An Embodied Approach for Evolving Robust Visual Classifiers

ABSTRACT

Despite recent demonstrations that deep learning methods can successfully recognize and categorize objects using high dimensional visual input, other recent work has shown that these methods can fail when presented with novel input. However, a robot that is free to interact with objects should be able to reduce spurious differences between objects belonging to the same class through motion and thus reduce the likelihood of overfitting. Here we demonstrate a robot that achieves more robust categorization when it evolves to use proprioceptive sensors and is then trained to rely increasingly on vision, compared to a similar robot that is trained to categorize only with visual sensors. This work thus suggests that embodied methods may help scaffold the eventual achievement of robust visual classification.

References

1. R. D. Beer. The dynamics of active categorical perception in an evolved model agent. Adaptive Behavior, 11(4):209--243, 2003.
2. Y. Bengio. Learning deep architectures for AI. Foundations and Trends® in Machine Learning, 2(1):1--127, 2009.
3. J. Bongard. The utility of evolving simulated robot morphology increases with task complexity for object manipulation. Artificial Life, 16(3):201--223, 2010.
4. J. Bongard. Morphological and environmental scaffolding synergize when evolving robot controllers: artificial life/robotics/evolvable hardware. In Proceedings of the 13th annual conference on Genetic and Evolutionary Computation, pages 179--186. ACM, 2011.
5. J. Bongard. Morphological change in machines accelerates the evolution of robust behavior. Proceedings of the National Academy of Sciences, 108(4):1234--1239, 2011.
6. J. C. Bongard. Evolutionary robotics. Communications of the ACM, 56(8):74--83, 2013.
7. E. Coumans et al. Bullet Physics Library, version 2.82. http://bulletphysics.org, 2014.
8. M. Dorigo and M. Colombetti. Robot Shaping: Developing Autonomous Agents Through Learning. Artificial Intelligence, 71(2):321--370, 1994.
9. M. H. Fischer and R. A. Zwaan. Embodied language: A review of the role of the motor system in language comprehension. The Quarterly Journal of Experimental Psychology, 61(6):825--850, 2008.
10. P. Fitzpatrick, G. Metta, L. Natale, S. Rao, and G. Sandini. Learning about objects through action: initial steps towards artificial cognition. In IEEE Intl Conf on Robotics and Automation, volume 3, pages 3140--3145. IEEE, 2003.
11. N. Hansen. Cma evolution strategy, 1.1.05. https://www.lri.fr/ hansen/cmaes\_inmatlab.html, 2014.
12. S. Harnad. To cognize is to categorize: Cognition is Categorization. Handbook of Categorization in Cognitive Science, pages 20--45, 2005.
13. G. E. Hinton. Learning multiple layers of representation. Trends in Cognitive Sciences, 11(10):428--434, 2007.
14. G. Lakoff and R. E. Núñez. Where mathematics comes from: How the embodied mind brings mathematics into being. Basic Books, 2000.
15. M. Lungarella, G. Metta, R. Pfeifer, and G. Sandini. Developmental robotics: a survey. Connection Science, 15(4):151--190, 2003.
16. A. Nguyen, J. Yosinski, and J. Clune. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. IEEE CVPR, 2015.
17. S. Perkins and G. Hayes. Robot shaping: Principles, methods and architectures. 1996.
18. J. Plumert and P. Nichols-Whitehead. Parental scaffolding of young children. Developmental Psychology, 32(3):523--32, 1996.
19. L. M. Saksida, S. M. Raymond, and D. S. Touretzky. Shaping robot behavior using principles from instrumental conditioning. Robotics and Autonomous Systems, 22(3):231--249, 1997.
20. C. Scheier and R. Pfeifer. Classification as sensory-motor coordination. In Advances in Artificial Life, pages 657--667. Springer, 1995.
21. C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. Intriguing properties of neural networks. International Conference on Learning Representations, 2014.
22. E. Tuci, G. Massera, and S. Nolfi. Active categorical perception of object shapes in a simulated anthropomorphic robotic arm. IEEE Transactions on Evolutionary Computation, 14(6):885--899, 2010.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Control methods

    • Search methodologies

• Theory of computation

  • Design and analysis of algorithms

    • Algorithm design techniques

      • Dynamic programming