Simulation as an engine of physical scene understanding

By Peter W. Battaglia, Jessica B. Hamrick, Josh Tenenbaum. 2013

854 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition, Developmental and Educational Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

In Computer Vision and Pattern Recognition

In Developmental and Educational Psychology

Citations in the corpus

Interaction Networks for Learning about Objects, Relations and Physics (2016, background): “[3] recently posited a simulation-based “intuitive physics engine” 288 model to explain human physical scene understanding.”
Toward Causal Representation Learning (2021, background): “Such a representation allows children to quickly learn new tasks as their knowledge and intuitive understanding of physics can be reused [17], [53], [144], [250].”
Towards Causal Representation Learning (2021, background): “their knowledge and intuitive understanding of physics can be re-used [15, 52, 144, 250].”
CLEVRER: CoLlision Events for Video REpresentation and Reasoning (2019, background): “Our work is also related to research on learning scene dynamics for physical and causal reasoning (Lerer et al., 2016; Battaglia et al., 2013; Mottaghi et al., 2016; Fragkiadaki et al., 2016; Battaglia et al., 2016; Chang et al., 2017; Agrawal et al., 2016; Finn et al., 2016; Shao et al., 2014;…”
Generalization in anti-causal learning (2018, background): “It has been conjectured that humans internally build powerful causal models for simulations and approximate physical mechanisms through intuitive theories (Krynski and Tenenbaum, 2007; Waldmann et al., 2006; Hamrick et al., 2011; Battaglia et al., 2013; Gerstenberg and Tenenbaum, 2017).”
Learning to predict the cosmological structure formation (2018, background): “The ability of these models to learn complex functions has motivated many to use them to understand the physics of interacting objects leveraging image, video and relational data (40–50).”
Relational inductive biases, deep learning, and graph networks (2018, background): “, 1996; Goodwin and Johnson-Laird, 2005; Kemp and Tenenbaum, 2008), such as judging whether a haphazard stack of objects is stable (Battaglia et al., 2013).”
Flexible Neural Representation for Physics Prediction (2018, background): “Recent research in computational cognitive science has posited that humans run physics simulations in their mind [5, 3, 20, 48, 21].”
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions (2018, background): “This prevents such end-to-end neural approaches from efﬁciently learning functions that operate on multiple entities and generalize in a human-like way (c.f. Battaglia et al. (2013); Lake et al. (2016); Santoro et al. (2017), but see Perez et al. (2017)).”
Visual Interaction Networks: Learning a Physics Simulator from Video (2017, background): “These systems include previously studied gravitational and billiards systems [3, 1] with the added challenge of natural image backgrounds.”
A Compositional Object-Based Approach to Learning Physical Dynamics (2016, methodology): “We view this program as a simulator that takes input provided by a physical scene and the past states of objects, and outputs the future states and physical properties of relevant objects (Anderson, 1990; Battaglia et al., 2013; Goodman and Tenenbaum, 2016).”
The limits and potentials of deep learning for robotics (2018, background): “Humans, on the other hand, operate under intuitive rather than exact physical models [6], [7], [10], [45], [74], [88].”
Learning Physical Intuition of Block Towers by Example (2016, methodology): “The most closely related work to ours is (Battaglia et al., 2013) who explore the physics involved with falling blocks.”
Unsupervised Learning for Physical Interaction through Video Prediction (2016, background): “Learning physics: Several works have explicitly addressed prediction of physical interactions, including predicting ball motion [5], block falling [2], the effects of forces [19, 18], future human interactions [9], and future car trajectories [26].”
Graph networks as learnable physics engines for inference and control (2018, background): “Cognitive scientists have long pointed to rich generative models as central to perception, reasoning, and decision-making (Craik, 1967; Johnson-Laird, 1980; Miall & Wolpert, 1996; Spelke & Kinzler, 2007; Battaglia et al., 2013).”
"What Happens If..." Learning to Predict the Effect of Forces in Images (2016, background): “In fact, even with a static image [10,1], humans can perform a mental simulation of the future states and reliably predict the dynamics of the interactions.”
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015, background): “Cognitive studies: Recent studies in computational cognitive science show that humans approximate the principles of Newtonian dynamics and simulate the future states of the world using these principles [14, 5].”