This document summarizes a robot arena game project. It includes an architecture overview with three main components: world representation using an arena map, robot characters, and physics simulation; individual AI using behaviors, decision trees, and evaluation; and group AI using a defense-based strategy. It describes the arena map, robot characters, physics simulation, individual robot behaviors and decision making, and how group AI evaluates threats and provides support to robots in danger. The project presentation includes videos demonstrating the game's physics, behaviors, and defense-based group strategy.
17. Architecture Overview
● World Representation
○ Arena Map
○ Robot Character
○ Physics Simulation
● Individual AI
○ Behaviors
○ Decision Tree
○ Evaluation
● Group AI
○ Defense-based Strategy
○ Evaluation
18. Group AI (Defense-based Strategy)
When one robot is in danger, its teammates should
consider providing support.
ASI (Ally Safety Index) = ∑ (allyMass / reachTime)
HSI (Hide Safety Index) = selfMass / reachTime
ETI (Enemy Threat Index) =∑ (enemyMass / reachTime)
BTI (Border Threat Index) = 1 / reachTime
TSI (Total Safety Index) = ASI + HSI - ETI - BTI
19. Group AI
When one robot is in danger, its teammates should
consider providing support.
Path Risk (teammate) = ∑ (enemyMass / reachTime)
Gain (teammate) = TSI (seek) - TSI (current)
Group AI (Defense-based Strategy)
20. Group AI (Defense-based Strategy)
● Defense-based Strategy
When one robot is in danger, its teammates should
consider providing support.
for all Gain(robot) > 0 do
while(ally still in danger) do
GainMAX(robot) -> go guard the one in danger
end
end