Inferring guidance information in cooperative human-robot tasks

Erik Berger, David Vogt, Nooshin Haji-Ghassemi, Bernhard Jung, Hani Ben Amor

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

6 Citations (Scopus)

Abstract

In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.

Original languageEnglish (US)
Title of host publicationIEEE-RAS International Conference on Humanoid Robots
PublisherIEEE Computer Society
Pages124-129
Number of pages6
Volume2015-February
EditionFebruary
DOIs
StatePublished - Feb 3 2015
Externally publishedYes
Event2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013 - Atlanta, United States
Duration: Oct 15 2013Oct 17 2013

Other

Other2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013
CountryUnited States
CityAtlanta
Period10/15/1310/17/13

Fingerprint

Robots
Sensors
Robotics
Pressure sensors
Accelerometers
Learning systems
Statistical Models

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Berger, E., Vogt, D., Haji-Ghassemi, N., Jung, B., & Ben Amor, H. (2015). Inferring guidance information in cooperative human-robot tasks. In IEEE-RAS International Conference on Humanoid Robots (February ed., Vol. 2015-February, pp. 124-129). [7029966] IEEE Computer Society. https://doi.org/10.1109/HUMANOIDS.2013.7029966

Inferring guidance information in cooperative human-robot tasks. / Berger, Erik; Vogt, David; Haji-Ghassemi, Nooshin; Jung, Bernhard; Ben Amor, Hani.

IEEE-RAS International Conference on Humanoid Robots. Vol. 2015-February February. ed. IEEE Computer Society, 2015. p. 124-129 7029966.

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

Berger, E, Vogt, D, Haji-Ghassemi, N, Jung, B & Ben Amor, H 2015, Inferring guidance information in cooperative human-robot tasks. in IEEE-RAS International Conference on Humanoid Robots. February edn, vol. 2015-February, 7029966, IEEE Computer Society, pp. 124-129, 2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013, Atlanta, United States, 10/15/13. https://doi.org/10.1109/HUMANOIDS.2013.7029966
Berger E, Vogt D, Haji-Ghassemi N, Jung B, Ben Amor H. Inferring guidance information in cooperative human-robot tasks. In IEEE-RAS International Conference on Humanoid Robots. February ed. Vol. 2015-February. IEEE Computer Society. 2015. p. 124-129. 7029966 https://doi.org/10.1109/HUMANOIDS.2013.7029966
Berger, Erik ; Vogt, David ; Haji-Ghassemi, Nooshin ; Jung, Bernhard ; Ben Amor, Hani. / Inferring guidance information in cooperative human-robot tasks. IEEE-RAS International Conference on Humanoid Robots. Vol. 2015-February February. ed. IEEE Computer Society, 2015. pp. 124-129
@inproceedings{921fc7ba594a4df3937c4296fc5e07ea,
title = "Inferring guidance information in cooperative human-robot tasks",
abstract = "In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.",
author = "Erik Berger and David Vogt and Nooshin Haji-Ghassemi and Bernhard Jung and {Ben Amor}, Hani",
year = "2015",
month = "2",
day = "3",
doi = "10.1109/HUMANOIDS.2013.7029966",
language = "English (US)",
volume = "2015-February",
pages = "124--129",
booktitle = "IEEE-RAS International Conference on Humanoid Robots",
publisher = "IEEE Computer Society",
edition = "February",

}

TY - GEN

T1 - Inferring guidance information in cooperative human-robot tasks

AU - Berger, Erik

AU - Vogt, David

AU - Haji-Ghassemi, Nooshin

AU - Jung, Bernhard

AU - Ben Amor, Hani

PY - 2015/2/3

Y1 - 2015/2/3

N2 - In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.

AB - In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84937855652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937855652&partnerID=8YFLogxK

U2 - 10.1109/HUMANOIDS.2013.7029966

DO - 10.1109/HUMANOIDS.2013.7029966

M3 - Conference contribution

VL - 2015-February

SP - 124

EP - 129

BT - IEEE-RAS International Conference on Humanoid Robots

PB - IEEE Computer Society

ER -