A distributed monitoring approach for human interaction with multi-robot systems

Prashanth Krishnamurthy, Farshad Khorrami

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A novel methodology to enable robust and seamless human-robot interaction in the context of multi-robot systems (or swarms) is introduced based on a distributed multi-agent monitoring approach. Through real-time monitoring by each agent of other agents in its observable neighborhood, anomalies (due to malfunctions, cyber-attacks, etc.) in behavior of agents are detected within a probabilistic framework. In the proposed approach, anomaly likelihood estimation is based on how rational/explainable an observed agent's behavior is within the context of the estimated overall situational awareness. A distributed architecture is utilized wherein each agent bases its estimation of other agents' anomaly likelihoods on information currently available to the agent (e.g., from sensors, communications from other agents, etc.).

Original languageEnglish (US)
Title of host publicationHRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction
PublisherIEEE Computer Society
Pages173-174
Number of pages2
VolumePart F126657
ISBN (Electronic)9781450348850
DOIs
StatePublished - Mar 6 2017
Event12th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2017 - Vienna, Austria
Duration: Mar 6 2017Mar 9 2017

Other

Other12th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2017
CountryAustria
CityVienna
Period3/6/173/9/17

Fingerprint

Robots
Monitoring
Human robot interaction
Communication
Sensors

Keywords

  • collaboration
  • multi-agent systems
  • prototyping/implementation
  • real-time monitoring
  • safety-critical systems

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Krishnamurthy, P., & Khorrami, F. (2017). A distributed monitoring approach for human interaction with multi-robot systems. In HRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction (Vol. Part F126657, pp. 173-174). IEEE Computer Society. https://doi.org/10.1145/3029798.3038327

A distributed monitoring approach for human interaction with multi-robot systems. / Krishnamurthy, Prashanth; Khorrami, Farshad.

HRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction. Vol. Part F126657 IEEE Computer Society, 2017. p. 173-174.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Krishnamurthy, P & Khorrami, F 2017, A distributed monitoring approach for human interaction with multi-robot systems. in HRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction. vol. Part F126657, IEEE Computer Society, pp. 173-174, 12th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2017, Vienna, Austria, 3/6/17. https://doi.org/10.1145/3029798.3038327
Krishnamurthy P, Khorrami F. A distributed monitoring approach for human interaction with multi-robot systems. In HRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction. Vol. Part F126657. IEEE Computer Society. 2017. p. 173-174 https://doi.org/10.1145/3029798.3038327
Krishnamurthy, Prashanth ; Khorrami, Farshad. / A distributed monitoring approach for human interaction with multi-robot systems. HRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction. Vol. Part F126657 IEEE Computer Society, 2017. pp. 173-174
@inproceedings{571912fcc0474b0990195f7031fd8b87,
title = "A distributed monitoring approach for human interaction with multi-robot systems",
abstract = "A novel methodology to enable robust and seamless human-robot interaction in the context of multi-robot systems (or swarms) is introduced based on a distributed multi-agent monitoring approach. Through real-time monitoring by each agent of other agents in its observable neighborhood, anomalies (due to malfunctions, cyber-attacks, etc.) in behavior of agents are detected within a probabilistic framework. In the proposed approach, anomaly likelihood estimation is based on how rational/explainable an observed agent's behavior is within the context of the estimated overall situational awareness. A distributed architecture is utilized wherein each agent bases its estimation of other agents' anomaly likelihoods on information currently available to the agent (e.g., from sensors, communications from other agents, etc.).",
keywords = "collaboration, multi-agent systems, prototyping/implementation, real-time monitoring, safety-critical systems",
author = "Prashanth Krishnamurthy and Farshad Khorrami",
year = "2017",
month = "3",
day = "6",
doi = "10.1145/3029798.3038327",
language = "English (US)",
volume = "Part F126657",
pages = "173--174",
booktitle = "HRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - A distributed monitoring approach for human interaction with multi-robot systems

AU - Krishnamurthy, Prashanth

AU - Khorrami, Farshad

PY - 2017/3/6

Y1 - 2017/3/6

N2 - A novel methodology to enable robust and seamless human-robot interaction in the context of multi-robot systems (or swarms) is introduced based on a distributed multi-agent monitoring approach. Through real-time monitoring by each agent of other agents in its observable neighborhood, anomalies (due to malfunctions, cyber-attacks, etc.) in behavior of agents are detected within a probabilistic framework. In the proposed approach, anomaly likelihood estimation is based on how rational/explainable an observed agent's behavior is within the context of the estimated overall situational awareness. A distributed architecture is utilized wherein each agent bases its estimation of other agents' anomaly likelihoods on information currently available to the agent (e.g., from sensors, communications from other agents, etc.).

AB - A novel methodology to enable robust and seamless human-robot interaction in the context of multi-robot systems (or swarms) is introduced based on a distributed multi-agent monitoring approach. Through real-time monitoring by each agent of other agents in its observable neighborhood, anomalies (due to malfunctions, cyber-attacks, etc.) in behavior of agents are detected within a probabilistic framework. In the proposed approach, anomaly likelihood estimation is based on how rational/explainable an observed agent's behavior is within the context of the estimated overall situational awareness. A distributed architecture is utilized wherein each agent bases its estimation of other agents' anomaly likelihoods on information currently available to the agent (e.g., from sensors, communications from other agents, etc.).

KW - collaboration

KW - multi-agent systems

KW - prototyping/implementation

KW - real-time monitoring

KW - safety-critical systems

UR - http://www.scopus.com/inward/record.url?scp=85016441033&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016441033&partnerID=8YFLogxK

U2 - 10.1145/3029798.3038327

DO - 10.1145/3029798.3038327

M3 - Conference contribution

VL - Part F126657

SP - 173

EP - 174

BT - HRI 2017 - Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction

PB - IEEE Computer Society

ER -