Robust Localization Using Context-Aware Filtering
Radoslav Ivanov, Nikolay A. Atanasov, Miroslav Pajic, Insup Lee, George Pappas

Citation
Radoslav Ivanov, Nikolay A. Atanasov, Miroslav Pajic, Insup Lee, George Pappas. "Robust Localization Using Context-Aware Filtering". Workshop on Multi-view Geometry in Robotics at the Robotics: Science and Systems (RSS) Conference, 2015.

Abstract
In this paper we develop a robot localization technique that incorporates discrete context measurements, in addition to standard continuous state measurements. Context measurements provide binary information about detected events in the robot's environment, e.g., a building is recognized using image processing or a known radio station is received. Such measurements can only be detected from certain positions and can, therefore, be correlated with the robot's state. We investigate two specific examples where context measurements are especially useful - an urban localization scenario where GPS measurements are not reliable as well as the capture of the RQ-170 Sentinel drone in Iran, where GPS measurements were spoofed. By focusing on a specific class of probability of context detection functions, we derive a closed-form Gaussian mixture filter that is precise, captures context, and has the theoretical properties of the Kalman filter. Finally, we provide simulations of the urban localization scenario with an unmanned ground vehicle and show that the proposed context-aware filter is more robust and more accurate than the conventional extended Kalman filter, which only uses continuous measurements.

Electronic downloads

Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Radoslav Ivanov, Nikolay A. Atanasov, Miroslav Pajic, Insup
  Lee, George Pappas. <a
  href="http://www.terraswarm.org/pubs/598.html"
  >Robust Localization Using Context-Aware
  Filtering</a>, Workshop on Multi-view Geometry in
  Robotics at the Robotics: Science and Systems (RSS)
  Conference, 2015.

• Plain text

  Radoslav Ivanov, Nikolay A. Atanasov, Miroslav Pajic, Insup
  Lee, George Pappas. "Robust Localization Using
  Context-Aware Filtering". Workshop on Multi-view
  Geometry in Robotics at the Robotics: Science and Systems
  (RSS) Conference, 2015.

• BibTeX

  @inproceedings{IvanovAtanasovPajicLeePappas15_RobustLocalizationUsingContextAwareFiltering,
      author = {Radoslav Ivanov and Nikolay A. Atanasov and
                Miroslav Pajic and Insup Lee and George Pappas},
      title = {Robust Localization Using Context-Aware Filtering},
      booktitle = {Workshop on Multi-view Geometry in Robotics at the
                Robotics: Science and Systems (RSS) Conference},
      year = {2015},
      abstract = {In this paper we develop a robot localization
                technique that incorporates discrete context
                measurements, in addition to standard continuous
                state measurements. Context measurements provide
                binary information about detected events in the
                robot's environment, e.g., a building is
                recognized using image processing or a known radio
                station is received. Such measurements can only be
                detected from certain positions and can,
                therefore, be correlated with the robot's state.
                We investigate two specific examples where context
                measurements are especially useful - an urban
                localization scenario where GPS measurements are
                not reliable as well as the capture of the RQ-170
                Sentinel drone in Iran, where GPS measurements
                were spoofed. By focusing on a specific class of
                probability of context detection functions, we
                derive a closed-form Gaussian mixture filter that
                is precise, captures context, and has the
                theoretical properties of the Kalman filter.
                Finally, we provide simulations of the urban
                localization scenario with an unmanned ground
                vehicle and show that the proposed context-aware
                filter is more robust and more accurate than the
                conventional extended Kalman filter, which only
                uses continuous measurements.},
      URL = {http://terraswarm.org/pubs/598.html}
  }
  

Posted by Nikolay A. Atanasov on 7 Aug 2015.
Groups: services