A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics

Dimitris Panagopoulos; Giannis Petousakis; Aniketh Ramesh; Tianshu Ruan; Grigoris Nikolaou; Rustam Stolkin; Manolis Chiou

doi:10.1109/ICHMS56717.2022.9980686

A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics

Dimitris Panagopoulos, Giannis Petousakis, Aniketh Ramesh, Tianshu Ruan, Grigoris Nikolaou, Rustam Stolkin, Manolis Chiou

Metallurgy and Materials

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

Abstract

This paper presents a Mixed-Initiative (MI) framework for addressing the problem of control authority transfer between a remote human operator and an AI agent when cooperatively controlling a mobile robot. Our Hierarchical Expert-guided Mixed-Initiative Control Switcher (HierEMICS) leverages information on the human operator's state and intent. The control switching policies are based on a criticality hierarchy. An experimental evaluation was conducted in a high-fidelity simulated disaster response and remote inspection scenario, comparing HierEMICS with a state-of-the-art Expert-guided Mixed-Initiative Control Switcher (EMICS) in the context of mobile robot navigation. Results suggest that HierEMICS reduces conflicts for control between the human and the AI agent, which is a fundamental challenge in both the MI control paradigm and also in the related shared control paradigm. Additionally, we provide statistically significant evidence of improved, navigational safety (i.e., fewer collisions), LOA switching efficiency, and conflict for control reduction.

Original language	English
Title of host publication	2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS)
Editors	David Kaber, Antonio Guerrieri, Giancarlo Fortino, Andreas Nurnberger
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9781665452380
ISBN (Print)	9781665452397 (PoD)
DOIs	https://doi.org/10.1109/ICHMS56717.2022.9980686
Publication status	Published - 19 Dec 2022
Event	3rd IEEE International Conference on Human-Machine Systems, ICHMS 2022 - Orlando, United States Duration: 17 Nov 2022 → 19 Nov 2022

Publication series

Name	IEEE International Conference on Human-Machine Systems

Conference

Conference	3rd IEEE International Conference on Human-Machine Systems, ICHMS 2022
Country/Territory	United States
City	Orlando
Period	17/11/22 → 19/11/22

Bibliographical note

Funding Information:
* First and second authors contributed equally. This work was supported by the EPSRC grant EP/P01366X/1. 978-1-6654-5238-0/22/$31.00 ©2022 IEEE

Publisher Copyright:
© 2022 IEEE.

Keywords

Cognitive Availability
Human state
Human-in-the-Loop
Human-Robot Interaction
Human-Robot Teaming
Intent Recognition
Mixed-Initiative
Transfer of Control
Variable Autonomy

ASJC Scopus subject areas

Human-Computer Interaction
Media Technology
Control and Optimization

Access to Document

10.1109/ICHMS56717.2022.9980686

Robotics for Nuclear Environments - Lead Manchester University (EP/P01366X/1)
Leonardis, A. & Stolkin, R.
Engineering & Physical Science Research Council
1/04/17 → 31/03/23
Project: Research

Cite this

Panagopoulos, D., Petousakis, G., Ramesh, A., Ruan, T., Nikolaou, G., Stolkin, R., & Chiou, M. (2022). A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics. In D. Kaber, A. Guerrieri, G. Fortino, & A. Nurnberger (Eds.), 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS) Article 9980686 (IEEE International Conference on Human-Machine Systems). IEEE. https://doi.org/10.1109/ICHMS56717.2022.9980686

Panagopoulos, Dimitris ; Petousakis, Giannis ; Ramesh, Aniketh et al. / A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics. 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS). editor / David Kaber ; Antonio Guerrieri ; Giancarlo Fortino ; Andreas Nurnberger. IEEE, 2022. (IEEE International Conference on Human-Machine Systems).

@inproceedings{c0ecae3a2a8d434b93ede8d7e0ee227a,

title = "A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics",

abstract = "This paper presents a Mixed-Initiative (MI) framework for addressing the problem of control authority transfer between a remote human operator and an AI agent when cooperatively controlling a mobile robot. Our Hierarchical Expert-guided Mixed-Initiative Control Switcher (HierEMICS) leverages information on the human operator's state and intent. The control switching policies are based on a criticality hierarchy. An experimental evaluation was conducted in a high-fidelity simulated disaster response and remote inspection scenario, comparing HierEMICS with a state-of-the-art Expert-guided Mixed-Initiative Control Switcher (EMICS) in the context of mobile robot navigation. Results suggest that HierEMICS reduces conflicts for control between the human and the AI agent, which is a fundamental challenge in both the MI control paradigm and also in the related shared control paradigm. Additionally, we provide statistically significant evidence of improved, navigational safety (i.e., fewer collisions), LOA switching efficiency, and conflict for control reduction.",

keywords = "Cognitive Availability, Human state, Human-in-the-Loop, Human-Robot Interaction, Human-Robot Teaming, Intent Recognition, Mixed-Initiative, Transfer of Control, Variable Autonomy",

author = "Dimitris Panagopoulos and Giannis Petousakis and Aniketh Ramesh and Tianshu Ruan and Grigoris Nikolaou and Rustam Stolkin and Manolis Chiou",

note = "Funding Information: * First and second authors contributed equally. This work was supported by the EPSRC grant EP/P01366X/1. 978-1-6654-5238-0/22/$31.00 {\textcopyright}2022 IEEE Publisher Copyright: {\textcopyright} 2022 IEEE.; 3rd IEEE International Conference on Human-Machine Systems, ICHMS 2022 ; Conference date: 17-11-2022 Through 19-11-2022",

year = "2022",

month = dec,

day = "19",

doi = "10.1109/ICHMS56717.2022.9980686",

language = "English",

isbn = "9781665452397 (PoD)",

series = "IEEE International Conference on Human-Machine Systems",

publisher = "IEEE",

editor = "David Kaber and Antonio Guerrieri and Giancarlo Fortino and Andreas Nurnberger",

booktitle = "2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS)",

}

Panagopoulos, D, Petousakis, G, Ramesh, A, Ruan, T, Nikolaou, G, Stolkin, R & Chiou, M 2022, A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics. in D Kaber, A Guerrieri, G Fortino & A Nurnberger (eds), 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS)., 9980686, IEEE International Conference on Human-Machine Systems, IEEE, 3rd IEEE International Conference on Human-Machine Systems, ICHMS 2022, Orlando, United States, 17/11/22. https://doi.org/10.1109/ICHMS56717.2022.9980686

A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics. / Panagopoulos, Dimitris; Petousakis, Giannis; Ramesh, Aniketh et al.
2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS). ed. / David Kaber; Antonio Guerrieri; Giancarlo Fortino; Andreas Nurnberger. IEEE, 2022. 9980686 (IEEE International Conference on Human-Machine Systems).

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

TY - GEN

T1 - A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics

AU - Panagopoulos, Dimitris

AU - Petousakis, Giannis

AU - Ramesh, Aniketh

AU - Ruan, Tianshu

AU - Nikolaou, Grigoris

AU - Stolkin, Rustam

AU - Chiou, Manolis

N1 - Funding Information: * First and second authors contributed equally. This work was supported by the EPSRC grant EP/P01366X/1. 978-1-6654-5238-0/22/$31.00 ©2022 IEEE Publisher Copyright: © 2022 IEEE.

PY - 2022/12/19

Y1 - 2022/12/19

N2 - This paper presents a Mixed-Initiative (MI) framework for addressing the problem of control authority transfer between a remote human operator and an AI agent when cooperatively controlling a mobile robot. Our Hierarchical Expert-guided Mixed-Initiative Control Switcher (HierEMICS) leverages information on the human operator's state and intent. The control switching policies are based on a criticality hierarchy. An experimental evaluation was conducted in a high-fidelity simulated disaster response and remote inspection scenario, comparing HierEMICS with a state-of-the-art Expert-guided Mixed-Initiative Control Switcher (EMICS) in the context of mobile robot navigation. Results suggest that HierEMICS reduces conflicts for control between the human and the AI agent, which is a fundamental challenge in both the MI control paradigm and also in the related shared control paradigm. Additionally, we provide statistically significant evidence of improved, navigational safety (i.e., fewer collisions), LOA switching efficiency, and conflict for control reduction.

AB - This paper presents a Mixed-Initiative (MI) framework for addressing the problem of control authority transfer between a remote human operator and an AI agent when cooperatively controlling a mobile robot. Our Hierarchical Expert-guided Mixed-Initiative Control Switcher (HierEMICS) leverages information on the human operator's state and intent. The control switching policies are based on a criticality hierarchy. An experimental evaluation was conducted in a high-fidelity simulated disaster response and remote inspection scenario, comparing HierEMICS with a state-of-the-art Expert-guided Mixed-Initiative Control Switcher (EMICS) in the context of mobile robot navigation. Results suggest that HierEMICS reduces conflicts for control between the human and the AI agent, which is a fundamental challenge in both the MI control paradigm and also in the related shared control paradigm. Additionally, we provide statistically significant evidence of improved, navigational safety (i.e., fewer collisions), LOA switching efficiency, and conflict for control reduction.

KW - Cognitive Availability

KW - Human state

KW - Human-in-the-Loop

KW - Human-Robot Interaction

KW - Human-Robot Teaming

KW - Intent Recognition

KW - Mixed-Initiative

KW - Transfer of Control

KW - Variable Autonomy

UR - http://www.scopus.com/inward/record.url?scp=85146298464&partnerID=8YFLogxK

U2 - 10.1109/ICHMS56717.2022.9980686

DO - 10.1109/ICHMS56717.2022.9980686

M3 - Conference contribution

AN - SCOPUS:85146298464

SN - 9781665452397 (PoD)

T3 - IEEE International Conference on Human-Machine Systems

BT - 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS)

A2 - Kaber, David

A2 - Guerrieri, Antonio

A2 - Fortino, Giancarlo

A2 - Nurnberger, Andreas

PB - IEEE

T2 - 3rd IEEE International Conference on Human-Machine Systems, ICHMS 2022

Y2 - 17 November 2022 through 19 November 2022

ER -

Panagopoulos D, Petousakis G, Ramesh A, Ruan T, Nikolaou G, Stolkin R et al. A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics. In Kaber D, Guerrieri A, Fortino G, Nurnberger A, editors, 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS). IEEE. 2022. 9980686. (IEEE International Conference on Human-Machine Systems). doi: 10.1109/ICHMS56717.2022.9980686

A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Projects

Robotics for Nuclear Environments - Lead Manchester University (EP/P01366X/1)

Cite this