How qualitative spatial reasoning can improve strategy game AIs

AAAI Conferences

Spatial reasoning is a major source of difficulties for strategy game AIs. We conjecture that qualitative spatial reasoning techniques can help overcome these difficulties. We briefly review the relevant qualitative reasoning ideas, and outline four potential advantages of our approach. We describe two explorations in progress: How visual routines can be used to quickly compute qualitative spatial descriptions for war games, and how qualitative descriptions can help in path-finding. Introduction Creating good strategy game AIs is hard. Spatial reasoning is a major source of difficulties: Terrain is of vital importance in war games, and geography is key in Civilization-style empire/trading games. Since today's strategy AI's are tightly bound to the underlying game world simulation, it is hard to start their development before the game world is up and rurming, and harder still to reuse the algorithms and representations in a new game, unless the underlying engine is extremely similar to the old engine.


Qualitative Spatial Reasoning Extracting and Reasoning with Spatial Aggregates

AI Magazine

Reasoning about spatial data is a key task in many applications, including geographic information systems, meteorological and fluid-flow analysis, computer-aided design, and protein structure databases. Such applications often require the identifi- cation and manipulation of qualitative spatial representations, for example, to detect whether one object will soon occlude another in a digital image or efficiently determine relationships between a proposed road and wetland regions in a geographic data set. Qualitative spatial reasoning (QSR) provides representational primitives (a spatial "vocabulary") and inference mechanisms for these tasks. This article first reviews representative work on QSR for data-poor scenarios, where the goal is to design representations that can answer qualitative queries without much numeric information. It then turns to the data-rich case, where the goal is to derive and manipulate qualitative spatial representations that efficiently and correctly abstract important spatial aspects of the underlying data for use in subsequent tasks. This article focuses on how a particular QSR system, SPATIAL AGGREGATION, can help answer spatial queries for scientific and engineering data sets. A case study application of weather analysis illustrates the effective representation and reasoning supported by both data-poor and data-rich forms of QSR


Qualitative Spatial Reasoning for Rule Compliant Agent Navigation

AAAI Conferences

Artificial agents participating in public traffic must respect rules that regulate traffic. Rule sets are commonly formulated in natural language using purely qualitative terms. We present a case study on how to realize rule compliant agent control in the domain of sea navigation by using qualitative spatial reasoning techniques.


SparQ--A Spatial Reasoning Toolbox

AAAI Conferences

SparQ is a toolbox for qualitative spatial reasoning. Interpreting reasoning in a broad sense, SparQ covers mapping information from quantitative to qualitative, applying constraint reasoning to qualitative information, reasoning about calculi, and mapping qualitative information back to the quantitative domain. The toolbox is designed for extensibility and released under the GNU GPL public license for free software.


Qualitative Spatial Reasoning Extracting and Reasoning with Spatial Aggregates

AI Magazine

Reasoning about spatial data is a key task in many applications, including geographic information systems, meteorological and fluid-flow analysis, computer-aided design, and protein structure databases. Qualitative spatial reasoning (QSR) provides representational primitives (a spatial "vocabulary") and inference mechanisms for these tasks. It then turns to the data-rich case, where the goal is to derive and manipulate qualitative spatial representations that efficiently and correctly abstract important spatial aspects of the underlying data for use in subsequent tasks. This article focuses on how a particular QSR system, SPATIAL AGGREGATION, can help answer spatial queries for scientific and engineering data sets.