The Data Market: Policies for Decentralised Visual Localisation

01/17/2018 ∙ by Matthew Gadd, et al. ∙ University of Oxford 0

This paper presents a mercantile framework for the decentralised sharing of navigation expertise amongst a fleet of robots which perform regular missions into a common but variable environment. We build on our earlier work and allow individual agents to intermittently initiate trades based on a real-time assessment of the nature of their missions or demand for localisation capability, and to choose trading partners with discrimination based on an internally evolving set of beliefs in the expected value of trading with each other member of the team. To this end, we suggest some obligatory properties that a formalisation of the distributed versioning of experience maps should exhibit, to ensure the eventual convergence in the state of each agent's map under a sequence of pairwise exchanges, as well as the uninterrupted integrity of the representation under versioning operations. To mitigate limitations in hardware and network resources, the "data market" is catalogued by distinct sections of the world, which the agents treat as "products" for appraisal and purchase. To this end, we demonstrate and evaluate our system using the publicly available Oxford RobotCar Dataset, the hand-labelled data market catalogue (approaching 446km of fully indexed sections-of-interest) for which we plan to release alongside the existing raw stereo imagery. We show that, by refining market policies over time, agents achieve improved localisation in a directed and accelerated manner.



There are no comments yet.


page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.


  • [1] M. Gadd and P. Newman, “Checkout my map: Version control for fleetwide visual localisation,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, South Korea, October 2016.
  • [2] W. Maddern, G. Pascoe, C. Linegar, and P. Newman, “1 Year, 1000km: The Oxford RobotCar Dataset,” The International Journal of Robotics Research (IJRR), vol. 36, no. 1, pp. 3–15, 2017. [Online]. Available:
  • [3] M. J. Milford and G. F. Wyeth, “Seqslam: Visual route-based navigation for sunny summer days and stormy winter nights,” in Robotics and Automation (ICRA), 2012 IEEE International Conference on.   IEEE, 2012, pp. 1643–1649.
  • [4] T. Naseer, L. Spinello, W. Burgard, and C. Stachniss, “Robust visual robot localization across seasons using network flows.” in AAAI, 2014, pp. 2564–2570.
  • [5] M. Dymczyk, S. Lynen, T. Cieslewski, M. Bosse, R. Siegwart, and P. Furgale, “The gist of maps-summarizing experience for lifelong localization,” in Robotics and Automation (ICRA), 2015 IEEE International Conference on.   IEEE, 2015, pp. 2767–2773.
  • [6] C. Linegar, W. Churchill, and P. Newman, “Work smart, not hard: Recalling relevant experiences for vast-scale but time-constrained localisation,” in Robotics and Automation (ICRA), 2015 IEEE International Conference on.   IEEE, 2015, pp. 90–97.
  • [7] M. Milford and G. Wyeth, “Persistent navigation and mapping using a biologically inspired slam system,” The International Journal of Robotics Research, vol. 29, no. 9, pp. 1131–1153, 2010.
  • [8] L. Riazuelo, J. Civera, and J. Montiel, “C 2 tam: A cloud framework for cooperative tracking and mapping,” Robotics and Autonomous Systems, vol. 62, no. 4, pp. 401–413, 2014.
  • [9] C. Forster, S. Lynen, L. Kneip, and D. Scaramuzza, “Collaborative monocular slam with multiple micro aerial vehicles,” in 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.   IEEE, 2013, pp. 3962–3970.
  • [10] L. C. Carrillo-Arce, E. D. Nerurkar, J. L. Gordillo, and S. I. Roumeliotis, “Decentralized multi-robot cooperative localization using covariance intersection,” in 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.   IEEE, 2013, pp. 1412–1417.
  • [11] D. Fox, W. Burgard, H. Kruppa, and S. Thrun, “A probabilistic approach to collaborative multi-robot localization,” Autonomous robots, vol. 8, no. 3, pp. 325–344, 2000.
  • [12] A. Cunningham, V. Indelman, and F. Dellaert, “Ddf-sam 2.0: Consistent distributed smoothing and mapping,” in Robotics and Automation (ICRA), 2013 IEEE International Conference on.   IEEE, 2013, pp. 5220–5227.
  • [13] T. Cieslewski, S. Lynen, M. Dymczyk, S. Magnenat, and R. Siegwart, “Map api-scalable decentralized map building for robots,” in 2015 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2015, pp. 6241–6247.
  • [14] W. Nagel, Subversion Version Control: Using the Subversion Version Control System in Development Projects.   Prentice Hall PTR, 2005.
  • [15] J. Loeliger and M. McCullough, Version Control with Git: Powerful tools and techniques for collaborative software development.   ” O’Reilly Media, Inc.”, 2012.
  • [16] V. Frias-Martinez, E. Sklar, and S. Parsons, “Exploring auction mechanisms for role assignment in teams of autonomous robots,” in Robot Soccer World Cup.   Springer, 2004, pp. 532–539.
  • [17] L. Wang, M. Liu, and M. Q.-H. Meng, “A pricing mechanism for task oriented resource allocation in cloud robotics,” in Robots and Sensor Clouds.   Springer, 2016, pp. 3–31.
  • [18] J. Dagit, “Type-correct changes — a safe approach to version control implementation,” Ph.D. dissertation, 2009.
  • [19] D. Roundy, “Darcs: distributed version management in haskell,” in Proceedings of the 2005 ACM SIGPLAN workshop on Haskell.   ACM, 2005, pp. 1–4.
  • [20] C. Linegar, W. Churchill, and P. Newman, “Work Smart, Not Hard: Recalling Relevant Experiences for Vast-Scale but Time-Constrained Localisation,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA, May 2015.
  • [21] M. Gadd and P. Newman, “A framework for infrastructure-free warehouse navigation,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA, May 2015.
  • [22] M. Cummins and P. Newman, “Appearance-only slam at large scale with fab-map 2.0,” The International Journal of Robotics Research, November 2010.
  • [23] C. P. Robert, Monte carlo methods.   Wiley Online Library, 2004.
  • [24] P. Auer, N. Cesa-Bianchi, Y. Freund, and R. E. Schapire, “The nonstochastic multiarmed bandit problem,” SIAM journal on computing, vol. 32, no. 1, pp. 48–77, 2002.
  • [25]

    J. Langford and T. Zhang, “The epoch-greedy algorithm for multi-armed bandits with side information,” in

    Advances in neural information processing systems, 2008, pp. 817–824.
  • [26] P. M. Newman, “Moos-mission orientated operating suite,” 2008.
  • [27] B. S. Bosik and M. Ü. Uyar, “Finite state machine based formal methods in protocol conformance testing: from theory to implementation,” Computer Networks and ISDN Systems, vol. 22, no. 1, pp. 7–33, 1991.
  • [28] S. R. Kosaraju, “Limitations of dijkstra’s semaphore primitives and petri nets,” ACM SIGOPS Operating Systems Review, vol. 7, no. 4, pp. 122–126, 1973.