Search Results for author: Changkyu Song

Found 5 papers, 1 papers with code

A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs

1 code implementation10 Nov 2020 Juntao Tan, Changkyu Song, Abdeslam Boularias

The triplet examples are finally used to train a siamese neural network that projects the generic visual features into a low-dimensional manifold.

Clustering object-detection +2

Learning to Slide Unknown Objects with Differentiable Physics Simulations

no code implementations11 May 2020 Changkyu Song, Abdeslam Boularias

We propose a new technique for pushing an unknown object from an initial configuration to a goal configuration with stability constraints.

Friction

Identifying Mechanical Models through Differentiable Simulations

no code implementations L4DC 2020 Changkyu Song, Abdeslam Boularias

This paper proposes a new method for manipulating unknown objects through a sequence of non-prehensile actions that displace an object from its initial configuration to a given goal configuration on a flat surface.

Friction

Inferring 3D Shapes of Unknown Rigid Objects in Clutter through Inverse Physics Reasoning

no code implementations13 Mar 2019 Changkyu Song, Abdeslam Boularias

We present a probabilistic approach for building, on the fly, 3-D models of unknown objects while being manipulated by a robot.

Fast ADMM Algorithm for Distributed Optimization with Adaptive Penalty

no code implementations30 Jun 2015 Changkyu Song, Sejong Yoon, Vladimir Pavlovic

We propose new methods to speed up convergence of the Alternating Direction Method of Multipliers (ADMM), a common optimization tool in the context of large scale and distributed learning.

Distributed Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.