Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers

Raynaldio Limarga; Kwai Wa Tse; Louise Dennis; Clare Dixon; Fatma Faruq; Michael Fisher

doi:10.1109/eras63351.2025.11135852

Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers

Raynaldio Limarga
, Kwai Wa Tse
, Louise Dennis
, Clare Dixon
, Fatma Faruq
, Michael Fisher

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

39 Downloads (Pure)

Abstract

Controllers for real-world robots are constructed based on expectation models which cannot account for all unexpected events. If unexpected events occur, the robot might either stop working altogether or do something that violates its
given mission specification. In this paper, we aim to provide a more principled mechanism for dealing with specifications when encountering the inherent uncertainty of the real-world. We utilise agent-based control of a robotic system wherein a rational agent, programmed using a Belief-Desire-Intention (BDI) agent programming language, acts as a high-level robot controller. This
agent is aware of its mission specification and is able to recognise violations of this specification caused by unexpected events. On recognising such a violation, the agent can switch to a more suitable plan. However, if there are no suitable plans, the agent can also weaken its mission specification dynamically. The agent can output not only which parts of the mission specification have been achieved but which parts have been weakened and why.

Original language	English
Title of host publication	Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers
DOIs	https://doi.org/10.1109/eras63351.2025.11135852
Publication status	Published - 29 May 2025

Keywords

Belief-Desire-Intention Agent
Mission Specification
Robot Planning
Weakening Constraint

Access to Document

10.1109/eras63351.2025.11135852

Reliable_Robot_MissionsAccepted author manuscript, 974 KBLicence: CC BY

CRADLE: CRADLE - Centre for Robotic Autonomy in Demanding and Long-lasting Environments
Fisher, M. (PI), Adorno, B. (CoI), Cangelosi, A. (CoI), Dennis, L. (CoI), Dixon, C. (CoI), Groves, K. (CoI), Lennox, B. (CoI), Watson, S. (CoI), Weightman, A. (CoI), Farrell, M. (CoI), Marinho, M. (CoI), Ladosz, P. (CoI), Wood, K. (CoI), Collins, E. (CoI), Smith, K. (CoI), Parslew, B. (CoI), Li, Z. (CoI), Clinch, S. (CoI), Baniqued, P. D. (Support team), Flint, S. (Support team), Khan, D. (Technical team), Tse, K. W. (Technical team), Atia, M. (Researcher), Song, Y. (Researcher), Leslie-Dalley, S. (PGR student), Bettles, J. (PGR student), Limarga, R. (Researcher), Zheng, S. (Researcher), Slusarz, N. (Researcher), Le, H. (PGR student), Tavella, F. (Researcher), Bolarinwa, J. (Researcher), Chi, X. (PGR student), Rolph, M. (PGR student), Saravanan, D. (PGR student), Abeywickrama, D. (Researcher), Rafiq, Y. (Researcher), Bishop, C. (Researcher), Khan, S. M. (Researcher), Wheelhouse, L. (PGR student), Morley, A. (PGR student), Greenhaus, Y. (PGR student), Arumugam, S. (PGR student) & Soboyejo, T. (PGR student)
1/09/23 → 31/08/28
Project: Research

Cite this

@inproceedings{7d22c4eaf89042b3b505608b08c336e4,

title = "Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers",

abstract = "Controllers for real-world robots are constructed based on expectation models which cannot account for all unexpected events. If unexpected events occur, the robot might either stop working altogether or do something that violates its given mission specification. In this paper, we aim to provide a more principled mechanism for dealing with specifications when encountering the inherent uncertainty of the real-world. We utilise agent-based control of a robotic system wherein a rational agent, programmed using a Belief-Desire-Intention (BDI) agent programming language, acts as a high-level robot controller. This agent is aware of its mission specification and is able to recognise violations of this specification caused by unexpected events. On recognising such a violation, the agent can switch to a more suitable plan. However, if there are no suitable plans, the agent can also weaken its mission specification dynamically. The agent can output not only which parts of the mission specification have been achieved but which parts have been weakened and why.",

keywords = "Belief-Desire-Intention Agent, Mission Specification, Robot Planning, Weakening Constraint",

author = "Raynaldio Limarga and Tse, \{Kwai Wa\} and Louise Dennis and Clare Dixon and Fatma Faruq and Michael Fisher",

year = "2025",

month = may,

day = "29",

doi = "10.1109/eras63351.2025.11135852",

language = "English",

booktitle = "Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers",

}

TY - GEN

T1 - Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers

AU - Limarga, Raynaldio

AU - Tse, Kwai Wa

AU - Dennis, Louise

AU - Dixon, Clare

AU - Faruq, Fatma

AU - Fisher, Michael

PY - 2025/5/29

Y1 - 2025/5/29

N2 - Controllers for real-world robots are constructed based on expectation models which cannot account for all unexpected events. If unexpected events occur, the robot might either stop working altogether or do something that violates its given mission specification. In this paper, we aim to provide a more principled mechanism for dealing with specifications when encountering the inherent uncertainty of the real-world. We utilise agent-based control of a robotic system wherein a rational agent, programmed using a Belief-Desire-Intention (BDI) agent programming language, acts as a high-level robot controller. This agent is aware of its mission specification and is able to recognise violations of this specification caused by unexpected events. On recognising such a violation, the agent can switch to a more suitable plan. However, if there are no suitable plans, the agent can also weaken its mission specification dynamically. The agent can output not only which parts of the mission specification have been achieved but which parts have been weakened and why.

AB - Controllers for real-world robots are constructed based on expectation models which cannot account for all unexpected events. If unexpected events occur, the robot might either stop working altogether or do something that violates its given mission specification. In this paper, we aim to provide a more principled mechanism for dealing with specifications when encountering the inherent uncertainty of the real-world. We utilise agent-based control of a robotic system wherein a rational agent, programmed using a Belief-Desire-Intention (BDI) agent programming language, acts as a high-level robot controller. This agent is aware of its mission specification and is able to recognise violations of this specification caused by unexpected events. On recognising such a violation, the agent can switch to a more suitable plan. However, if there are no suitable plans, the agent can also weaken its mission specification dynamically. The agent can output not only which parts of the mission specification have been achieved but which parts have been weakened and why.

KW - Belief-Desire-Intention Agent

KW - Mission Specification

KW - Robot Planning

KW - Weakening Constraint

U2 - 10.1109/eras63351.2025.11135852

DO - 10.1109/eras63351.2025.11135852

M3 - Conference contribution

BT - Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers

ER -

Reliable Robot Missions in Dynamic Environments Using Agent-based Controllers

Abstract

Keywords

Access to Document

Fingerprint

Projects

CRADLE: CRADLE - Centre for Robotic Autonomy in Demanding and Long-lasting Environments

Cite this