Index Prev Up Next

$\newcommand{\N}{\mathbb N} \newcommand{\Z}{\mathbb Z} \newcommand{\Q}{\mathbb Q} \newcommand{\R}{\mathbb R} \newcommand{\lt}{<} \newcommand{\gt}{>} \newcommand{\amp}{&} \definecolor{fillinmathshade}{gray}{0.9} \newcommand{\fillinmath}[1]{\mathchoice{\colorbox{fillinmathshade}{$\displaystyle \phantom{\,#1\,}$}}{\colorbox{fillinmathshade}{$\textstyle \phantom{\,#1\,}$}}{\colorbox{fillinmathshade}{$\scriptstyle \phantom{\,#1\,}$}}{\colorbox{fillinmathshade}{$\scriptscriptstyle\phantom{\,#1\,}$}}} $

Introduction

This chapter moves beyond a single robot working in isolation to consider fleets of robots that must coordinate with one another. You will start by contrasting centralized and decentralized control architectures for multi-agent systems, then see how swarm robotics achieves complex, coordinated group behavior from nothing more than simple local rules and indirect communication (stigmergy). From there you will study Multi-Robot Task Allocation (MRTA), including market-based auction protocols that let a fleet decide which robot should handle which task, and priority rules that keep robots from colliding when they share the same space. The chapter closes with a hands-on simulation that builds a working auction system from scratch.

Prev Top Next