Towards a Verifiable Toolchain for Robotics

Charlie Street; Yazz Warsame; Masoumeh Mansouri; Michaela Klauck; Christian Henkel; Marco Lampacrescia; Matteo Palmas; Ralph Lange; Enrico Ghiorzi; Armando Tacchella; Razane Azrou; Raphaël Lallement; Matteo Morelli; Ginny I. Chen; Danielle Wallis; Stefano Bernagozzi; Stefano Rosa; Marco Randazzo; Sofia Faraci; Lorenzo Natale

doi:10.1609/aaaiss.v4i1.31823

Towards a Verifiable Toolchain for Robotics

Charlie Street
, Yazz Warsame
, Masoumeh Mansouri
, Michaela Klauck
, Christian Henkel
, Marco Lampacrescia
, Matteo Palmas
, Ralph Lange
, Enrico Ghiorzi
, Armando Tacchella
, Razane Azrou
, Raphaël Lallement
, Matteo Morelli
, Ginny I. Chen
, Danielle Wallis
, Stefano Bernagozzi
, Stefano Rosa
, Marco Randazzo
, Sofia Faraci
, Lorenzo Natale

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

128 Downloads (Pure)

Abstract

There is a growing need for autonomous robots to complete complex tasks robustly in dynamic and unstructured environments. However, current robot performance is limited to simple tasks in controlled environments. To improve robot autonomy in complex environments, the robot's deliberation system must be able to synthesise correct plans for a task and generate contingency plans for handling anomalous scenarios that were not expected at design time. The robustness of such a system can be quantified using techniques for formal verification and validation. This paper outlines the progress of EU project CONVINCE (CONtext-aware Verifiable and adaptIve dyNamiC dEliberation), which aims to develop a software toolchain that aids developers in designing, developing, and deploying robot deliberation systems that are fully verified. We describe our modelling approach, each of the toolchain components, and how they interact. We also discuss survey results which demonstrate the demand for a verifiable toolchain among the robotics community.

Original language	English
Title of host publication	Proceedings of the AAAI Symposium Series
Editors	Feras A. Batarseh, Frank Stein
Publisher	AAAI Press
Pages	398-403
Number of pages	6
ISBN (Electronic)	9781577358947
DOIs	https://doi.org/10.1609/aaaiss.v4i1.31823
Publication status	Published - 8 Nov 2024
Event	2024 AAAI Fall Symposium on Unifying Representations for Robot Application Development - Westin Arlington Gateway, Arlington, United States Duration: 7 Nov 2024 → 9 Nov 2024 https://sites.google.com/view/aaai-ur-rad-symposium/home

Publication series

Name	AAAI Fall Symposium Series
Publisher	AAAI
Number	1
Volume	4
ISSN (Electronic)	2994-4317

Conference

Conference	2024 AAAI Fall Symposium on Unifying Representations for Robot Application Development
Abbreviated title	UR-RAD
Country/Territory	United States
City	Arlington
Period	7/11/24 → 9/11/24
Internet address	https://sites.google.com/view/aaai-ur-rad-symposium/home

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1609/aaaiss.v4i1.31823Licence: None: All rights reserved

StreetC2024TowardsAccepted author manuscript, 262 KBLicence: None: All rights reserved

CONVINCE - CONtext-aware VerifIable dyNamiC dEliberation
Mansouri, M. (Principal Investigator)
UKRI Horizon Europe Underwriting Innovate UK
1/10/22 → 31/03/26
Project: Research

Cite this

Street, C., Warsame, Y., Mansouri, M., Klauck, M., Henkel, C., Lampacrescia, M., Palmas, M., Lange, R., Ghiorzi, E., Tacchella, A., Azrou, R., Lallement, R., Morelli, M., I. Chen, G., Wallis, D., Bernagozzi, S., Rosa, S., Randazzo, M., Faraci, S., & Natale, L. (2024). Towards a Verifiable Toolchain for Robotics. In F. A. Batarseh, & F. Stein (Eds.), Proceedings of the AAAI Symposium Series (pp. 398-403). (AAAI Fall Symposium Series; Vol. 4, No. 1). AAAI Press. https://doi.org/10.1609/aaaiss.v4i1.31823

@inproceedings{be79e0d898434b8eb1f89a1d3a10385c,

title = "Towards a Verifiable Toolchain for Robotics",

abstract = "There is a growing need for autonomous robots to complete complex tasks robustly in dynamic and unstructured environments. However, current robot performance is limited to simple tasks in controlled environments. To improve robot autonomy in complex environments, the robot's deliberation system must be able to synthesise correct plans for a task and generate contingency plans for handling anomalous scenarios that were not expected at design time. The robustness of such a system can be quantified using techniques for formal verification and validation. This paper outlines the progress of EU project CONVINCE (CONtext-aware Verifiable and adaptIve dyNamiC dEliberation), which aims to develop a software toolchain that aids developers in designing, developing, and deploying robot deliberation systems that are fully verified. We describe our modelling approach, each of the toolchain components, and how they interact. We also discuss survey results which demonstrate the demand for a verifiable toolchain among the robotics community.",

author = "Charlie Street and Yazz Warsame and Masoumeh Mansouri and Michaela Klauck and Christian Henkel and Marco Lampacrescia and Matteo Palmas and Ralph Lange and Enrico Ghiorzi and Armando Tacchella and Razane Azrou and Rapha{\"e}l Lallement and Matteo Morelli and \{I. Chen\}, Ginny and Danielle Wallis and Stefano Bernagozzi and Stefano Rosa and Marco Randazzo and Sofia Faraci and Lorenzo Natale",

year = "2024",

month = nov,

day = "8",

doi = "10.1609/aaaiss.v4i1.31823",

language = "English",

series = "AAAI Fall Symposium Series",

publisher = "AAAI Press",

number = "1",

pages = "398--403",

editor = "Batarseh, \{Feras A.\} and Frank Stein",

booktitle = "Proceedings of the AAAI Symposium Series",

note = "2024 AAAI Fall Symposium on Unifying Representations for Robot Application Development, UR-RAD ; Conference date: 07-11-2024 Through 09-11-2024",

url = "https://sites.google.com/view/aaai-ur-rad-symposium/home",

}

Street, C , Warsame, Y , Mansouri, M, Klauck, M, Henkel, C, Lampacrescia, M, Palmas, M, Lange, R, Ghiorzi, E, Tacchella, A, Azrou, R, Lallement, R, Morelli, M, I. Chen, G, Wallis, D, Bernagozzi, S, Rosa, S, Randazzo, M, Faraci, S & Natale, L 2024, Towards a Verifiable Toolchain for Robotics. in FA Batarseh & F Stein (eds), Proceedings of the AAAI Symposium Series. AAAI Fall Symposium Series, no. 1, vol. 4, AAAI Press, pp. 398-403, 2024 AAAI Fall Symposium on Unifying Representations for Robot Application Development, Arlington, Virginia, United States, 7/11/24. https://doi.org/10.1609/aaaiss.v4i1.31823

TY - GEN

T1 - Towards a Verifiable Toolchain for Robotics

AU - Street, Charlie

AU - Warsame, Yazz

AU - Mansouri, Masoumeh

AU - Klauck, Michaela

AU - Henkel, Christian

AU - Lampacrescia, Marco

AU - Palmas, Matteo

AU - Lange, Ralph

AU - Ghiorzi, Enrico

AU - Tacchella, Armando

AU - Azrou, Razane

AU - Lallement, Raphaël

AU - Morelli, Matteo

AU - I. Chen, Ginny

AU - Wallis, Danielle

AU - Bernagozzi, Stefano

AU - Rosa, Stefano

AU - Randazzo, Marco

AU - Faraci, Sofia

AU - Natale, Lorenzo

PY - 2024/11/8

Y1 - 2024/11/8

N2 - There is a growing need for autonomous robots to complete complex tasks robustly in dynamic and unstructured environments. However, current robot performance is limited to simple tasks in controlled environments. To improve robot autonomy in complex environments, the robot's deliberation system must be able to synthesise correct plans for a task and generate contingency plans for handling anomalous scenarios that were not expected at design time. The robustness of such a system can be quantified using techniques for formal verification and validation. This paper outlines the progress of EU project CONVINCE (CONtext-aware Verifiable and adaptIve dyNamiC dEliberation), which aims to develop a software toolchain that aids developers in designing, developing, and deploying robot deliberation systems that are fully verified. We describe our modelling approach, each of the toolchain components, and how they interact. We also discuss survey results which demonstrate the demand for a verifiable toolchain among the robotics community.

AB - There is a growing need for autonomous robots to complete complex tasks robustly in dynamic and unstructured environments. However, current robot performance is limited to simple tasks in controlled environments. To improve robot autonomy in complex environments, the robot's deliberation system must be able to synthesise correct plans for a task and generate contingency plans for handling anomalous scenarios that were not expected at design time. The robustness of such a system can be quantified using techniques for formal verification and validation. This paper outlines the progress of EU project CONVINCE (CONtext-aware Verifiable and adaptIve dyNamiC dEliberation), which aims to develop a software toolchain that aids developers in designing, developing, and deploying robot deliberation systems that are fully verified. We describe our modelling approach, each of the toolchain components, and how they interact. We also discuss survey results which demonstrate the demand for a verifiable toolchain among the robotics community.

U2 - 10.1609/aaaiss.v4i1.31823

DO - 10.1609/aaaiss.v4i1.31823

M3 - Conference contribution

T3 - AAAI Fall Symposium Series

SP - 398

EP - 403

BT - Proceedings of the AAAI Symposium Series

A2 - Batarseh, Feras A.

A2 - Stein, Frank

PB - AAAI Press

T2 - 2024 AAAI Fall Symposium on Unifying Representations for Robot Application Development

Y2 - 7 November 2024 through 9 November 2024

ER -

Towards a Verifiable Toolchain for Robotics

Abstract

Publication series

Conference

UN SDGs

Access to Document

Fingerprint

Projects

CONVINCE - CONtext-aware VerifIable dyNamiC dEliberation

Cite this