Abstract
We introduce an approach to building a custom model from ready-made self-supervised models via their associating instead of training and fine-tuning. We demonstrate it with an example of a humanoid robot looking at the mirror and learning to detect the 3D pose of its own body from the image it perceives. To build our model, we first obtain features from the visual input and the postures of the robot’s body via models prepared before the robot’s operation. Then we map their corresponding latent spaces by a sample-efficient robot’s self-exploration at the mirror. In this way, the robot builds the solicited 3D pose detector, which quality is immediately perfect on the acquired samples instead of obtaining the quality gradually. The mapping, which employs associating the pairs of feature vectors, is then implemented in the same way as the key–value mechanism of the famous transformer models. Finally, deploying our model for imitation to a simulated robot allows us to study, tune up and systematically evaluate its hyperparameters without the involvement of the human counterpart, advancing our previous research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
see the video at https://youtu.be/-3BVbU9BeRE.
- 2.
see the video at https://youtu.be/_CBnCOnWRdY.
- 3.
see the video at https://youtu.be/ZNkF5BTKOLU.
- 4.
see the video at https://youtu.be/G6xWAKDMpsM.
References
Bahl, S., Gupta, A., Pathak, D.: Human-to-robot imitation in the wild. arXiv preprint arXiv:2207.09450 (2022)
Bandera, J.P., Rodriguez, J.A., Molina-Tanco, L., Bandera, A.: A survey of vision-based architectures for robot learning by imitation. Int. J. Humanoid Robot. 9, 1250006 (2012). world Scientific Publishing Company https://doi.org/10.1142/S0219843612500065
Boucenna, S., Anzalone, S., Tilmont, E., Cohen, D., Chetouani, M.: Learning of social signatures through imitation game between a robot and a human partner. IEEE Trans. Auton. Mental Dev. 6(3), 213–225 (2014). https://doi.org/10.1109/TAMD.2014.2319861
Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the International Conference on Computer Vision, ICCV (2021)
Dai, T., Liu, H., Anthony Bharath, A.: Episodic self-imitation learning with hindsight. Electronics 9(10) (2020). https://doi.org/10.3390/electronics9101742
Dennett, D.C.: Kinds of Minds: Towards an Understanding of Consciousness. Weidenfeld & Nicolson, London (1996)
Garello, L., Rea, F., Noceti, N., Sciutti, A.: Towards third-person visual imitation learning using generative adversarial networks. In: IEEE International Conference on Development and Learning (ICDL), pp. 121–126 (2022)
Goodfellow, I.: Generative adversarial networks. Neural Inf. Process. Syst. (2016)
Heyes, C.: Where do mirror neurons come from? Neurosci. Biobehav. Rev. 34(4), 575–83 (2010)
Kingma, D.P., Welling, M.: An introduction to variational autoencoders. Found. Trends Mach. Learn. 12(4), 307–392 (2019)
Lúčny, A.: Building complex systems with agent-space architecture. Comput. Inf. 23(1), 1–36 (2004)
Lúčny, A.: iCubSim at the mirror. In: Proceedings of EUCognition. Vienna (2016)
Lúčny, A.: Towards one-shot learning via attention. In: CEUR Workshop Proceedings, ITAT 2022, pp. 4–11. 3226 (2022)
Marcel, V., OâĂŹRegan, J.K., Hoffmann, M.: Learning to reach to own body from spontaneous self-touch using a generative model. In: IEEE International Conference on Development and Learning (ICDL), pp. 328–335 (2022)
Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: International Conference on Computer Vision, ICCV (2021)
Pospíchal, J., Farkaš, I., Pecháč, M., Malinovská, K.: Modeling self-organized emergence of perspective in/variant mirror neurons in a robotic system. In: Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), pp. 278–283 (2019)
Rebrová K., Pecháč M., Farkaš I.: Towards a robotic model of the mirror neuron system. In: International Conference on Development and Learning and on Epigenetic Robotics, IEEE (2013)
Seker, M.Y., Ahmetoglu, A., Nagai, Y., Asada, M., Oztop, E., Ugur, E.: Imitation and mirror systems in robots through deep modality blending networks. Neural Netw. 146, 22–35 (2022). https://doi.org/10.1016/j.neunet.2021.11.004
Sermanet, P., et al.: Time-contrastive networks: Self-supervised learning from video. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 1134–1141 (2018)
Tessitore, G., Prevete, R., Catanzariti, E., Tamburrini, G.: From motor to sensory processing in mirror neuron computational modelling. Biol. Cybern. 103(6), 471–485 (2010)
Vaswani, A., et al.: Attention is all you need. In: 31st International Conference on Neural Information Processing Systems, ACM (2017)
Vernon, D., Metta, G., Sandini, G.: The iCub cognitive architecture: Interactive development in a humanoid robot. In: IEEE 6th International Conference on Development and Learning, pp. 122–127 (2007)
Šejnová, G., Štěpánová, K.: Feedback-driven incremental imitation learning using sequential VAE. In: IEEE International Conference on Development and Learning (ICDL), pp. 238–243 (2022)
Zahra, O., Tolu, S., Zhou, P., Duan, A., Navarro-Alarcon, D.: A bio-inspired mechanism for learning robot motion from mirrored human demonstrations. Frontiers Neurorobot. 16 (2022). https://doi.org/10.3389/fnbot.2022.826410
Zambelli, M., Cully, A., Demiris, Y.: Multimodal representation models for prediction and control from partial information. Robot. Autonom. Syst. 123, 103312 (2020)
Acknowledgements
This work was supported by the EU-funded project TERAIS, no. 101079338, and partly by the national VEGA 1/0373/23 project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lúčny, A., Malinovská, K., Farkaš, I. (2023). Robot at the Mirror: Learning to Imitate via Associating Self-supervised Models. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14254. Springer, Cham. https://doi.org/10.1007/978-3-031-44207-0_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-44207-0_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44206-3
Online ISBN: 978-3-031-44207-0
eBook Packages: Computer ScienceComputer Science (R0)