Export 8 results:
Filters: Author is Kevin A. Smith [Clear All Filters]
Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning. Proceedings of the National Academy of Sciences 201912341 (2020). doi:10.1073/pnas.1912341117
Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) (2019). at <http: //physadept.csail.mit.edu/>
Differentiable physics and stable modes for tool-use and manipulation planning. Robotics: Science and Systems 2018 (2018).
End-to-end differentiable physics for learning and control. Advances in Neural Information Processing Systems 31 (NIPS 2018) (2018).
Faulty Towers: A counterfactual simulation model of physical support. Proceedings of the 39th Annual Conference of the Cognitive Science Society (2017).
Rapid Physical Predictions from Convolutional Neural Networks. Neural Information Processing Systems, Intuitive Physics Workshop (2016). at <http://phys.csail.mit.edu/papers/9.pdf>