A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation

DImitris Panagopoulos; Giannis Petousakis; Rustam Stolkin; Grigoris Nikolaou; Manolis Chiou

doi:10.1109/SMC52423.2021.9658942

A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation

DImitris Panagopoulos, Giannis Petousakis, Rustam Stolkin, Grigoris Nikolaou, Manolis Chiou

Metallurgy and Materials

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

Abstract

This paper addresses the problem of human operator intent recognition during teleoperated robot navigation. In this context, recognition of the operator's intended navigational goal, could enable an artificial intelligence (AI) agent to assist the operator in an advanced human-robot interaction framework. We propose a Bayesian Operator Intent Recognition (BOIR) probabilistic method that utilizes: (i) an observation model that fuses information as a weighting combination of multiple observation sources providing geometric information; (ii) a transition model that indicates the evolution of the state; and (iii) an action model, the Active Intent Recognition Model (AIRM), that enables the operator to communicate their explicit intent asynchronously. The proposed method is evaluated in an experiment where operators controlling a remote mobile robot are tasked with navigation and exploration under various scenarios with different map and obstacle layouts. Results demonstrate that BOIR outperforms two related methods from literature in terms of accuracy and uncertainty of the intent recognition.

Original language	English
Title of host publication	2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Publisher	IEEE
Pages	125-131
Number of pages	7
ISBN (Electronic)	9781665442077
ISBN (Print)	9781665442084
DOIs	https://doi.org/10.1109/SMC52423.2021.9658942
Publication status	Published - 6 Jan 2022
Event	2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021 - Melbourne, Australia Duration: 17 Oct 2021 → 20 Oct 2021

Publication series

Name	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Publisher	IEEE
ISSN (Print)	1062-922X
ISSN (Electronic)	2577-1655

Conference

Conference	2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021
Country/Territory	Australia
City	Melbourne
Period	17/10/21 → 20/10/21

Bibliographical note

Funding Information:
This work was supported by the UKRI-EPSRC grand EP/R02572X/1 (National Centre for Nuclear Robotics).

Publisher Copyright:
© 2021 IEEE.

Keywords

Bayesian Inference
Human Operator Intent Recognition
Human-in-the-Loop
Human-robot Interaction
Human-robot Teaming

ASJC Scopus subject areas

Electrical and Electronic Engineering
Control and Systems Engineering
Human-Computer Interaction

Access to Document

10.1109/SMC52423.2021.9658942

1 Preprint

A Bayesian-based approach to human operator intent recognition in remote mobile robot navigation
Panagopoulos, D., Petousakis, G., Stolkin, R., Nikolaou, G. & Chiou, M., 24 Sept 2021, arXiv.
Research output: Working paper/Preprint › Preprint

1 Finished

National Centre for Nuclear Robotics (NCNR)
Stolkin, R., Leonardis, A. & Stone, B.
Engineering & Physical Science Research Council
2/10/17 → 1/04/22
Project: Research

Cite this

Panagopoulos, DI., Petousakis, G., Stolkin, R., Nikolaou, G., & Chiou, M. (2022). A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 125-131). (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). IEEE. https://doi.org/10.1109/SMC52423.2021.9658942

@inproceedings{00b98c7506434665b7207b347901220f,

title = "A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation",

abstract = "This paper addresses the problem of human operator intent recognition during teleoperated robot navigation. In this context, recognition of the operator's intended navigational goal, could enable an artificial intelligence (AI) agent to assist the operator in an advanced human-robot interaction framework. We propose a Bayesian Operator Intent Recognition (BOIR) probabilistic method that utilizes: (i) an observation model that fuses information as a weighting combination of multiple observation sources providing geometric information; (ii) a transition model that indicates the evolution of the state; and (iii) an action model, the Active Intent Recognition Model (AIRM), that enables the operator to communicate their explicit intent asynchronously. The proposed method is evaluated in an experiment where operators controlling a remote mobile robot are tasked with navigation and exploration under various scenarios with different map and obstacle layouts. Results demonstrate that BOIR outperforms two related methods from literature in terms of accuracy and uncertainty of the intent recognition.",

keywords = "Bayesian Inference, Human Operator Intent Recognition, Human-in-the-Loop, Human-robot Interaction, Human-robot Teaming",

author = "DImitris Panagopoulos and Giannis Petousakis and Rustam Stolkin and Grigoris Nikolaou and Manolis Chiou",

note = "Funding Information: This work was supported by the UKRI-EPSRC grand EP/R02572X/1 (National Centre for Nuclear Robotics). Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021 ; Conference date: 17-10-2021 Through 20-10-2021",

year = "2022",

month = jan,

day = "6",

doi = "10.1109/SMC52423.2021.9658942",

language = "English",

isbn = "9781665442084",

series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

publisher = "IEEE",

pages = "125--131",

booktitle = "2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)",

}

Panagopoulos, DI, Petousakis, G, Stolkin, R, Nikolaou, G & Chiou, M 2022, A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation. in 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, IEEE, pp. 125-131, 2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021, Melbourne, Australia, 17/10/21. https://doi.org/10.1109/SMC52423.2021.9658942

A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation. / Panagopoulos, DImitris; Petousakis, Giannis; Stolkin, Rustam et al.
2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 2022. p. 125-131 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

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

TY - GEN

T1 - A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation

AU - Panagopoulos, DImitris

AU - Petousakis, Giannis

AU - Stolkin, Rustam

AU - Nikolaou, Grigoris

AU - Chiou, Manolis

PY - 2022/1/6

Y1 - 2022/1/6

N2 - This paper addresses the problem of human operator intent recognition during teleoperated robot navigation. In this context, recognition of the operator's intended navigational goal, could enable an artificial intelligence (AI) agent to assist the operator in an advanced human-robot interaction framework. We propose a Bayesian Operator Intent Recognition (BOIR) probabilistic method that utilizes: (i) an observation model that fuses information as a weighting combination of multiple observation sources providing geometric information; (ii) a transition model that indicates the evolution of the state; and (iii) an action model, the Active Intent Recognition Model (AIRM), that enables the operator to communicate their explicit intent asynchronously. The proposed method is evaluated in an experiment where operators controlling a remote mobile robot are tasked with navigation and exploration under various scenarios with different map and obstacle layouts. Results demonstrate that BOIR outperforms two related methods from literature in terms of accuracy and uncertainty of the intent recognition.

AB - This paper addresses the problem of human operator intent recognition during teleoperated robot navigation. In this context, recognition of the operator's intended navigational goal, could enable an artificial intelligence (AI) agent to assist the operator in an advanced human-robot interaction framework. We propose a Bayesian Operator Intent Recognition (BOIR) probabilistic method that utilizes: (i) an observation model that fuses information as a weighting combination of multiple observation sources providing geometric information; (ii) a transition model that indicates the evolution of the state; and (iii) an action model, the Active Intent Recognition Model (AIRM), that enables the operator to communicate their explicit intent asynchronously. The proposed method is evaluated in an experiment where operators controlling a remote mobile robot are tasked with navigation and exploration under various scenarios with different map and obstacle layouts. Results demonstrate that BOIR outperforms two related methods from literature in terms of accuracy and uncertainty of the intent recognition.

KW - Bayesian Inference

KW - Human Operator Intent Recognition

KW - Human-in-the-Loop

KW - Human-robot Interaction

KW - Human-robot Teaming

UR - http://www.scopus.com/inward/record.url?scp=85124256936&partnerID=8YFLogxK

U2 - 10.1109/SMC52423.2021.9658942

DO - 10.1109/SMC52423.2021.9658942

M3 - Conference contribution

AN - SCOPUS:85124256936

SN - 9781665442084

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 125

EP - 131

BT - 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

PB - IEEE

T2 - 2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021

Y2 - 17 October 2021 through 20 October 2021

ER -

Panagopoulos DI, Petousakis G, Stolkin R, Nikolaou G, Chiou M. A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE. 2022. p. 125-131. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). doi: 10.1109/SMC52423.2021.9658942

A Bayesian-Based Approach to Human Operator Intent Recognition in Remote Mobile Robot Navigation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Research output

A Bayesian-based approach to human operator intent recognition in remote mobile robot navigation

Projects

National Centre for Nuclear Robotics (NCNR)

Cite this