Skip to main content
SpringerLink
Log in

Topological navigation graph framework

  • Published:
Autonomous Robots Aims and scope Submit manuscript

Abstract

In this paper, we focus on the utilisation of reactive trajectory imitation controllers for goal-directed visual navigation in mobile robotics. We propose topological navigation graph (TNG) framework. TNG is an imitation-learning-based topological navigation framework for navigating through environments with intersecting trajectories. It represents the environment as a directed graph composed of perception and action modules. Each vertex of the graph corresponds to a trajectory and is represented by a trajectory identification classifier and a trajectory imitation controller. The edges of TNG correspond to intersections between trajectories and are represented by trajectory intersection recognition classifiers. Having a visually specified goal state, TNG navigates by forming a sequential composition plan of trajectory imitation controllers. We also propose to apply neural object detection architectures for the task of trajectory following by detecting direction of movement. We provide empirical evaluation of the proposed navigation framework and its components both in simulated and real-world environments and demonstrate that TNG allows us to utilise non-goal-directed, imitation-learning methods for goal-directed autonomous navigation.

Graphic abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Notes

  1. https://software.intel.com/en-us/movidius-ncs.

  2. http://gazebosim.org.

References

  • Aström, K. J., & Murray, R. M. (2010). Feedback systems: An introduction for scientists and engineers. Princeton: Princeton University Press.

    Google Scholar 

  • Bansal, M., Krizhevsky, A., & Ogale, A. S. (2018). Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst. arXiv:1812.03079.

  • Bewley, A., Rigley, J., Liu, Y., Hawke, J., Shen, R., Lam, V.-D., et al. (2019). Learning to drive from simulation without real world labels. In ICRA.

  • Bojarski, M., Testa, D. D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., et al. (2016). End to end learning for self-driving cars. In CoRR. arXiv:1604.07316.

  • Bruce, J., Sünderhauf, N., Mirowski, P. W., Hadsell, R., & Milford, M. (2018). Learning deployable navigation policies at kilometer scale from a single traversal. In CoRL (pp. 346–361).

  • Burridge, R. R., Rizzi, A. A., & Koditschek, D. E. (1999). Sequential composition of dynamically dexterous robot behaviors. The International Journal of Robotics Research, 18(6), 534–555.

    Article  Google Scholar 

  • Calero, C. I., Shalom, D. E., Spelke, E. S., & Sigman, M. (2019). Language, gesture, and judgment: Children’s paths to abstract geometry. Journal of Experimental Child Psychology, 177, 70–85.

    Article  Google Scholar 

  • Calonder, M., Lepetit, V., Strecha, C., & Fua, P. (2010). Brief: Binary robust independent elementary features. In Computer vision ECCV (pp. 778–792). Springer.

  • Codevilla, F., López, A., Koltun, V., & Dosovitskiy, A. (2018a). On offline evaluation of vision-based driving models. In ECCV (Vol. 15, pp. 246–262).

  • Codevilla, F., Miiller, M., López, A., Koltun, V., & Dosovitskiy, A. (2018b). End-to-end driving via conditional imitation learning. In ICRA (pp. 1–9). IEEE.

  • Conner, D. C. (2008). Integrating planning and control for constrained dynamical systems. PhD thesis, Carnegie Mellon University, Pittsburgh, PA.

  • Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE Computer Society conference on computer vision and pattern recognition (pp. 248–255). IEEE.

  • Engel, J., & Cremers, D. (2014). Lsd-slam: Large-scale direct monocular slam. In ECCV (pp. 834–849).

  • Fraundorfer, F., Engels, C., & Nistér, D. (2007). Topological mapping, localization and navigation using image collections. In IROS (pp. 3872–3877).

  • Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning, volume 1. Springer series in statistics. New York.

  • Gaussier, P., & Zrehen, S. (1995). Perac: A neural architecture to control artificial animals. Robotics and Autonomous Systems, 16, 291–320.

    Article  Google Scholar 

  • Gershman, S. J., Horvitz, E. J., & Tenenbaum, J. B. (2015). Computational rationality: A converging paradigm for intelligence in brains, minds, and machines. Science, 349(6245), 273–278.

    Article  MathSciNet  Google Scholar 

  • Glasmachers, T. (2017). Limits of end-to-end learning. In JMLR (Vol. 77, pp. 17–32).

  • Gupta, S., Davidson, J., Levine, S., Sukthankar, R., & Malik, J. (2017). Cognitive mapping and planning for visual navigation. In Proceedings of the IEEE Computer Society conference on computer vision and pattern recognition (pp. 7272–7281).

  • He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Computer Society conference on computer vision and pattern recognition (pp. 770–778).

  • Ho, J., & Ermon, S. (2016). Generative adversarial imitation learning. In CoRR. arXiv:1606.03476.

  • Hussein, A., Elyan, E., Gaber, M. M., & Jayne, C. (2018). Deep imitation learning for 3d navigation tasks. Neural Computing and Applications, 29(7), 389–404.

    Article  Google Scholar 

  • Ikeda, T., Fukaya, M., & Mita, T. (2001). Position and attitude control of an underwater vehicle using variable constraint control. In Proceedings of the 40th IEEE conference on decision and control (Cat. No.01CH37228) (Vol. 4, pp. 3758–3763).

  • Kallem, V., Komoroski, A. T., & Kumar, V. (2011). Sequential composition for navigating a nonholonomic cart in the presence of obstacles. IEEE Transactions on Robotics, 27(6), 1152–1159.

    Article  Google Scholar 

  • Kantor, G., & Rizzi, A. A. (2005). Feedback control of underactuated systems via sequential composition: Visually guided control of a unicycle. In Robotics research. The eleventh international symposium (pp. 281–290). Springer.

  • Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. In ICLR.

  • Kuefler, A., Morton, J., Wheeler, T., & Kochenderfer, M. (2017). Imitating driver behavior with generative adversarial networks. In IV (pp. 204–211).

  • Labbé, M. (2011). Find-object. Retrieved from January 24, 2021, http://introlab.github.io/find-object.

  • LaValle, S. M. (2006). Planning algorithms. New York: Cambridge University Press.

    Book  Google Scholar 

  • Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et al. (2014). Microsoft coco: Common objects in context. In Computer vision ECCV (pp. 740–755). Springer.

  • Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., et al. (2016). Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21–37). Springer.

  • Milford, M. J., & Wyeth, G. F. (2008). Mapping a suburb with a single camera using a biologically inspired slam system. IEEE Transactions on Robotics, 24(5), 1038–1053.

    Article  Google Scholar 

  • Mirowski, P., Grimes, M. K., Malinowski, M., Hermann, K. M., Anderson, K., Teplyashin, D., et al. (2018). Learning to navigate in cities without a map. In Proceedings of the 32nd international conference on neural information processing systems, NIPS’18 (pp. 2424–2435). Red Hook, NY: Curran Associates Inc.

  • Mur-Artal, R., Montiel, J., & Tardos, J. (2015). Orb-slam: A versatile and accurate monocular slam system. IEEE Transactions on Robotics, 31, 1147–1163.

    Article  Google Scholar 

  • Murphy, K. P. (2013). Machine learning: A probabilistic perspective. Cambridge: MIT Press.

    MATH  Google Scholar 

  • Neurotechnology. (2018a). SentiBotics mobile robot prototype specification. Retrieved from January 24, 2021, https://download.neurotechnology.com/SentiBotics_Platform_Hardware_Specifications.pdf.

  • Neurotechnology. (2018b). SentiBotics navigation SDK 3.0. Retrieved from Accessed January 24, 2021, https://www.neurotechnology.com/sentibotics-navigation.html.

  • Osa, T., Pajarinen, J., Neumann, G., Bagnell, J., Abbeel, P., & Peters, J. (2018). An algorithmic perspective on imitation learning. Foundations and Trends in Robotics, 7(1–2), 1–179.

    Article  Google Scholar 

  • Özcan, M., & Ankarali, M. M. (2019). Feedback motion planning for a dynamic car model via random sequential composition. In 2019 IEEE international conference on systems, man and cybernetics (SMC) (pp. 4239–4244). IEEE.

  • Pathak, D., Mahmoudieh, P., Luo, G., Agrawal, P., Chen, D., Shentu, Y., et al. (2018). Zero-shot visual imitation. In ICLR.

  • Pomerleau, D. (1988). Alvinn: An autonomous land vehicle in a neural network. In NIPS.

  • Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., Leibs, J., et al. (2009). Ros: An open-source robot operating system. In ICRA workshop on open source software (Vol. 3, p. 5). Kobe, Japan.

  • Ross, S., Gordon, G. J., & Andrew-Bagnell, J. (2010). A reduction of imitation learning and structured prediction to no-regret online learning. Journal of Machine Learning Research, 15, 627–635.

    Google Scholar 

  • Rosten, E., & Drummond, T. (2006). Machine learning for high-speed corner detection. In Computer vision ECCV (pp. 430–443). Berlin, Heidelberg: Springer.

  • Ruder, S. (2016). An overview of gradient descent optimization algorithms.

  • Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Computer Society conference on computer vision and pattern recognition (pp. 4510–4520).

  • Sartoretti, G., Kerr, J., Shi, Y., Wagner, G., Kumar, T., Koenig, S., et al. (2019). Primal: Pathfinding via reinforcement and imitation multi-agent learning. IEEE Robotics and Automation Letters, 4(3), 2378–2385.

    Article  Google Scholar 

  • Savinov, N., Dosovitskiy, A., & Koltun, V. (2018). Semi-parametric topological memory for navigation. In ICLR.

  • Thrun, S. (1998). Learning metric-topological maps for indoor mobile robot navigation. Artificial Intelligence, 99, 21–71.

    Article  Google Scholar 

  • Wang, D., Devin, C., Cai, Q.-Z., Yu, F., & Darrell, T. (2018). Deep object centric policies for autonomous driving. In CoRR. arXiv:1811.05432.

Download references

Acknowledgements

We are grateful to Neurotechnology for providing resources and support for this research. We also thank anonymous reviewers for useful remarks and suggestions.

Funding

This research was funded by Neurotechnology.

Author information

Authors and Affiliations

  1. Neurotechnology, Vilnius, Lithuania

    Povilas Daniušis, Shubham Juneja, Lukas Valatka & Linas Petkevičius

Authors
  1. Povilas Daniušis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shubham Juneja
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lukas Valatka
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Linas Petkevičius
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Povilas Daniušis.

Ethics declarations

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary material 1 (avi 54016 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Daniušis, P., Juneja, S., Valatka, L. et al. Topological navigation graph framework. Auton Robot 45, 633–646 (2021). https://doi.org/10.1007/s10514-021-09980-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10514-021-09980-x

Keywords

Search

Navigation