On the crowdsourcing of behaviors for autonomous agents

TL;DR

This paper formalizes the process of designing autonomous agent behaviors through crowdsourced data, presenting a control-theoretic approach and an algorithmic solution validated by a numerical example.

Contribution

It introduces a novel control-based framework for crowdsourcing behaviors in autonomous agents and provides an algorithmic method for behavior synthesis from contributor data.

Findings

Formalization of crowdsourcing as a control problem

Development of an algorithmic behavior synthesis procedure

Validation through a numerical example

Abstract

This paper is concerned with the problem of designing, from data, agents that are able to craft their behavior from a number of contributors in order to fulfill some agent-specific task. This is not necessarily known to the contributors. After formalizing this crowdsourcing process as a control problem, we present a result to synthesize behaviors from the information made available by the contributors. The result is turned into an algorithmic procedure and the theoretical findings are complemented via a numerical example.