Hu-bot: promoting the cooperation between humans and mobile robots

Karine Miras; Decebal Mocanu; A. E. Eiben

doi:10.1007/s00521-022-08061-z

Hu-bot: promoting the cooperation between humans and mobile robots

Karine Miras^*
, Decebal Mocanu
, A. E. Eiben

^*Corresponding author for this work

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

This paper investigates human–robot collaboration in a novel setup: a human helps a mobile robot that can move and navigate freely in an environment. Specifically, the human helps by remotely taking over control during the learning of a task. The task is to find and collect several items in a walled arena, and Reinforcement Learning is used to seek a suitable controller. If the human observes undesired robot behavior, they can directly issue commands for the wheels through a game joystick. Experiments in a simulator showed that human assistance improved robot behavior efficacy by 30% and efficiency by 12%. The best policies were also tested in real life, using physical robots. Hardware experiments showed no significant difference concerning the simulations, providing empirical validation of our approach in practice.

Original language	English
Pages (from-to)	16841-16852
Number of pages	12
Journal	Neural Computing and Applications
Volume	35
Issue number	23
Early online date	13 Jan 2023
DOIs	https://doi.org/10.1007/s00521-022-08061-z
Publication status	Published - Aug 2023

Bibliographical note

Funding Information:
This research was funded by the Hybrid Intelligence Center, a 10-year program funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organization for Scientific Research ( https://www.hybrid-intelligence-centre.nl ), Grant No. 024.004.022.

Publisher Copyright:
© 2023, The Author(s).

Funding

This research was funded by the Hybrid Intelligence Center, a 10-year program funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organization for Scientific Research ( https://www.hybrid-intelligence-centre.nl ), Grant No. 024.004.022.

Keywords

Automation
Human-in-the-loop
Human–robot cooperation
Mobile robots
Reinforcement learning
Safety

Access to Document

10.1007/s00521-022-08061-z

Persistent URL (handle)

Persistent link

Cite this

@article{f187fd45b18d46fa945ab72e2d981510,

title = "Hu-bot: promoting the cooperation between humans and mobile robots",

abstract = "This paper investigates human–robot collaboration in a novel setup: a human helps a mobile robot that can move and navigate freely in an environment. Specifically, the human helps by remotely taking over control during the learning of a task. The task is to find and collect several items in a walled arena, and Reinforcement Learning is used to seek a suitable controller. If the human observes undesired robot behavior, they can directly issue commands for the wheels through a game joystick. Experiments in a simulator showed that human assistance improved robot behavior efficacy by 30\% and efficiency by 12\%. The best policies were also tested in real life, using physical robots. Hardware experiments showed no significant difference concerning the simulations, providing empirical validation of our approach in practice.",

keywords = "Automation, Human-in-the-loop, Human–robot cooperation, Mobile robots, Reinforcement learning, Safety",

author = "Karine Miras and Decebal Mocanu and Eiben, \{A. E.\}",

note = "Funding Information: This research was funded by the Hybrid Intelligence Center, a 10-year program funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organization for Scientific Research ( https://www.hybrid-intelligence-centre.nl ), Grant No. 024.004.022. Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = aug,

doi = "10.1007/s00521-022-08061-z",

language = "English",

volume = "35",

pages = "16841--16852",

journal = "Neural Computing and Applications",

issn = "0941-0643",

publisher = "Springer London",

number = "23",

}

TY - JOUR

T1 - Hu-bot

T2 - promoting the cooperation between humans and mobile robots

AU - Miras, Karine

AU - Mocanu, Decebal

AU - Eiben, A. E.

N1 - Funding Information: This research was funded by the Hybrid Intelligence Center, a 10-year program funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organization for Scientific Research ( https://www.hybrid-intelligence-centre.nl ), Grant No. 024.004.022. Publisher Copyright: © 2023, The Author(s).

PY - 2023/8

Y1 - 2023/8

N2 - This paper investigates human–robot collaboration in a novel setup: a human helps a mobile robot that can move and navigate freely in an environment. Specifically, the human helps by remotely taking over control during the learning of a task. The task is to find and collect several items in a walled arena, and Reinforcement Learning is used to seek a suitable controller. If the human observes undesired robot behavior, they can directly issue commands for the wheels through a game joystick. Experiments in a simulator showed that human assistance improved robot behavior efficacy by 30% and efficiency by 12%. The best policies were also tested in real life, using physical robots. Hardware experiments showed no significant difference concerning the simulations, providing empirical validation of our approach in practice.

AB - This paper investigates human–robot collaboration in a novel setup: a human helps a mobile robot that can move and navigate freely in an environment. Specifically, the human helps by remotely taking over control during the learning of a task. The task is to find and collect several items in a walled arena, and Reinforcement Learning is used to seek a suitable controller. If the human observes undesired robot behavior, they can directly issue commands for the wheels through a game joystick. Experiments in a simulator showed that human assistance improved robot behavior efficacy by 30% and efficiency by 12%. The best policies were also tested in real life, using physical robots. Hardware experiments showed no significant difference concerning the simulations, providing empirical validation of our approach in practice.

KW - Automation

KW - Human-in-the-loop

KW - Human–robot cooperation

KW - Mobile robots

KW - Reinforcement learning

KW - Safety

UR - https://www.scopus.com/pages/publications/85146250864

UR - https://www.scopus.com/pages/publications/85146250864#tab=citedBy

U2 - 10.1007/s00521-022-08061-z

DO - 10.1007/s00521-022-08061-z

M3 - Article

AN - SCOPUS:85146250864

SN - 0941-0643

VL - 35

SP - 16841

EP - 16852

JO - Neural Computing and Applications

JF - Neural Computing and Applications

IS - 23

ER -

Hu-bot: promoting the cooperation between humans and mobile robots

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this