Adapting Behaviour Based On Trust In Human-Agent Ad Hoc Teamwork Ana Carrasco

2025-04-24 0 0 244.84KB 4 页 10玖币

侵权投诉

Adapting Behaviour Based On Trust In

Human-Agent Ad Hoc Teamwork⋆

Ana Carrasco⋆⋆

INESC-ID, Instituto Superior Técnico, University of Lisbon

Lisbon, Portugal

ana.carrasco@gaips.inesc-id.pt

Abstract. This work proposes a framework that incorporates trust in

an ad hoc teamwork scenario with human-agent teams, where an agent

must collaborate with a human to perform a task. During the task, the

agent must infer, through interactions and observations, how much the

human trusts it and adapt its behaviour to maximize the team’s perfor-

mance. To achieve this, we propose collecting data from human partic-

ipants in experiments to deﬁne diﬀerent settings (based on trust levels)

and learning optimal policies for each of them. Then, we create a module

to infer the current setting (depending on the amount of trust). Finally,

we validate this framework in a real-world scenario and analyse how this

adaptable behaviour aﬀects trust.

Keywords: Ad Hoc Teamwork ·Trust ·Human-Robot Interaction

1 Introduction

Ad Hoc Teamwork (AHT) [8] is a well-known research problem where an agent

must be able to cooperate with a group of teammates (humans or agents), with-

out any prior coordination or communication protocols. The AHT is character-

ized by three assumptions: the agent has no prior coordination or communication

mechanisms established with its teammates, the agent has no control over the

teammates and all teammates are assumed to have a common objective (or

task) [5]. As deﬁned by Melo and Sardinha [4], the AHT problem can be divided

into three sub-tasks: identifying the common task, identifying the teammates

and what they are doing and plan actions accordingly.

A review of the recent literature on the subject reveals that, as autonomous

agents capabilities advance, human-robot collaboration scenarios become more

⋆This work was partially supported by national funds through FCT, Fundação para

a Ciência e a Tecnologia, under project UIDB/50021/2020 (INESC-ID multi-annual

funding) and the HOTSPOT project, with reference PTDC/CCI-COM/7203/2020.

In addition, this material is based upon work supported by TAILOR, a project

funded by EU Horizon 2020 research and innovation programme under GA N.

952215.

⋆⋆ The advisors of this work are: Ana Paiva (paiva.a@gmail.com), Alberto Sardinha

(jose.alberto.sardinha@tecnico.ulisboa.pt), Francisco S. Melo(fmelo@inesc-id.pt)

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

AdaptingBehaviourBasedOnTrustInHuman-AgentAdHocTeamwork⋆AnaCarrasco⋆⋆INESC-ID,InstitutoSuperiorTécnico,UniversityofLisbonLisbon,Portugalana.carrasco@gaips.inesc-id.ptAbstract.Thisworkproposesaframeworkthatincorporatestrustinanadhocteamworkscenariowithhuman-agentteams,whereanagentmustcollaboratewitha...

展开>> 收起<<

Adapting Behaviour Based On Trust In Human-Agent Ad Hoc Teamwork Ana Carrasco.pdf

共4页,预览1页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

Adapting Behaviour Based On Trust In Human-Agent Ad Hoc Teamwork Ana Carrasco

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: