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 - assisted living at home
KW - goal recognition
KW - intention recognition
KW - probabilistic logic programming
KW - smart home
UR - http://www.scopus.com/inward/record.url?scp=85132605266&partnerID=8YFLogxK
U2 - 10.3389/frai.2022.806262
DO - 10.3389/frai.2022.806262
M3 - Article
C2 - 35558169
SN - 2624-8212
VL - 5
JO - Frontiers in Artificial Intelligence
JF - Frontiers in Artificial Intelligence
M1 - 806262
ER -