Distributed Robust Inference and Data Association

We consider multi-robot inference over variables of interest (e.g. robot poses), from unknown initial robot poses and undetermined data association. This problem is relevant for different multi-robot collaborative applications, such as cooperative mapping, localization, tracking, and surveillance. Collaboration requires the robots to share a common world model and to be able to correctly interpret information communicated with each other. We show that establishing this collaboration first requires inferring concurrently a common reference frame between the robots and resolving data association. The problem becomes even more challenging in the incremental setting and in presence of perceptual aliasing (e.g. two different but similar in appearance corridors). We develop an Expectation-Maximization (EM) and model selection framework to address this problem.

Below is a demonstration of our approach using real-world experiment involving two quadrotors (colored blue and red) operating in indoor environment and sharing informative laser scans. As the robots do not have a common reference frame established, their initial poses are set to /arbitrary/ values; in practice, both robots start operating from the same location (middle image). Multi-robot candidate correspondences are generated by ICP-matching the shared laser scans. After some time, our approach successfully estimates the initial relative pose between the robots and determines multi-robot data association (right image). From that moment, it becomes possible for the robots to robustly infer variables of interest, in this case each other’s trajectories, and to identify the inlier correspondences (denoted in black) in newly arriving data. The movie shows the process from the perspective of each robot (first red and then blue robot).

A distributed real-time implementation of the approach is demonstrated below.

Related Publications:

Articles

  • V. Indelman, E. Nelson, J. Dong, N. Michael, and F. Dellaert. Incremental Distributed Inference from Arbitrary Poses and Unknown Data Association: Using Collaborating Robots to Establish a Common Reference. IEEE Control Systems Magazine (CSM), Special Issue on Distributed Control and Estimation for Robotic Vehicle Networks, 36(2):41-74, 2016.
    [BibTeX] [URL] [PDF]
    @Article{Indelman16csm,
    author = {V. Indelman and E. Nelson and J. Dong and N. Michael, and F. Dellaert},
    title = {Incremental Distributed Inference from Arbitrary Poses and Unknown Data Association: Using Collaborating Robots to Establish a Common Reference},
    journal = "IEEE Control Systems Magazine (CSM), Special Issue on Distributed Control and Estimation for Robotic Vehicle Networks",
    year = 2016,
    volume = {36},
    number = {2},
    pages = {41-74},
    url = "http://ieeexplore.ieee.org/xpl/abstractAuthors.jsp?reload=true&arnumber=7434165",
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Indelman16csm.pdf",
    researchtopic = {DistributedRobust, DistributedMultiRobotNav},
    }

In Collections

  • E. Nelson, V. Indelman, N. Michael, and F. Dellaert. An Experimental Study of Robust Distributed Multi-Robot Data Association from Arbitrary Poses. In Experimental Robotics, The 14th International Symposium on Experimental Robotics, Springer Tracts in Advanced Robotics 109, pages 323-338. Springer, 2016.
    [BibTeX] [URL] [PDF]
    @incollection{Nelson16chapter,
    booktitle={Experimental Robotics, The 14th International Symposium on Experimental Robotics},
    series={Springer Tracts in Advanced Robotics 109},
    title={An Experimental Study of Robust Distributed Multi-Robot Data Association from Arbitrary Poses},
    publisher={Springer},
    author={E. Nelson and V. Indelman and N. Michael and F. Dellaert},
    pages="323-338",
    year={2016},
    url = "http://link.springer.com/chapter/10.1007%2F978-3-319-23778-7_22",
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Nelson16chapter.pdf",
    researchtopic = {DistributedRobust},
    }

In Proceedings

  • S. Pathak, A. Thomas, A. Feniger, and V. Indelman. Towards Data Association Aware Belief Space Planning for Robust Active Perception. In AI for Long-term Autonomy, workshop in conjunction with IEEE International Conference on Robotics and Automation (ICRA), May 2016.
    [BibTeX] [PDF] [Poster]
    @inproceedings{Pathak16icra_ws,
    author = {S. Pathak and A. Thomas and A. Feniger and V. Indelman},
    title = {Towards Data Association Aware Belief Space Planning for Robust Active Perception},
    booktitle = {AI for Long-term Autonomy, workshop in conjunction with IEEE International Conference on Robotics and Automation (ICRA)},
    year = 2016,
    month = "May",
    location = {Sweden},
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Pathak16icra_ws.pdf",
    poster = "http://indelman.github.io/ANPL-Website/Publications/Pathak16icra_ws_poster.pdf",
    researchtopic = {RAP, DistributedRobust},
    }

  • J. Dong, E. Nelson, V. Indelman, N. Michael, and F. Dellaert. Distributed Real-time Cooperative Localization and Mapping using an Uncertainty-Aware Expectation Maximization Approach. In IEEE International Conference on Robotics and Automation (ICRA), May 2015.
    [BibTeX] [PDF] [Slides] [Video]
    @InProceedings{Dong15icra,
    author = {J. Dong and E. Nelson and V. Indelman and N. Michael and F. Dellaert},
    title = {Distributed Real-time Cooperative Localization and Mapping using an Uncertainty-Aware Expectation Maximization Approach},
    booktitle = "IEEE International Conference on Robotics and Automation (ICRA)",
    year = 2015,
    month = "May",
    location = {Washington, USA},
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Dong15icra.pdf",
    slides = "http://indelman.github.io/ANPL-Website/Publications/Dong15icra_ppt.pdf",
    video = "https://www.youtube.com/watch?v=m_bLSdsT2kg",
    researchtopic = {DistributedRobust},
    }

  • V. Indelman, E. Nelson, N. Michael, and F. Dellaert. Distributed Navigation with Unknown Initial Poses and Data Association via Expectation Maximization. In 56th Israel Annual Conference on Aerospace Sciences, March 2015.
    [BibTeX] [PDF] [Slides]
    @InProceedings{Indelman15iacas_c,
    author = {V. Indelman and E. Nelson and N. Michael and F. Dellaert},
    title = {Distributed Navigation with Unknown Initial Poses and Data Association via Expectation Maximization},
    booktitle = {56th Israel Annual Conference on Aerospace Sciences},
    year = 2015,
    month = "March",
    location = {Israel},
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Indelman15iacas_c.pdf",
    slides = "http://indelman.github.io/ANPL-Website/Publications/Indelman15iacas_c_ppt.pdf",
    researchtopic = {DistributedRobust, DistributedMultiRobotNav},
    }

  • V. Indelman, N. Michael, and F. Dellaert. Incremental Distributed Robust Inference from Arbitrary Robot Poses via EM and Model Selection. In RSS Workshop on Distributed Control and Estimation for Robotic Vehicle Networks, July 2014.
    [BibTeX] [PDF] [Poster]
    @InProceedings{Indelman14rss_ws,
    author = {V. Indelman and N. Michael and F. Dellaert},
    title = {Incremental Distributed Robust Inference from Arbitrary Robot Poses via EM and Model Selection},
    booktitle = "RSS Workshop on Distributed Control and Estimation for Robotic Vehicle Networks",
    year = 2014,
    month = "July",
    location = {Berkeley, USA},
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Indelman14rss_ws.pdf",
    poster = "http://indelman.github.io/ANPL-Website/Publications/Indelman14rss_ws_poster.pdf",
    researchtopic = {DistributedRobust},
    }

  • E. Nelson, V. Indelman, N. Michael, and F. Dellaert. An Experimental Study of Robust Distributed Multi-Robot Data Association from Arbitrary Poses. In International Symposium on Experimental Robotics (ISER), June 2014.
    [BibTeX] [PDF] [Slides]
    @InProceedings{Nelson14iser,
    author = {E. Nelson and V. Indelman and N. Michael and F. Dellaert},
    title = {An Experimental Study of Robust Distributed Multi-Robot Data Association from Arbitrary Poses},
    booktitle = "International Symposium on Experimental Robotics (ISER)",
    year = 2014,
    month = "June",
    location = {Morocco},
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Nelson14iser.pdf",
    slides = "http://indelman.github.io/ANPL-Website/Publications/Nelson14iser_ppt.pdf",
    researchtopic = {DistributedRobust},
    }

  • V. Indelman, E. Nelson, N. Michael, and F. Dellaert. Multi-Robot Pose Graph Localization and Data Association from Unknown Initial Relative Poses via Expectation Maximization. In IEEE International Conference on Robotics and Automation (ICRA), June 2014.
    [BibTeX] [PDF] [Slides]
    @InProceedings{Indelman14icra_b,
    author = {V. Indelman and E. Nelson and N. Michael and F. Dellaert},
    title = {Multi-Robot Pose Graph Localization and Data Association from Unknown Initial Relative Poses via Expectation Maximization},
    booktitle = "IEEE International Conference on Robotics and Automation (ICRA)",
    year = 2014,
    month = "June",
    location = {Hong Kong, China},
    pdf = "http://indelman.github.io/ANPL-Website/Publications/Indelman14icra_b.pdf",
    slides = "http://indelman.github.io/ANPL-Website/Publications/Indelman14icra_b_ppt.pdf",
    researchtopic = {DistributedRobust},
    }

wordpress stat