance
3,862 Citations1987Daniel C. Dennett
Artificial fishes
621 Citations1994Xiaoyuan Tu, Demetri Terzopoulos
A framework for animation that can achieve the intricacy of motion evident in certain natural ecosystems with minimal input from the animator is proposed and a physics-based, virtual marine world is developed.
Cognition: Exploring the Science of the Mind
424 Citations1996Daniel Reisberg
It knows what you're going to do
240 Citations2001John E. Laird
An AI bot for the game Quake II that tries to incorporate some of the missing capabilities of human players, developed in the Soar architecture and uses dynamical hierarchical task decomposition to organize it knowledge and actions.
DSpace@MIT (Massachusetts Institute of Technology)Old tricks, new dogs: ethology and interactive creatures
203 Citations1997Bruce Blumberg, Pattie Maes
The MIT Press eBooksAction-Selection in Hamsterdam: Lessons from Ethology
145 Citations1994Bruce Blumberg
A computational model of action-selection is presented, which by drawing on ideas from Ethology, addresses a number of problems which have been noted in models proposed to date including the need for greater control over the temporal aspects of behavior, theneed for a loose hierarchical structure with information sharing, and the need of a flexible means of modeling the influence of internal and external factors.
Sympathetic interfaces
142 Citations1999Michael P. Johnson, Andrew D. Wilson +3 more
The concept of a sympathetic interace for controlling an animated synthetic character in a 3D virtualenvironment using a plush doll embedded with wireless sensors to manipulate the virtual character in an iconic and intentional manner is introduced.
Creatures
104 Citations1997Stephen Grand, Dave Cliff +1 more
A technical description of Creatures, a commercial home-entertainment software package that provides a simulated environment in which exist a number of synthetic agents that a user can interact with in real-time, and a discussion of the scientific implications of the system.
A layered brain architecture for synthetic creatures
89 Citations2001Damián Isla, Robert Burke +2 more
A new layered brain architecture for simulated autonomous and semi-autonomous creatures that inhabit graphical worlds that communicate through common access to an internal mental blackboard is described.
Creature Smarts: The Art and Architecture of a Virtual Brain
77 Citations2001Robert Burke, Damián Isla +3 more
What motivates the Synthetic Characters group at the MIT Media Lab to build complete systems that can interact with each other and with human participants?
Interactive Training for Synthetic Characters
39 Citations2000Song-Yee Yoon, Robert Burke +2 more
Inspired by pet training, a character is implemented that can be trained using the “clicker training” technique and the necessary plasticity of system interconnections shaped by associations and rewards that is required by clicker training was integrated into the creature kernel framework.
DSpace@MIT (Massachusetts Institute of Technology)Interactivity and emotion through cinematography
13 Citations1999William Michael Tomlinson
Thesis (S.M.)--Massachusetts Institute of Technology, Program in Media Arts & Sciences, 1999.
Social Behavior, Emotion and Learning in a Pack of Virtual Wolves
11 Citations2001Bill Tomlinson, Bruce Blumberg
The computational representations that allow social learning in the authors' virtual wolves demonstrate the intimate connections among social behavior, emotion and learning and are applicable to building a wider range of socially intelligent agents.
DSpace@MIT (Massachusetts Institute of Technology)Observation-based expectation generation and response for behavior-based artificial creatures
11 Citations1999Christopher Kline
This thesis addresses the need to generate short-term, observation-based expectations about the world and react appropriately to the violation of those expectations and proposes a model for generating expectations and responding to their violation.
DSpace@MIT (Massachusetts Institute of Technology)The virtual hippocampus : spatial common sense for synthetic creatures
9 Citations2001Damián Isla
This thesis investigates the problem of spatial perception and reasoning in synthetic creatures by taking the Hippocampus a brain structure that is strongly believed to constitute a "cognitive mapping" system in animals as an inspiration and demonstrating a system that visually learns cognitive maps.
DSpace@MIT (Massachusetts Institute of Technology)It's about time : temporal representations for synthetic characters
5 Citations2001Robert Burke
This thesis integrates representations for time and rate into a behavior-based architecture for autonomous virtual creatures that allows these creatures to discover and refine their understanding of apparent temporal causality relationships which may or may not involve self-action.