learning on humanoid robots
play

Learning on Humanoid Robots Vadym Gryshchuk 19.11.2018 Outline - PowerPoint PPT Presentation

Neural Architectures for Lif ifelong Learning on Humanoid Robots Vadym Gryshchuk 19.11.2018 Outline Motivation Background Approaches Results Discussion Conclusion Neural Architectures for Lifelong Learning on Humanoid


  1. Neural Architectures for Lif ifelong Learning on Humanoid Robots Vadym Gryshchuk 19.11.2018

  2. Outline • Motivation • Background • Approaches • Results • Discussion • Conclusion Neural Architectures for Lifelong Learning on Humanoid Robots 2

  3. • Motivation • Background • Approaches • Results • Discussion • Conclusion Neural Architectures for Lifelong Learning on Humanoid Robots 3

  4. What is is Lif ifelong Learning? • Continual acquisition of knowledge • Fine-tuning of knowledge • Learning from experiences • Retaining of previously learnt experiences Figure 1.1: NICO – Neuro-Inspired COmpanion (Source: Kerzel et al. [2]). Neural Architectures for Lifelong Learning on Humanoid Robots 4

  5. Catastrophic Forgetting • Interference of learnt representations with new information Representation 2 Representation 1 Neural Architectures for Lifelong Learning on Humanoid Robots 5

  6. In Inspiration from Biological Systems • Neurosynaptic plasticity • Hippocampus and cerebral cortex • Transfer learning • Intrinsic motivation • Crossmodal learning • Incremental learning Neural Architectures for Lifelong Learning on Humanoid Robots 6

  7. • Motivation • Background • Approaches • Results • Discussion • Conclusion Neural Architectures for Lifelong Learning on Humanoid Robots 7

  8. Neural Networks Figure 2.1: Neural network representation (Source: McDonald [3]). Neural Architectures for Lifelong Learning on Humanoid Robots 8

  9. Convolutional Neural l Networks (C (CNNs) Figure 2.2: Convolutional neural network (Source: Cavaioni [1]) Neural Architectures for Lifelong Learning on Humanoid Robots 9

  10. Self lf-Organizing Networks • Self-Organizing Map (SOM) • Grow When Required Network (GWR Network) • Recurrent GWR Neural Architectures for Lifelong Learning on Humanoid Robots 10

  11. • Motivation • Background • Approaches • Results • Discussion • Conclusion Neural Architectures for Lifelong Learning on Humanoid Robots 11

  12. Object Recognition: CNN + Cla lassifier • Learning from video sequences • Visual transformations of objects • Changing environment Figure 3.1: iCub (Source: Pasquale et al. [6]). Neural Architectures for Lifelong Learning on Humanoid Robots 12

  13. Object Recognition: CNN + Classifier apple ball CNN tomato cup Classifier Neural Architectures for Lifelong Learning on Humanoid Robots 13

  14. iC iCub: Object Learning Source: https://www.youtube.com/watch?v=ghUFweqm7W8 Neural Architectures for Lifelong Learning on Humanoid Robots 14

  15. iCub: Object Learning Source: https://www.youtube.com/watch?v=ghUFweqm7W8 Neural Architectures for Lifelong Learning on Humanoid Robots 15

  16. iCub: Object Learning Source: https://www.youtube.com/watch?v=ghUFweqm7W8 Neural Architectures for Lifelong Learning on Humanoid Robots 16

  17. iCub: Object Learning Source: https://www.youtube.com/watch?v=ghUFweqm7W8 Neural Architectures for Lifelong Learning on Humanoid Robots 17

  18. iCub: Object Learning Source: https://www.youtube.com/watch?v=ghUFweqm7W8 Neural Architectures for Lifelong Learning on Humanoid Robots 18

  19. iCub: Object Learning Source: https://www.youtube.com/watch?v=ghUFweqm7W8 Neural Architectures for Lifelong Learning on Humanoid Robots 19

  20. Sensorimotor Learning: Self lf-Organization • Latency in sensorimotor systems • Predictive mechanisms for future motor states • Online learning Source: https://upload.wikimedia.org/wikipedia/commons/ 4/47/Nao_Robot_%28Robocup_2016%29.jpg Neural Architectures for Lifelong Learning on Humanoid Robots 20

  21. Sensorimotor Learning: Self-Organization Figure 3.2: The imitation scenario (Source: Mici et al. [4]). Neural Architectures for Lifelong Learning on Humanoid Robots 21

  22. Sensorimotor Learning: Self-Organization Figure 3.3: Visuomotor learning (Source: Mici et al. [4]). Neural Architectures for Lifelong Learning on Humanoid Robots 22

  23. Object Recognition: CNN + Self-Organization Pre-trained CNN RGB sequence Features Self-organizing network Depth Pre-trained CNN sequence Label Figure 3.4: Recognition pipeline (Adapted from Part et al. [5]). Neural Architectures for Lifelong Learning on Humanoid Robots 23

  24. • Motivation • Background • Approaches • Results • Discussion • Conclusion Neural Architectures for Lifelong Learning on Humanoid Robots 24

  25. Object Recognition: CNN + Cla lassifier Figure 4.1: Classification accuracy of the model, which was trained on an incremental number of objects (Source: Pasquale et al. [6]). Neural Architectures for Lifelong Learning on Humanoid Robots 25

  26. Object Recognition: CNN + Cla lassifier Figure 4.2: Classification accuracy of the model trained incrementally on different days (Source: Pasquale et al. [6]). Neural Architectures for Lifelong Learning on Humanoid Robots 26

  27. Sensorimotor Learning: : Self-Organizing Architecture Figure 4.3: Behaviour of the architecture (Source: Mici et al. [4]). Neural Architectures for Lifelong Learning on Humanoid Robots 27

  28. Object Recognition: CNN + Self-Organization Figure 4.4: Recognition pipeline (Source: Part et al. [5]). Neural Architectures for Lifelong Learning on Humanoid Robots 28

  29. Dis iscussion • CNN + Classifier architecture for object recognition: • Features extracted from a CNN are dependent on a dataset the model was trained on • Old representations are overwritten by the new information • Self-organizing architecture for sensorimotor learning: • Incremental online learning and prediction • Unreliability of visual body tracking framework in complex body positions • CNN + self-organization for object recognition: • Self-organizing network grows when required • Temporal context is not considered Neural Architectures for Lifelong Learning on Humanoid Robots 29

  30. Conclusion • Lifelong learning is crucial for intelligent robots • Biological systems provide a basis for the incremental learning • Self-organizing networks preserve the topology • CNNs learn efficient feature descriptors • Catastrophic forgetting increases during incremental tasks Neural Architectures for Lifelong Learning on Humanoid Robots 30

  31. Thank You! Questions? Neural Architectures for Lifelong Learning on Humanoid Robots 31

  32. References • [1] Cavaioni, M. Deep Learning series: Convolutional Neural Networks. https://medium.com/machine- learning- bites/deeplearning-series-convolutional-neural-networks-a9c2f2ee1524 . [Online; accessed 13-November-2018]. • [2] Kerzel, M., Strahl, E., Magg, S., Navarro-Guerrero, N., Heinrich, S., Wermter, S.NICO - neuro-inspired companion: A developmental humanoid robot platform for multimodal interaction. In26th IEEE International Symposium on Robot and Human Interactive Communication, ROMAN 2017, Lisbon, Portugal, August 28 - Sept. 1, 2017, pages 113 – 120, 2017. • [3] McDonald, C. Machine learning fundamentals (II): Neural networks. https://towardsdatascience.com/machine- learning-fundamentals-ii-neural-networks-f1e7b2cb3eef. [Online; accessed 13-November-2018]. • [4] Mici, L., Parisi, I. G., Wermter, S. An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction. CoRR, abs/1712.08521, 2017. • [5] Part l. J., Lemon, O. Incremental online learning of objects for robots operating in real environments. In Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2017, Lisbon, Portugal, September 18-21, 2017, pages 304 – 310, 2017. • [6] Pasquale, G., Ciliberto, C., Odone, F., Rosasco, L., Natale, L. Real-world object recognition with off-the-shelf deep conv nets: How many objects can iCub learn? CoRR, abs/1504.03154, 2015. Neural Architectures for Lifelong Learning on Humanoid Robots 32

Recommend


More recommend