Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Probabilistic Programs

Or Wertheim; Dan R. Suissa; Ronen I. Brafman

doi:10.1109/LRA.2023.3334682

Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Probabilistic Programs

Or Wertheim, Dan R. Suissa, Ronen I. Brafman

Department of Computer Science

Ben-Gurion University of the Negev

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

Abstract

We describe AOS, the first general-purpose system for model-based control of autonomous robots using AI planning that fully supports partial observability and noisy sensing. The AOS provides a code-based language for specifying a generative model of the system, making model specification easier and model sampling efficient. It provides a language for specifying the relation between the model and the code, using which it auto-generates all required integration code. This allows Plug'n Play behavior, which facilitates incremental and modular system design. Extensive experiments on real and simulated robotic platforms demonstrate these advantages.

Original language	American English
Pages (from-to)	587-594
Number of pages	8
Journal	IEEE Robotics and Automation Letters
Volume	9
Issue number	1
DOIs	https://doi.org/10.1109/LRA.2023.3334682
State	Published - 1 Jan 2024

Keywords

AI-enabled robotics
autonomous agents
integrated planning and control
planning under uncertainty
software architecture for robotic and automation

All Science Journal Classification (ASJC) codes

Mechanical Engineering
Control and Optimization
Artificial Intelligence
Human-Computer Interaction
Control and Systems Engineering
Computer Vision and Pattern Recognition
Biomedical Engineering
Computer Science Applications

Access to Document

10.1109/LRA.2023.3334682

Cite this

@article{dd029cad11c249d89210ee2d8d373985,

title = "Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Probabilistic Programs",

abstract = "We describe AOS, the first general-purpose system for model-based control of autonomous robots using AI planning that fully supports partial observability and noisy sensing. The AOS provides a code-based language for specifying a generative model of the system, making model specification easier and model sampling efficient. It provides a language for specifying the relation between the model and the code, using which it auto-generates all required integration code. This allows Plug'n Play behavior, which facilitates incremental and modular system design. Extensive experiments on real and simulated robotic platforms demonstrate these advantages.",

keywords = "AI-enabled robotics, autonomous agents, integrated planning and control, planning under uncertainty, software architecture for robotic and automation",

author = "Or Wertheim and Suissa, \{Dan R.\} and Brafman, \{Ronen I.\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.",

year = "2024",

month = jan,

day = "1",

doi = "10.1109/LRA.2023.3334682",

language = "American English",

volume = "9",

pages = "587--594",

journal = "IEEE Robotics and Automation Letters",

issn = "2377-3766",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Probabilistic Programs

AU - Wertheim, Or

AU - Suissa, Dan R.

AU - Brafman, Ronen I.

PY - 2024/1/1

Y1 - 2024/1/1

N2 - We describe AOS, the first general-purpose system for model-based control of autonomous robots using AI planning that fully supports partial observability and noisy sensing. The AOS provides a code-based language for specifying a generative model of the system, making model specification easier and model sampling efficient. It provides a language for specifying the relation between the model and the code, using which it auto-generates all required integration code. This allows Plug'n Play behavior, which facilitates incremental and modular system design. Extensive experiments on real and simulated robotic platforms demonstrate these advantages.

AB - We describe AOS, the first general-purpose system for model-based control of autonomous robots using AI planning that fully supports partial observability and noisy sensing. The AOS provides a code-based language for specifying a generative model of the system, making model specification easier and model sampling efficient. It provides a language for specifying the relation between the model and the code, using which it auto-generates all required integration code. This allows Plug'n Play behavior, which facilitates incremental and modular system design. Extensive experiments on real and simulated robotic platforms demonstrate these advantages.

KW - AI-enabled robotics

KW - autonomous agents

KW - integrated planning and control

KW - planning under uncertainty

KW - software architecture for robotic and automation

UR - http://www.scopus.com/inward/record.url?scp=85178013449&partnerID=8YFLogxK

U2 - 10.1109/LRA.2023.3334682

DO - 10.1109/LRA.2023.3334682

M3 - Article

SN - 2377-3766

VL - 9

SP - 587

EP - 594

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

IS - 1

ER -

Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Probabilistic Programs

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this