Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization

Giuseppe Loianno, Vincenzo Lippiello, Carlo Fischione, Bruno Siciliano

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

Abstract

Motion estimation is an open research field in control and robotic applications. Sensor fusion algorithms are generally used to achieve an accurate estimation of the vehicle motion by combining heterogeneous sensors measurements with different statistical characteristics. In this paper, a new method that combines measurements provided by an inertial sensor and a vision system is presented. Compared to classical modelbased techniques, the method relies on a Pareto optimization that trades off the statistical properties of the measurements. The proposed technique is evaluated with simulations in terms of computational requirements and estimation accuracy with respect to a classical Kalman filter approach. It is shown that the proposed method gives an improved estimation accuracy at the cost of a slightly increased computational complexity.

Original languageEnglish (US)
Title of host publicationIROS 2013
Subtitle of host publicationNew Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems
Pages3993-3999
Number of pages7
DOIs
StatePublished - Dec 1 2013
Event2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013 - Tokyo, Japan
Duration: Nov 3 2013Nov 8 2013

Other

Other2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013
CountryJapan
CityTokyo
Period11/3/1311/8/13

Fingerprint

Data fusion
Motion estimation
Sensors
Kalman filters
Computational complexity
Robotics

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Loianno, G., Lippiello, V., Fischione, C., & Siciliano, B. (2013). Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization. In IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 3993-3999). [6696927] https://doi.org/10.1109/IROS.2013.6696927

Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization. / Loianno, Giuseppe; Lippiello, Vincenzo; Fischione, Carlo; Siciliano, Bruno.

IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2013. p. 3993-3999 6696927.

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

Loianno, G, Lippiello, V, Fischione, C & Siciliano, B 2013, Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization. in IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems., 6696927, pp. 3993-3999, 2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013, Tokyo, Japan, 11/3/13. https://doi.org/10.1109/IROS.2013.6696927
Loianno G, Lippiello V, Fischione C, Siciliano B. Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization. In IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2013. p. 3993-3999. 6696927 https://doi.org/10.1109/IROS.2013.6696927
Loianno, Giuseppe ; Lippiello, Vincenzo ; Fischione, Carlo ; Siciliano, Bruno. / Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization. IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2013. pp. 3993-3999
@inproceedings{6cc0310773c04051aad34da7ed7b688d,
title = "Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization",
abstract = "Motion estimation is an open research field in control and robotic applications. Sensor fusion algorithms are generally used to achieve an accurate estimation of the vehicle motion by combining heterogeneous sensors measurements with different statistical characteristics. In this paper, a new method that combines measurements provided by an inertial sensor and a vision system is presented. Compared to classical modelbased techniques, the method relies on a Pareto optimization that trades off the statistical properties of the measurements. The proposed technique is evaluated with simulations in terms of computational requirements and estimation accuracy with respect to a classical Kalman filter approach. It is shown that the proposed method gives an improved estimation accuracy at the cost of a slightly increased computational complexity.",
author = "Giuseppe Loianno and Vincenzo Lippiello and Carlo Fischione and Bruno Siciliano",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/IROS.2013.6696927",
language = "English (US)",
isbn = "9781467363587",
pages = "3993--3999",
booktitle = "IROS 2013",

}

TY - GEN

T1 - Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization

AU - Loianno, Giuseppe

AU - Lippiello, Vincenzo

AU - Fischione, Carlo

AU - Siciliano, Bruno

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Motion estimation is an open research field in control and robotic applications. Sensor fusion algorithms are generally used to achieve an accurate estimation of the vehicle motion by combining heterogeneous sensors measurements with different statistical characteristics. In this paper, a new method that combines measurements provided by an inertial sensor and a vision system is presented. Compared to classical modelbased techniques, the method relies on a Pareto optimization that trades off the statistical properties of the measurements. The proposed technique is evaluated with simulations in terms of computational requirements and estimation accuracy with respect to a classical Kalman filter approach. It is shown that the proposed method gives an improved estimation accuracy at the cost of a slightly increased computational complexity.

AB - Motion estimation is an open research field in control and robotic applications. Sensor fusion algorithms are generally used to achieve an accurate estimation of the vehicle motion by combining heterogeneous sensors measurements with different statistical characteristics. In this paper, a new method that combines measurements provided by an inertial sensor and a vision system is presented. Compared to classical modelbased techniques, the method relies on a Pareto optimization that trades off the statistical properties of the measurements. The proposed technique is evaluated with simulations in terms of computational requirements and estimation accuracy with respect to a classical Kalman filter approach. It is shown that the proposed method gives an improved estimation accuracy at the cost of a slightly increased computational complexity.

UR - http://www.scopus.com/inward/record.url?scp=84893752076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893752076&partnerID=8YFLogxK

U2 - 10.1109/IROS.2013.6696927

DO - 10.1109/IROS.2013.6696927

M3 - Conference contribution

SN - 9781467363587

SP - 3993

EP - 3999

BT - IROS 2013

ER -