Abstract
Simultaneous Localization and Mapping (SLAM) with fixed landmark objects creates topological maps by extracting semantic information from the environment. In this paper, we propose a new method for mapping, Neural Object SLAM (NeoSLAM), which uses objects seen in stereo images to learn associations between the pose of the robot and the observed landmark objects. We perform mapping with a biologically inspired approach based on creating patterns memorizing places in a network of grid cells and head direction cells. Our model is inspired by the object vector cells discovered recently by neuroscientists exploring the navigation of mammals. We model the firing field of these cells with a feed-forward neural network and create keyframes of objects with their 3D pose in a world-centered frame of reference. We train a Hebbian network connecting keyframe templates to the grid cells to memorize familiar places. We use the NeuroSLAM algorithm to train the grid cells and the head direction cells with the 4 Degree of Freedom (DoF) poses of the robot. Then, we detect loops in the trajectory by matching objects in the keyframes. Finally, we create an object experience map and correct the cumulative error if we detect loop closure candidates. Thus, our system performs object-based place recognition with a brain-inspired approach and produces 2D/3D object topological maps.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ambruş, R., Bore, N., Folkesson, J., Jensfelt, P.: Meta-rooms: building and maintaining long term spatial models in a dynamic world. In: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1854–1861 (2014). https://doi.org/10.1109/IROS.2014.6942806
Ball, D., Heath, S., Wiles, J., Wyeth, G., Corke, P., Milford, M.: OpenRatSLAM: an open source brain-based SLAM system. Auton. Robot. 34, 149–176 (2013)
Banino, A., Barry, C.: Vector-based navigation using grid-like representations in artificial agents. Nature 557, 429–433 (2018)
Doherty, K., Baxter, D., Schneeweiss, E., Leonard, J.: Probabilistic data association via mixture models for robust semantic SLAM. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 1098–1104 (2020)
Finman, R., Paull, L., Leonard, J.: Toward object-based place recognition in dense RGB-D maps (2015)
Fritsch, J., Kuehnl, T., Geiger, A.: A new performance measure and evaluation benchmark for road detection algorithms. In: International Conference on Intelligent Transportation Systems (ITSC) (2013)
Geiger, A., Ziegler, J., Stiller, C.: StereoScan: dense 3D reconstruction in real-time. In: Intelligent Vehicles Symposium (IV) (2011)
Høydal, Ø.A., Skytøen, E., Andersson, S., Moser, M.B., Moser, E.: Object-vector coding in the medial entorhinal cortex. Nature 568, 1–8 (2019). https://doi.org/10.1038/s41586-019-1077-7
Kiggundu, A., Weber, C., Wermter, S.: A compressing auto-encoder as a developmental model of grid cells. In: Human Brain Project HBP Student Conference, Austria, pp. 35–37 (2017)
Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: Tenth IEEE International Conference on Computer Vision (ICCV 2005), vol. 2, 1482–1489 (2005)
Liu, Z., Amini, A., Zhu, S., Karaman, S., Han, S., Rus, D.: Efficient and robust lidar-based end-to-end navigation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13247–13254 (2021)
Müller, S., Weber, C., Wermter, S.: RatSLAM on humanoids - a bio-inspired SLAM model adapted to a humanoid robot. In: Wermter, S., et al. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 789–796. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11179-7_99
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. ArXiv arXiv:1804.02767 (2018)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.R.: ORB: an efficient alternative to SIFT or SURF. In: 2011 International Conference on Computer Vision, pp. 2564–2571 (2011)
Yu, F., Shang, J., Hu, Y., Milford, M.: NeuroSLAM: a brain-inspired SLAM system for 3d environments. Biol. Cybern. 113(5–6), 515–545 (2019). https://doi.org/10.1007/s00422-019-00806-9, https://eprints.qut.edu.au/198104/
Zhou, X., Weber, C., Wermter, S.: A self-organizing method for robot navigation based on learned place and head-direction cells. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Raoui, Y., Weber, C., Wermter, S. (2022). NeoSLAM: Neural Object SLAM for Loop Closure and Navigation. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13531. Springer, Cham. https://doi.org/10.1007/978-3-031-15934-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-15934-3_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15933-6
Online ISBN: 978-3-031-15934-3
eBook Packages: Computer ScienceComputer Science (R0)