Skip to main content

2018 | OriginalPaper | Buchkapitel

Interpretable Intuitive Physics Model

verfasst von : Tian Ye, Xiaolong Wang, James Davidson, Abhinav Gupta

Erschienen in: Computer Vision – ECCV 2018

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Humans have a remarkable ability to use physical commonsense and predict the effect of collisions. But do they understand the underlying factors? Can they predict if the underlying factors have changed? Interestingly, in most cases humans can predict the effects of similar collisions with different conditions such as changes in mass, friction, etc. It is postulated this is primarily because we learn to model physics with meaningful latent variables. This does not imply we can estimate the precise values of these meaningful variables (estimate exact values of mass or friction). Inspired by this observation, we propose an interpretable intuitive physics model where specific dimensions in the bottleneck layers correspond to different physical properties. In order to demonstrate that our system models these underlying physical properties, we train our model on collisions of different shapes (cube, cone, cylinder, spheres etc.) and test on collisions of unseen combinations of shapes. Furthermore, we demonstrate our model generalizes well even when similar scenes are simulated with different underlying properties.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Agrawal, P., Nair, A., Abbeel, P., Malik, J., Levine, S.: Learning to poke by poking: experiential learning of intuitive physics. In: Neural Information Processing Systems (NIPS) (2016) Agrawal, P., Nair, A., Abbeel, P., Malik, J., Levine, S.: Learning to poke by poking: experiential learning of intuitive physics. In: Neural Information Processing Systems (NIPS) (2016)
2.
Zurück zum Zitat Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Neural Information Processing Systems (NIPS) (2016) Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Neural Information Processing Systems (NIPS) (2016)
3.
Zurück zum Zitat Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Neural Information Processing Systems (NIPS) (2016) Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Neural Information Processing Systems (NIPS) (2016)
4.
Zurück zum Zitat Chang, M.B., Ullman, T., Torralba, A., Tenenbaum, J.B.: A compositional object-based approach to learning physical dynamics. In: International Conference on Learning Representations (ICLR) (2017) Chang, M.B., Ullman, T., Torralba, A., Tenenbaum, J.B.: A compositional object-based approach to learning physical dynamics. In: International Conference on Learning Representations (ICLR) (2017)
5.
Zurück zum Zitat Edmonds, M., et al.: Feeling the force: integrating force and pose for fluent discovery through imitation learning to open medicine bottles. In: Intelligent Robots and Systems (IROS) (2017) Edmonds, M., et al.: Feeling the force: integrating force and pose for fluent discovery through imitation learning to open medicine bottles. In: Intelligent Robots and Systems (IROS) (2017)
6.
Zurück zum Zitat Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Neural Information Processing Systems (NIPS) (2016) Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Neural Information Processing Systems (NIPS) (2016)
7.
Zurück zum Zitat Fragkiadaki, K., Agrawal, P., Levine, S., Malik, J.: Learning visual predictive models of physics for playing billiards. In: International Conference on Learning Representations (ICLR) (2016) Fragkiadaki, K., Agrawal, P., Levine, S., Malik, J.: Learning visual predictive models of physics for playing billiards. In: International Conference on Learning Representations (ICLR) (2016)
8.
Zurück zum Zitat Grzeszczuk, R., Terzopoulos, D., Hinton, G.: Neuroanimator: fast neural network emulation and control of physics-based models. In: Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, pp. 9–20. ACM (1998) Grzeszczuk, R., Terzopoulos, D., Hinton, G.: Neuroanimator: fast neural network emulation and control of physics-based models. In: Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, pp. 9–20. ACM (1998)
9.
Zurück zum Zitat Hamrick, J., Battaglia, P., Tenenbaum, J.B.: Internal physics models guide probabilistic judgments about object dynamics. In: Proceedings of the 33rd Annual Conference of the Cognitive Science Society (2011) Hamrick, J., Battaglia, P., Tenenbaum, J.B.: Internal physics models guide probabilistic judgments about object dynamics. In: Proceedings of the 33rd Annual Conference of the Cognitive Science Society (2011)
10.
Zurück zum Zitat Hamrick, J.B., Battaglia, P.W., Griffiths, T.L., Tenenbaum, J.B.: Inferring mass in complex scenes by mental simulation. Cognition (2016) Hamrick, J.B., Battaglia, P.W., Griffiths, T.L., Tenenbaum, J.B.: Inferring mass in complex scenes by mental simulation. Cognition (2016)
12.
Zurück zum Zitat Kulkarni, T.D., Whitney, W.F., Kohli, P., Tenenbaum, J.: Deep convolutional inverse graphics network. In: Neural Information Processing Systems (NIPS) (2015) Kulkarni, T.D., Whitney, W.F., Kohli, P., Tenenbaum, J.: Deep convolutional inverse graphics network. In: Neural Information Processing Systems (NIPS) (2015)
13.
Zurück zum Zitat Lerer, A., Gross, S., Fergus, R.: Learning physical intuition of block towers by example. In: International Conference on Machine Learning (ICML) (2016) Lerer, A., Gross, S., Fergus, R.: Learning physical intuition of block towers by example. In: International Conference on Machine Learning (ICML) (2016)
14.
Zurück zum Zitat Li, W., Azimi, S., Leonardis, A., Fritz, M.: To fall or not to fall: a visual approach to physical stability prediction. arXiv:1604.00066 (2016) Li, W., Azimi, S., Leonardis, A., Fritz, M.: To fall or not to fall: a visual approach to physical stability prediction. arXiv:​1604.​00066 (2016)
15.
Zurück zum Zitat Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: International Conference on Learning Representations (ICLR) (2016) Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: International Conference on Learning Representations (ICLR) (2016)
16.
Zurück zum Zitat Mottaghi, R., Bagherinezhad, H., Rastegari, M., Farhadi, A.: Newtonian scene understanding: unfolding the dynamics of objects in static images. In: Computer Vision and Pattern Recognition (CVPR) (2016) Mottaghi, R., Bagherinezhad, H., Rastegari, M., Farhadi, A.: Newtonian scene understanding: unfolding the dynamics of objects in static images. In: Computer Vision and Pattern Recognition (CVPR) (2016)
19.
Zurück zum Zitat Qi, S., Jia, B., Zhu, S.C.: Generalized earley parser: bridging symbolic grammars and sequence data for future prediction. In: International Conference on Machine Learning (ICML) (2018) Qi, S., Jia, B., Zhu, S.C.: Generalized earley parser: bridging symbolic grammars and sequence data for future prediction. In: International Conference on Machine Learning (ICML) (2018)
20.
Zurück zum Zitat Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning (ICML) (2015) Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning (ICML) (2015)
21.
Zurück zum Zitat Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Neural Information Processing Systems (NIPS) (2016) Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Neural Information Processing Systems (NIPS) (2016)
23.
Zurück zum Zitat Watters, N., Tacchetti, A., Weber, T., Pascanu, R., Battaglia, P., Zoran, D.: Visual interaction networks. In: Neural Information Processing Systems (NIPS) (2017) Watters, N., Tacchetti, A., Weber, T., Pascanu, R., Battaglia, P., Zoran, D.: Visual interaction networks. In: Neural Information Processing Systems (NIPS) (2017)
24.
Zurück zum Zitat Wu, J., Lim, J.J., Zhang, H., Tenenbaum, J.B., Freeman, W.T.: Physics 101: learning physical object properties from unlabeled videos. In: BMVC (2016) Wu, J., Lim, J.J., Zhang, H., Tenenbaum, J.B., Freeman, W.T.: Physics 101: learning physical object properties from unlabeled videos. In: BMVC (2016)
25.
Zurück zum Zitat Wu, J., Lu, E., Kohli, P., Freeman, W.T., Tenenbaum, J.B.: Learning to see physics via visual de-animation. In: Neural Information Processing Systems (NIPS) (2017) Wu, J., Lu, E., Kohli, P., Freeman, W.T., Tenenbaum, J.B.: Learning to see physics via visual de-animation. In: Neural Information Processing Systems (NIPS) (2017)
26.
Zurück zum Zitat Wu, J., Yildirim, I., Lim, J.J., Freeman, W.T., Tenenbaum, J.B.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: Neural Information Processing Systems (NIPS) (2015) Wu, J., Yildirim, I., Lim, J.J., Freeman, W.T., Tenenbaum, J.B.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: Neural Information Processing Systems (NIPS) (2015)
27.
Zurück zum Zitat Xue, T., Wu, J., Bouman, K.L., Freeman, W.T.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: Neural Information Processing Systems (NIPS) (2016) Xue, T., Wu, J., Bouman, K.L., Freeman, W.T.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: Neural Information Processing Systems (NIPS) (2016)
28.
Zurück zum Zitat Zhang, R., Wu, J., Zhang, C., Freeman, W.T., Tenenbaum, J.B.: A comparative evaluation of approximate probabilistic simulation and deep neural networks as accounts of human physical scene understanding. In: Proceedings of the 38th Annual Conference of the Cognitive Science Society (2016) Zhang, R., Wu, J., Zhang, C., Freeman, W.T., Tenenbaum, J.B.: A comparative evaluation of approximate probabilistic simulation and deep neural networks as accounts of human physical scene understanding. In: Proceedings of the 38th Annual Conference of the Cognitive Science Society (2016)
29.
Zurück zum Zitat Zheng, B., Zhao, Y., Yu, J., Ikeuchi, K., Zhu, S.C.: Scene understanding by reasoning stability and safety. Int. J. Comput. Vis. (IJCV) 112, 221–238 (2015)MathSciNetCrossRef Zheng, B., Zhao, Y., Yu, J., Ikeuchi, K., Zhu, S.C.: Scene understanding by reasoning stability and safety. Int. J. Comput. Vis. (IJCV) 112, 221–238 (2015)MathSciNetCrossRef
31.
Zurück zum Zitat Zhu, Y., Jiang, C., Zhao, Y., Terzopoulos, D., Zhu, S.C.: Inferring forces and learning human utilities from videos. In: Computer Vision and Pattern Recognition (CVPR) (2016) Zhu, Y., Jiang, C., Zhao, Y., Terzopoulos, D., Zhu, S.C.: Inferring forces and learning human utilities from videos. In: Computer Vision and Pattern Recognition (CVPR) (2016)
Metadaten
Titel
Interpretable Intuitive Physics Model
verfasst von
Tian Ye
Xiaolong Wang
James Davidson
Abhinav Gupta
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-01258-8_6

Premium Partner