Intention Recognition With ProbLog

Gary B. Smith; Vaishak Belle; Ronald P. A. Petrick

doi:10.3389/frai.2022.806262

Intention Recognition With ProbLog

Gary B. Smith^*, Vaishak Belle, Ronald P. A. Petrick

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

In many scenarios where robots or autonomous systems may be deployed, the capacity to infer and reason about the intentions of other agents can improve the performance or utility of the system. For example, a smart home or assisted living facility is better able to select assistive services to deploy if it understands the goals of the occupants in advance. In this article, we present a framework for reasoning about intentions using probabilistic logic programming. We employ ProbLog, a probabilistic extension to Prolog, to infer the most probable intention given observations of the actions of the agent and sensor readings of important aspects of the environment. We evaluated our model on a domain modeling a smart home. The model achieved 0.75 accuracy at full observability. The model was robust to reduced observability.

Original language	English
Article number	806262
Pages (from-to)	806262
Number of pages	12
Journal	Frontiers in Artificial Intelligence
Volume	5
DOIs	https://doi.org/10.3389/frai.2022.806262
Publication status	Published - 26 Apr 2022

Keywords / Materials (for Non-textual outputs)

intention recognition
goal recognition
Probabilistic logic programming
smart home
assisted living at home

Access to Document

10.3389/frai.2022.806262Licence: Creative Commons: Attribution (CC-BY)

Intention Recognition_SMITH_DOA22032022_VOR_CC-BYFinal published version, 1.1 MBLicence: Creative Commons: Attribution (CC-BY)

https://www.frontiersin.org/article/10.3389/frai.2022.806262Licence: Creative Commons: Attribution (CC-BY)

UKRI Trustworthy Autonomous Systems Node in Governance and Regulation
Ramamoorthy, R. (Principal Investigator), Belle, V. (Co-investigator), Bundy, A. (Co-investigator), Jackson, P. (Co-investigator), Lascarides, A. (Co-investigator) & Rajan, A. (Co-investigator)
EPSRC
1/11/20 → 30/04/24
Project: Research

Cite this

@article{2671bddc2d624ed0ad27c620883b4ea3,

title = "Intention Recognition With ProbLog",

abstract = "In many scenarios where robots or autonomous systems may be deployed, the capacity to infer and reason about the intentions of other agents can improve the performance or utility of the system. For example, a smart home or assisted living facility is better able to select assistive services to deploy if it understands the goals of the occupants in advance. In this article, we present a framework for reasoning about intentions using probabilistic logic programming. We employ ProbLog, a probabilistic extension to Prolog, to infer the most probable intention given observations of the actions of the agent and sensor readings of important aspects of the environment. We evaluated our model on a domain modeling a smart home. The model achieved 0.75 accuracy at full observability. The model was robust to reduced observability.",

keywords = "intention recognition, goal recognition, Probabilistic logic programming, smart home, assisted living at home",

author = "Smith, {Gary B.} and Vaishak Belle and Petrick, {Ronald P. A.}",

note = "Funding Information: We thank the Edinburgh Centre for Robotics for their support. VB was supported by a Royal Society University Research Fellowship. He was also supported by a grant from the UKRI Strategic Priorities Fund to the UKRI Research Node on Trustworthy Autonomous Systems Governance and Regulation (EP/V026607/1, 2020-2024). Publisher Copyright: Copyright {\textcopyright} 2022 Smith, Belle and Petrick.",

year = "2022",

month = apr,

day = "26",

doi = "10.3389/frai.2022.806262",

language = "English",

volume = "5",

pages = "806262",

journal = "Frontiers in Artificial Intelligence",

issn = "2624-8212",

publisher = "Frontiers Media SA",

}

TY - JOUR

T1 - Intention Recognition With ProbLog

AU - Smith, Gary B.

AU - Belle, Vaishak

AU - Petrick, Ronald P. A.

N1 - Funding Information: We thank the Edinburgh Centre for Robotics for their support. VB was supported by a Royal Society University Research Fellowship. He was also supported by a grant from the UKRI Strategic Priorities Fund to the UKRI Research Node on Trustworthy Autonomous Systems Governance and Regulation (EP/V026607/1, 2020-2024). Publisher Copyright: Copyright © 2022 Smith, Belle and Petrick.

PY - 2022/4/26

Y1 - 2022/4/26

N2 - In many scenarios where robots or autonomous systems may be deployed, the capacity to infer and reason about the intentions of other agents can improve the performance or utility of the system. For example, a smart home or assisted living facility is better able to select assistive services to deploy if it understands the goals of the occupants in advance. In this article, we present a framework for reasoning about intentions using probabilistic logic programming. We employ ProbLog, a probabilistic extension to Prolog, to infer the most probable intention given observations of the actions of the agent and sensor readings of important aspects of the environment. We evaluated our model on a domain modeling a smart home. The model achieved 0.75 accuracy at full observability. The model was robust to reduced observability.

AB - In many scenarios where robots or autonomous systems may be deployed, the capacity to infer and reason about the intentions of other agents can improve the performance or utility of the system. For example, a smart home or assisted living facility is better able to select assistive services to deploy if it understands the goals of the occupants in advance. In this article, we present a framework for reasoning about intentions using probabilistic logic programming. We employ ProbLog, a probabilistic extension to Prolog, to infer the most probable intention given observations of the actions of the agent and sensor readings of important aspects of the environment. We evaluated our model on a domain modeling a smart home. The model achieved 0.75 accuracy at full observability. The model was robust to reduced observability.

KW - intention recognition

KW - goal recognition

KW - Probabilistic logic programming

KW - smart home

KW - assisted living at home

U2 - 10.3389/frai.2022.806262

DO - 10.3389/frai.2022.806262

M3 - Article

C2 - 35558169

SN - 2624-8212

VL - 5

SP - 806262

JO - Frontiers in Artificial Intelligence

JF - Frontiers in Artificial Intelligence

M1 - 806262

ER -

Intention Recognition With ProbLog

Abstract

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Projects

UKRI Trustworthy Autonomous Systems Node in Governance and Regulation

Cite this