A Differentiable Physics Engine for Deep Learning in Robotics

Article, Preprint English OPEN
Degrave, Jonas; Hermans, Michiel; Dambre, Joni; wyffels, Francis;
(2019)
  • Publisher: Frontiers Media S.A.
  • Journal: Frontiers in Neurorobotics, volume 13 (issn: 1662-5218, eissn: 1662-5218)
  • Publisher copyright policies & self-archiving
  • Related identifiers: doi: 10.3389/fnbot.2019.00006/full, doi: 10.3389/fnbot.2019.00006, pmc: PMC6416213
  • Subject: Simulation Technology | Computer Science - Artificial Intelligence | Neurosciences. Biological psychiatry. Neuropsychiatry | RC321-571 | robotics | Computer Science - Robotics | Technology and Engineering | neural network controller | deep learning | Robotics and AI | backpropagation | Original Research | differentiable physics engine | gradient descent | Computer Science - Neural and Evolutionary Computing | Differential physics engine
    arxiv: Computer Science::Robotics

An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are... View more
  • References (23)
    23 references, page 1 of 3

    Al-Rfou, R., Alain, G., Almahairi, A., Angermueller, C., Bahdanau, D., Ballas, N., Bastien, F., Bayer, J., Belikov, A., et al. (2016). Theano: A python framework for fast computation of mathematical expressions. arXiv preprint arXiv:1605.02688.

    Catto, E. (2009). Modeling and solving constraints. In Game Developers Conference.

    Chappuis, D. (2013). Constraints derivation for rigid body simulation in 3D.

    Degrave, J., Burm, M., Kindermans, P.-J., Dambre, J., et al. (2015). Transfer learning of gaits on a quadrupedal robot. Adaptive Behavior, page 1059712314563620.

    Degrave, J., Burm, M., Waegeman, T., Wyffels, F., and Schrauwen, B. (2013). Comparing trotting and turning strategies on the quadrupedal oncilla robot. In Robotics and Biomimetics (ROBIO), 2013 IEEE International Conference on, pages 228-233. IEEE.

    Degrave, J., Dieleman, S., Dambre, J., et al. (2016). Spatial chirp-Z transformer networks. In European Symposium on Artificial Neural Networks (ESANN).

    Erez, T., Tassa, Y., and Todorov, E. (2015). Simulation tools for model-based robotics: Comparison of bullet, havok, mujoco, ode and physx. In International Conference on Robotics and Automation (ICRA), pages 4397-4404. IEEE.

    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Advances in Neural Information Processing Systems, pages 2672- 2680.

    Hansen, N. (2006). The cma evolution strategy: a comparing review. In Towards a new evolutionary computation, pages 75-102. Springer Berlin Heidelberg.

    Hermans, M., Schrauwen, B., Bienstman, P., and Dambre, J. (2014). Automated design of complex dynamic systems. PloS one, 9(1):e86696.

  • Related Research Results (1)
    Inferred by OpenAIRE
    dataset
    Automated Design of Complex Dynamic Systems (2016)
    53%
  • Metrics
Share - Bookmark