Towards explainable AI planning as a service

Michael Cashmore; Anna Collins; Benjamin Krarup; Senka Krivic; Daniele Magazzeni; David Smith

Towards explainable AI planning as a service

Michael Cashmore, Anna Collins, Benjamin Krarup, Senka Krivic, Daniele Magazzeni, David Smith

Computer And Information Sciences

Research output: Contribution to conference › Paper › peer-review

36 Downloads (Pure)

Abstract

Explainable AI is an important area of research within which Explainable Planning is an emerging topic. In this paper, we argue that Explainable Planning can be designed as a service -- that is, as a wrapper around an existing planning system that utilises the existing planner to assist in answering contrastive questions. We introduce a prototype framework to facilitate this, along with some examples of how a planner can be used to address certain types of contrastive questions. We discuss the main advantages and limitations of such an approach and we identify open questions for Explainable Planning as a service that identify several possible research directions.

Original language	English
Number of pages	9
Publication status	Published - 12 Jul 2019
Event	2nd ICAPS Workshop on Explainable Planning - Berkeley, United States Duration: 12 Jul 2019 → 12 Jul 2019

Conference

Conference	2nd ICAPS Workshop on Explainable Planning
Abbreviated title	XAIP 2019
Country/Territory	United States
City	Berkeley
Period	12/07/19 → 12/07/19

Keywords

explainable AI
planning system
research

Access to Document

Cashmore-etal-XAIP2019-Towards-explainable-AI-planning-as-a-serviceAccepted author manuscript, 580 KB

Cite this

@conference{0f1bd8e46718419280ce960f8c7ce4e5,

title = "Towards explainable AI planning as a service",

abstract = "Explainable AI is an important area of research within which Explainable Planning is an emerging topic. In this paper, we argue that Explainable Planning can be designed as a service -- that is, as a wrapper around an existing planning system that utilises the existing planner to assist in answering contrastive questions. We introduce a prototype framework to facilitate this, along with some examples of how a planner can be used to address certain types of contrastive questions. We discuss the main advantages and limitations of such an approach and we identify open questions for Explainable Planning as a service that identify several possible research directions. ",

keywords = "explainable AI, planning system, research",

author = "Michael Cashmore and Anna Collins and Benjamin Krarup and Senka Krivic and Daniele Magazzeni and David Smith",

year = "2019",

month = jul,

day = "12",

language = "English",

note = "2nd ICAPS Workshop on Explainable Planning, XAIP 2019 ; Conference date: 12-07-2019 Through 12-07-2019",

}

TY - CONF

T1 - Towards explainable AI planning as a service

AU - Cashmore, Michael

AU - Collins, Anna

AU - Krarup, Benjamin

AU - Krivic, Senka

AU - Magazzeni, Daniele

AU - Smith, David

PY - 2019/7/12

Y1 - 2019/7/12

N2 - Explainable AI is an important area of research within which Explainable Planning is an emerging topic. In this paper, we argue that Explainable Planning can be designed as a service -- that is, as a wrapper around an existing planning system that utilises the existing planner to assist in answering contrastive questions. We introduce a prototype framework to facilitate this, along with some examples of how a planner can be used to address certain types of contrastive questions. We discuss the main advantages and limitations of such an approach and we identify open questions for Explainable Planning as a service that identify several possible research directions.

AB - Explainable AI is an important area of research within which Explainable Planning is an emerging topic. In this paper, we argue that Explainable Planning can be designed as a service -- that is, as a wrapper around an existing planning system that utilises the existing planner to assist in answering contrastive questions. We introduce a prototype framework to facilitate this, along with some examples of how a planner can be used to address certain types of contrastive questions. We discuss the main advantages and limitations of such an approach and we identify open questions for Explainable Planning as a service that identify several possible research directions.

KW - explainable AI

KW - planning system

KW - research

M3 - Paper

T2 - 2nd ICAPS Workshop on Explainable Planning

Y2 - 12 July 2019 through 12 July 2019

ER -

Towards explainable AI planning as a service

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this