Explicabilty versus explanations in human-aware planning

Tathagata Chakrabroti, Sarath Sreedharan, Subbarao Kambhampati

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Human aware planning requires an agent to be aware of the mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to the human as well as the ability to provide explanations when such plans cannot be generated. In this paper, we bring these two concepts together and show how an agent can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA∗. This provides a revised perspective of what it means for an AI agent to be "human-aware" by bringing together recent works on explicable planning and plans explanations under the umbrella of a single plan generation process. We illustrate these concepts using a robot involved in a typical search and reconnaissance task with an external supervisor.

Original languageEnglish (US)
Title of host publication17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages2180-2182
Number of pages3
Volume3
ISBN (Print)9781510868083
StatePublished - Jan 1 2018
Event17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018 - Stockholm, Sweden
Duration: Jul 10 2018Jul 15 2018

Other

Other17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018
CountrySweden
CityStockholm
Period7/10/187/15/18

Fingerprint

Planning
Supervisory personnel
Robots

Keywords

  • Argumentation
  • Human-aware planning
  • Model reconciliation
  • Plan explanations
  • Plan explicability

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering

Cite this

Chakrabroti, T., Sreedharan, S., & Kambhampati, S. (2018). Explicabilty versus explanations in human-aware planning. In 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018 (Vol. 3, pp. 2180-2182). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

Explicabilty versus explanations in human-aware planning. / Chakrabroti, Tathagata; Sreedharan, Sarath; Kambhampati, Subbarao.

17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018. Vol. 3 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2018. p. 2180-2182.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chakrabroti, T, Sreedharan, S & Kambhampati, S 2018, Explicabilty versus explanations in human-aware planning. in 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018. vol. 3, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 2180-2182, 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018, Stockholm, Sweden, 7/10/18.
Chakrabroti T, Sreedharan S, Kambhampati S. Explicabilty versus explanations in human-aware planning. In 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018. Vol. 3. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). 2018. p. 2180-2182
Chakrabroti, Tathagata ; Sreedharan, Sarath ; Kambhampati, Subbarao. / Explicabilty versus explanations in human-aware planning. 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018. Vol. 3 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2018. pp. 2180-2182
@inproceedings{bc2c28c0ea0e4ff3a01fff4b3665dd2d,
title = "Explicabilty versus explanations in human-aware planning",
abstract = "Human aware planning requires an agent to be aware of the mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to the human as well as the ability to provide explanations when such plans cannot be generated. In this paper, we bring these two concepts together and show how an agent can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA∗. This provides a revised perspective of what it means for an AI agent to be {"}human-aware{"} by bringing together recent works on explicable planning and plans explanations under the umbrella of a single plan generation process. We illustrate these concepts using a robot involved in a typical search and reconnaissance task with an external supervisor.",
keywords = "Argumentation, Human-aware planning, Model reconciliation, Plan explanations, Plan explicability",
author = "Tathagata Chakrabroti and Sarath Sreedharan and Subbarao Kambhampati",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781510868083",
volume = "3",
pages = "2180--2182",
booktitle = "17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

}

TY - GEN

T1 - Explicabilty versus explanations in human-aware planning

AU - Chakrabroti, Tathagata

AU - Sreedharan, Sarath

AU - Kambhampati, Subbarao

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Human aware planning requires an agent to be aware of the mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to the human as well as the ability to provide explanations when such plans cannot be generated. In this paper, we bring these two concepts together and show how an agent can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA∗. This provides a revised perspective of what it means for an AI agent to be "human-aware" by bringing together recent works on explicable planning and plans explanations under the umbrella of a single plan generation process. We illustrate these concepts using a robot involved in a typical search and reconnaissance task with an external supervisor.

AB - Human aware planning requires an agent to be aware of the mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to the human as well as the ability to provide explanations when such plans cannot be generated. In this paper, we bring these two concepts together and show how an agent can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA∗. This provides a revised perspective of what it means for an AI agent to be "human-aware" by bringing together recent works on explicable planning and plans explanations under the umbrella of a single plan generation process. We illustrate these concepts using a robot involved in a typical search and reconnaissance task with an external supervisor.

KW - Argumentation

KW - Human-aware planning

KW - Model reconciliation

KW - Plan explanations

KW - Plan explicability

UR - http://www.scopus.com/inward/record.url?scp=85054740783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054740783&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781510868083

VL - 3

SP - 2180

EP - 2182

BT - 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

ER -