Corpus ID: 7771457

Learning Physical Intuition of Block Towers by Example

@article{Lerer2016LearningPI,
  title={Learning Physical Intuition of Block Towers by Example},
  author={Adam Lerer and Sam Gross and Rob Fergus},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.01312}
}
Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world. [...] Key Method This data allows us to train large convolutional network models which can accurately predict the outcome, as well as estimating the block trajectories. The models are also able to generalize in two important ways: (i) to new physical scenarios, e.g. towers with an additional block and (ii) to images of real wooden blocks, where it obtains a performance…Expand
IntPhys: A Benchmark for Visual Intuitive Physics Reasoning.
TLDR
An evaluation benchmark is proposed which diagnoses how much a given system understands about physics by testing whether it can tell apart well matched videos of possible versus impossible events constructed with a game engine. Expand
IntPhys 2019: A Benchmark for Visual Intuitive Physics Understanding
In order to reach human performance on complex visual tasks, artificial systems need to incorporate a significant amount of understanding of the world in terms of macroscopic objects, movements,Expand
IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
TLDR
An evaluation framework which diagnoses how much a given system understands about physics by testing whether it can tell apart well matched videos of possible versus impossible events, and describes the first release of a benchmark dataset aimed at learning intuitive physics in an unsupervised way. Expand
Visual stability prediction for robotic manipulation
TLDR
This paper presents a learning-based approach based on simulated data that predicts stability of towers comprised of wooden blocks under different conditions and quantities related to the potential fall of the towers that in return enables successful stacking. Expand
University of Birmingham Visual stability prediction for robotic manipulation
Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel objects andExpand
Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning
TLDR
A synthetic block stacking environment with physics simulation is created in which the agent can learn a policy end-to-end through trial and error and a deep reinforcement learning framework that learns policies which are parametrized by a goal is proposed. Expand
Visual Stability Prediction and Its Application to Manipulation
TLDR
A learning-based approach based on simulated data that predicts stability of towers comprised of wooden blocks under different conditions and quantities related to the potential fall of the towers that in turn enables successful stacking. Expand
Learning to Poke by Poking: Experiential Learning of Intuitive Physics
TLDR
A novel approach based on deep neural networks is proposed for modeling the dynamics of robot's interactions directly from images, by jointly estimating forward and inverse models of dynamics. Expand
Neural Allocentric Intuitive Physics Prediction from Real Videos
TLDR
This work proposes a new perspective on the problem of learning intuitive physics that is inspired by the spatial memory representation of objects and spaces in human brains, in particular the co-existence of egocentric and allocentric spatial representations. Expand
Unsupervised Intuitive Physics from Visual Observations
TLDR
It is demonstrated for the first time that it is possible to learn reliable extrapolators of the object trajectories from raw videos alone, without any form of external supervision and with no more prior knowledge than the choice of a convolutional neural network architecture. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction
TLDR
A learning-based approach based on simulated data that predicts stability of towers comprised of wooden blocks under different conditions and quantities related to the potential fall of the towers by an end-to-end approach that directly predicts stability and related quantities from appearance. Expand
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning
TLDR
This study points towards an account of human vision with generative physical knowledge at its core, and various recognition models as helpers leading to efficient inference. Expand
Simulation as an engine of physical scene understanding
TLDR
This work proposes a model based on an “intuitive physics engine,” a cognitive mechanism similar to computer engines that simulate rich physics in video games and graphics, but that uses approximate, probabilistic simulations to make robust and fast inferences in complex natural scenes where crucial information is unobserved. Expand
A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding
TLDR
Four experiments are reported that are the first rigorous comparisons of simulation-based and CNN-based models, where both approaches are concretely instantiated in algorithms that can run on raw image inputs and produce as outputs physical judgments such as whether a stack of blocks will fall. Expand
Humans predict liquid dynamics using probabilistic simulation
TLDR
This thesis finds evidence that people’s reasoning about how liquids move is consistent with a computational cognitive model based on approximate probabilistic simulation and extends this thesis to the more complex and unexplored domain of reasoning about liquids. Expand
Consistent physics underlying ballistic motion prediction
TLDR
It is argued that people can apply correct physical principles consistently to simulate the world forward, and that the tasks that require implicit prediction (catching the ball and cutting the string) can be explained by veridical physical principles. Expand
Continuous control with deep reinforcement learning
TLDR
This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs. Expand
Human-level control through deep reinforcement learning
TLDR
This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks. Expand
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response
TLDR
This work represents each possible future using an anticipatory temporal conditional random field (ATCRF) that models the rich spatial-temporal relations through object affordances and represents each ATCRF as a particle and represents the distribution over the potential futures using a set of particles. Expand
Mechanical reasoning by mental simulation
  • M. Hegarty
  • Medicine, Psychology
  • Trends in Cognitive Sciences
  • 2004
TLDR
Although it is frequently accompanied by imagery, mental simulation is not a process of inspecting a holistic visual image in the 'mind's eye'. Expand
...
1
2
3
4
...