paper-with-me

홈 › Papers

Predicting the dynamics of 2d objects with a deep residual network

2016-10-13 · François Fleuret

We investigate how a residual network can learn to predict the dynamics of interacting shapes purely as an image-to-image regression task. With a simple 2d physics simulator, we generate short sequences composed of rectangles put in motion by applying a pulling force at a point picked at random. The network is trained with a quadratic loss to predict the image of the resulting configuration, given the image of the starting configuration and an image indicating the point of grasping. Experiments show that the network learns to predict accurately the resulting image, which implies in particular that (1) it segments rectangles as distinct components, (2) it infers which one contains the grasping point, (3) it models properly the dynamic of a single rectangle, including the torque, (4) it detects and handles collisions to some extent, and (5) it re-synthesizes properly the entire scene with displaced rectangles.

📄 PDF Abstract BibTeX arXiv:1610.04032

Code (0)

등록된 구현이 없습니다.

Tasks

Image-to-Image Regression

Similar Papers 제목 키워드 기반

Predicting 3D Rigid Body Dynamics with Deep Residual Network

2024-07-09 · Abiodun Finbarrs Oketunji

This study investigates the application of deep residual networks for predicting the dynamics of interacting three-dimensional rigid bodies. We present a framework combining a 3D physics simulator implemented in C++ with…

FrictionPhysics-informed machine learning

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

2024-05-02 · Homanga Bharadhwaj, Roozbeh Mottaghi, Abhinav Gupta, Shubham Tulsiani

We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation: interacting with unseen objects in novel scenes without test-time adaptation. While typical approaches rely on a large a…

Robot ManipulationTest-time Adaptation

TossingBot: Learning to Throw Arbitrary Objects with Residual Physics

2019-03-27 · Andy Zeng, Shuran Song, Johnny Lee, Alberto Rodriguez 외

We investigate whether a robot arm can learn to pick and throw arbitrary objects into selected boxes quickly and accurately. Throwing has the potential to increase the physical reachability and picking speed of a robot a…

Friction

Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction

2019-10-17 · Ajay Jain, Sergio Casas, Renjie Liao, Yuwen Xiong 외

Self-driving vehicles plan around both static and dynamic objects, applying predictive models of behavior to estimate future locations of the objects in the environment. However, future behavior is inherently uncertain, …

Human motion predictionMotion Forecastingmotion predictionPrediction

MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy

2026-05-21 · Jiaxu Wang, Junhao He, Jingkai Sun, Yi Gu 외 arxiv

Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physical parameters, yet accuracy is ultimately bounded by the underlying p…

Robot Manipulation