role of pattern recognition in computer · pdf filefrom the game world and to construct...

24
Role of Pattern Recognition in Computer Games Asst. Prof. Dr. Chumphol Bunkhumpornpat Department of Computer Science Faculty of Science Chiang Mai University

Upload: vocong

Post on 24-Feb-2018

215 views

Category:

Documents


1 download

TRANSCRIPT

Role of Pattern Recognition in Computer Games

Asst. Prof. Dr. Chumphol Bunkhumpornpat Department of Computer Science

Faculty of Science Chiang Mai University

Introduction

• Computer games are an unique application area for pattern recognition.

• Computer games are the products of their developers, and, at first sight, it is easy to assume that the developers know inherently what phenomena occur in their game world.

204453: Pattern Recognition 2

Introduction (cont.)

• To implement challenging synthetic opponents computer should recognize the behavior of a human player.

• In this context, the purpose of pattern recognition is to abstract relevant information from the game world and to construct concepts and to deduce patterns from this information.

• These concepts are needed for decision-making system.

204453: Pattern Recognition 3

Introduction (cont.)

• Pattern recognition could provide essential information for the decision-making system, like what phenomena and events have occurred in the observed (dynamic) system or world.

• Pattern recognition can be utilized in finetuning the rules of the game world.

204453: Pattern Recognition 4

Relations between the world, pattern recognition, and decision-making

204453: Pattern Recognition 5

Pattern Recognition in Computer Games

• RTS (Real-Time Strategy)

– It remedies threats and strategizes.

• Fighting

– It reacts to enemy's frequent moves.

• Sports

– It reads the match.

204453: Pattern Recognition 6

Perspective Views of PR in CGs

• Decision Making Levels

• Stance Towards Players

• Game Graph

204453: Pattern Recognition 7

Decision Making Levels

• Strategical

• Tactical

• Operational

204453: Pattern Recognition 8

Strategical

• Long Period of Time

• Large Amount of Data

– Inhabitants

– Items

– Events

• High Cost of a Wrong Decision

• Speculative: What-If Scenarios

• Offline: Background

204453: Pattern Recognition 9

Tactical

• It connects between strategical and operational.

• It considers a group of entities and their cooperation.

• It is made more frequently than strategical, pattern recognition has less time to use.

• Consequently, the quality cannot be as high as on upper level.

204453: Pattern Recognition 10

Operational

• Concrete

• Atomatory Entities

• Reactive

• Short-Term

• Real-Time

• Online: in-the-Field

• Irrevocable Problems

204453: Pattern Recognition 11

Stance Towards Players

• Enemy

• Ally

• Neutral

204453: Pattern Recognition 12

Enemy

• It requires modus operandi of the player.

• It provides challenge.

204453: Pattern Recognition 13

Ally

• It accounts human perspective but not decision making system.

• Synthetic Reconnaissance Officer

– It reports on enemy movement.

– It suggests effective counteractions.

204453: Pattern Recognition 14

Neutral

• Autonomous Camera Director – It controls camera movement in sports games.

– It dictates by television practice.

• Referee – It allows the play continue.

– It interprets causality between offence and subsequent events.

• Interface should adapt dynamically to the needs of a player.

204453: Pattern Recognition 15

Game Graph

• A story progresses linearly.

• A game provides an illusion of free will.

204453: Pattern Recognition 16

Game Graph (cont.)

• Nodes

– Game States

• Direct Arches

– Actions

204453: Pattern Recognition 17

Game Graph (cont.)

• Outdegree

– The number of direct arches leaving a node

• Indegree

– The number of direct arches entering the node

204453: Pattern Recognition 18

Game Graph (cont.)

• The greater the outdegree means more freedom the player has.

• Uniqueness of a response can be measured as the indegree.

• The game properties can be analyzed through graph concepts (e.g., repetitiveness corresponds to cycles in the graph).

204453: Pattern Recognition 19

A linear progression (e.g., a story) allows no diversion.

204453: Pattern Recognition 20

In this case node Si has an outdegree of 2.

204453: Pattern Recognition 21

In this case node Sn has an indegree of 3.

204453: Pattern Recognition 22

Although the number of possible actions is the same as in the previous case,

each action has now a unique response.

204453: Pattern Recognition 23

Reference

• T. Kaukoranta, J. Smed, and H. Hakonen, Role of Pattern Recognition in Computer Games, Proceedings of the 2nd International Conference on Application and Development of Computer Games, pp. 189–94, Hong Kong SAR, China, 2003.

204453: Pattern Recognition 24