Distributed Multi-Robot Cooperative Navigation

A multi-agent scenario is considered, in which the different robots share information to improve navigation and extend sensing. A graph-based approach was developed to guarantee a consistent information fusion between the different robots assuming a general multi-robot measurement model. Using the graph structure, separately maintained by each robot, appropriate correlation terms are calculated upon-demand and used within the update step of the filter. The method (see IJRR2012) is also applicable to implicit measurement models and in particular when using three-view geometry constraints (more details). Such an approach was developed in RAS2012, where the three-view constraints are applied whenever the robots observe a common scene. One thing to note is that the scene does not necessarily have to be observed by the robots at the same time. A consistent decentralized data fusion (DDF) is studied within the smoothing and mapping framework as well. Here, the robots share certain variables of choice, such as observed 3D points, to both extend sensing horizon and improve localization and mapping. Consistent information fusion is guaranteed by explicitly avoiding using the same observation more than once (i.e. double counting), via information down-dating that is expressed in graphical models by anti-factors. Information summarization techniques are developed to efficiently retrieve the probabilistic information to-be-shared from the local factorized joint probability distribution, represented by the Bayes net.

Related Publications:

Journal Articles

  1. V. Tchuiev and V. Indelman, “Distributed Consistent Multi-Robot Semantic Localization and Mapping,” IEEE Robotics and Automation Letters (RA-L), no. 3, Jul. 2020.
    Tchuiev20ral.pdf DOI: 10.1109/LRA.2020.3003275 Tchuiev20ral.supplementary Tchuiev20ral.video
  2. 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, no. 2, 2016.
    Indelman16csm.pdf URL: http://ieeexplore.ieee.org/xpl/abstractAuthors.jsp?reload=true&arnumber=7434165
  3. V. Indelman, P. Gurfil, E. Rivlin, and H. Rotstein, “Graph-Based Distributed Cooperative Navigation for a General Multi-Robot Measurement Model,” International Journal of Robotics Research (IJRR), no. 9, Aug. 2012.
    Indelman12ijrr.pdf URL: http://ijr.sagepub.com/content/31/9/1057
  4. V. Indelman, P. Gurfil, E. Rivlin, and H. Rotstein, “Distributed Vision-Aided Cooperative Localization and Navigation Based on Three-View Geometry,” Robotics and Autonomous Systems, no. 6, Jun. 2012.
    Indelman12ras.pdf URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5747546&tag=1

Conference Articles

  1. V. Indelman, “Distributed Perception and Estimation: a Short Survey,” in Principles of Multi-Robot Systems, workshop in conjunction with Robotics Science and Systems (RSS) Conference, Jul. 2015.
    Indelman15rss_ws_c.pdf Indelman15rss_ws_c.slides
  2. 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, Mar. 2015.
    Indelman15iacas_c.pdf Indelman15iacas_c.slides
  3. A. Cunningham, V. Indelman, and F. Dellaert, “DDF-SAM 2.0: Consistent Distributed Smoothing and Mapping,” in IEEE International Conference on Robotics and Automation (ICRA), May 2013.
    Cunningham13icra.pdf Cunningham13icra.slides
  4. A. Cunningham, K. Ok, J. Antico, V. Indelman, and F. Dellaert, “Aerial Robot Experimental Design for Decentralized Visual SLAM,” in Unmanned Systems Technology XV - SPIE Defense, Security and Sensing, Apr. 2013.
  5. A. Cunningham, V. Indelman, and F. Dellaert, “Consistent Decentralized Graphical SLAM with Anti-Factor Down-Dating,” in 10th IEEE International Symposium on Safety Security and Rescue Robotics (SSRR), Nov. 2012.
    Cunningham12ssrr.pdf
  6. V. Indelman, P. Gurfil, E. Rivlin, and H. Rotstein, “Graph-Based Cooperative Navigation Using Three-View Constraints: Method Validation,” in IEEE/ION Position Location and Navigation System (PLANS) Conference, Apr. 2012.
    Indelman12plans_b.pdf
  7. V. Indelman, P. Gurfil, E. Rivlin, and H. Rotstein, “Distributed Vision-Aided Cooperative Localization and Navigation based on Three-View Geometry,” in IEEE Aerospace Conference, Mar. 2011.
    Indelman11aerospace.pdf Indelman11aerospace.slides
  8. V. Indelman, P. Gurfil, E. Rivlin, and H. Rotstein, “Graph-based Distributed Cooperative Navigation,” in IEEE International Conference on Robotics and Automation (ICRA), May 2011.
    Indelman11icra.pdf Indelman11icra.slides

Theses

  1. V. Indelman, “Navigation Performance Enhancement Using Online Mosaicking,” PhD thesis, Technion - Israel Institute of Technology, 2011.
    Indelman11thesis.pdf Indelman11thesis.slides