An artificial language for data-driven self-adaptation of networked robots in dynamic environments

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

Abstract

The interactive dynamics of goal-oriented multi-agent networked robots with on-board sensing, computation, and actuation devices, present a complex distributed computational environment of high dimensionality. The generating physics of such a system operating in an uncertain environment can be adequately captured in an artificial language that expresses the causal patterns observable in sensor data with maximal compression while preserving the statistical predictability of system states under Markovian assumptions. Hence it enables time-constrained in-situ distributed computation, communication, and data-driven adaptive control in resource-constrained uncertain operational environments. The multivariate sensor data is partitioned and symbolized for deriving the alphabet of the language. Observed data from multiple sensors is expressed as a univariate sequence of symbols from this alphabet. The semantics of the language are extracted from the observed data streams as invariant patterns which capture the essential causal structure of the dynamic system. An undersea mine-hunting mission using an undersea robot with on-board side-scan sonar is used to illustrate the development and use of this physics-driven computational language for time-constrained situational awareness and adaptive control.

Original languageEnglish (US)
Title of host publicationProceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013
Pages186-194
Number of pages9
DOIs
StatePublished - Aug 20 2013
Event8th International Conference on Computer Science and Education, ICCSE 2013 - Colombo, Sri Lanka
Duration: Aug 26 2013Aug 28 2013

Publication series

NameProceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013

Other

Other8th International Conference on Computer Science and Education, ICCSE 2013
CountrySri Lanka
CityColombo
Period8/26/138/28/13

Fingerprint

robot
Robots
Sensors
Physics
language
Sonar
physics
Dynamical systems
Semantics
Communication
symbol
semantics
communication
resources
time

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)
  • Education

Cite this

Phoha, S., & Ray, A. (2013). An artificial language for data-driven self-adaptation of networked robots in dynamic environments. In Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013 (pp. 186-194). [6553908] (Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013). https://doi.org/10.1109/ICCSE.2013.6553908
Phoha, Shashi ; Ray, Asok. / An artificial language for data-driven self-adaptation of networked robots in dynamic environments. Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013. 2013. pp. 186-194 (Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013).
@inproceedings{52767bda2ea2472bbf0877455a2a72d6,
title = "An artificial language for data-driven self-adaptation of networked robots in dynamic environments",
abstract = "The interactive dynamics of goal-oriented multi-agent networked robots with on-board sensing, computation, and actuation devices, present a complex distributed computational environment of high dimensionality. The generating physics of such a system operating in an uncertain environment can be adequately captured in an artificial language that expresses the causal patterns observable in sensor data with maximal compression while preserving the statistical predictability of system states under Markovian assumptions. Hence it enables time-constrained in-situ distributed computation, communication, and data-driven adaptive control in resource-constrained uncertain operational environments. The multivariate sensor data is partitioned and symbolized for deriving the alphabet of the language. Observed data from multiple sensors is expressed as a univariate sequence of symbols from this alphabet. The semantics of the language are extracted from the observed data streams as invariant patterns which capture the essential causal structure of the dynamic system. An undersea mine-hunting mission using an undersea robot with on-board side-scan sonar is used to illustrate the development and use of this physics-driven computational language for time-constrained situational awareness and adaptive control.",
author = "Shashi Phoha and Asok Ray",
year = "2013",
month = "8",
day = "20",
doi = "10.1109/ICCSE.2013.6553908",
language = "English (US)",
isbn = "9781467344623",
series = "Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013",
pages = "186--194",
booktitle = "Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013",

}

Phoha, S & Ray, A 2013, An artificial language for data-driven self-adaptation of networked robots in dynamic environments. in Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013., 6553908, Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013, pp. 186-194, 8th International Conference on Computer Science and Education, ICCSE 2013, Colombo, Sri Lanka, 8/26/13. https://doi.org/10.1109/ICCSE.2013.6553908

An artificial language for data-driven self-adaptation of networked robots in dynamic environments. / Phoha, Shashi; Ray, Asok.

Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013. 2013. p. 186-194 6553908 (Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013).

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

TY - GEN

T1 - An artificial language for data-driven self-adaptation of networked robots in dynamic environments

AU - Phoha, Shashi

AU - Ray, Asok

PY - 2013/8/20

Y1 - 2013/8/20

N2 - The interactive dynamics of goal-oriented multi-agent networked robots with on-board sensing, computation, and actuation devices, present a complex distributed computational environment of high dimensionality. The generating physics of such a system operating in an uncertain environment can be adequately captured in an artificial language that expresses the causal patterns observable in sensor data with maximal compression while preserving the statistical predictability of system states under Markovian assumptions. Hence it enables time-constrained in-situ distributed computation, communication, and data-driven adaptive control in resource-constrained uncertain operational environments. The multivariate sensor data is partitioned and symbolized for deriving the alphabet of the language. Observed data from multiple sensors is expressed as a univariate sequence of symbols from this alphabet. The semantics of the language are extracted from the observed data streams as invariant patterns which capture the essential causal structure of the dynamic system. An undersea mine-hunting mission using an undersea robot with on-board side-scan sonar is used to illustrate the development and use of this physics-driven computational language for time-constrained situational awareness and adaptive control.

AB - The interactive dynamics of goal-oriented multi-agent networked robots with on-board sensing, computation, and actuation devices, present a complex distributed computational environment of high dimensionality. The generating physics of such a system operating in an uncertain environment can be adequately captured in an artificial language that expresses the causal patterns observable in sensor data with maximal compression while preserving the statistical predictability of system states under Markovian assumptions. Hence it enables time-constrained in-situ distributed computation, communication, and data-driven adaptive control in resource-constrained uncertain operational environments. The multivariate sensor data is partitioned and symbolized for deriving the alphabet of the language. Observed data from multiple sensors is expressed as a univariate sequence of symbols from this alphabet. The semantics of the language are extracted from the observed data streams as invariant patterns which capture the essential causal structure of the dynamic system. An undersea mine-hunting mission using an undersea robot with on-board side-scan sonar is used to illustrate the development and use of this physics-driven computational language for time-constrained situational awareness and adaptive control.

UR - http://www.scopus.com/inward/record.url?scp=84881533973&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881533973&partnerID=8YFLogxK

U2 - 10.1109/ICCSE.2013.6553908

DO - 10.1109/ICCSE.2013.6553908

M3 - Conference contribution

SN - 9781467344623

T3 - Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013

SP - 186

EP - 194

BT - Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013

ER -

Phoha S, Ray A. An artificial language for data-driven self-adaptation of networked robots in dynamic environments. In Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013. 2013. p. 186-194. 6553908. (Proceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013). https://doi.org/10.1109/ICCSE.2013.6553908