Lecture

Encoder for Force and Vision in Manipulation

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture discusses combining force and vision into a lower dimensional representation for contact wrench manipulation, aiming to enhance downstream learning tasks' efficiency. Drawing inspiration from Helmholtz's theory of perception, the presenter proposes evaluating learned representations using mutual information between the full state and the learned representation.

Official source

Ontological neighbourhood

Physics

Mechanics: Classical mechanics

Related concepts (32)

Force

In physics, a force is an influence that can cause an object to change its velocity, i.e., to accelerate, unless counterbalanced by other forces. The concept of force makes the everyday notion of pushing or pulling mathematically precise. Because the magnitude and direction of a force are both important, force is a vector quantity. It is measured in the SI unit of newton (N) and often represented by the symbol F.

Variational autoencoder

In machine learning, a variational autoencoder (VAE) is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling. It is part of the families of probabilistic graphical models and variational Bayesian methods. Variational autoencoders are often associated with the autoencoder model because of its architectural affinity, but with significant differences in the goal and mathematical formulation. Variational autoencoders are probabilistic generative models that require neural networks as only a part of their overall structure.

Autoencoder

An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction. Variants exist, aiming to force the learned representations to assume useful properties.

Lagrangian mechanics

In physics, Lagrangian mechanics is a formulation of classical mechanics founded on the stationary-action principle (also known as the principle of least action). It was introduced by the Italian-French mathematician and astronomer Joseph-Louis Lagrange in his 1788 work, Mécanique analytique. Lagrangian mechanics describes a mechanical system as a pair consisting of a configuration space and a smooth function within that space called a Lagrangian. For many systems, where and are the kinetic and potential energy of the system, respectively.

Mutual information

In probability theory and information theory, the mutual information (MI) of two random variables is a measure of the mutual dependence between the two variables. More specifically, it quantifies the "amount of information" (in units such as shannons (bits), nats or hartleys) obtained about one random variable by observing the other random variable. The concept of mutual information is intimately linked to that of entropy of a random variable, a fundamental notion in information theory that quantifies the expected "amount of information" held in a random variable.

Related lectures (64)

Understanding Autoencoders

Explores autoencoders, from linear mappings in PCA to nonlinear mappings, deep autoencoders, and their applications.

Machine Learning Fundamentals

Introduces fundamental machine learning concepts, covering regression, classification, dimensionality reduction, and deep generative models.

Dimensionality Reduction: PCA & Autoencoders

Explores PCA, Autoencoders, and their applications in dimensionality reduction and data generation.

Deep Generative Models: Variational Autoencoders & GANs

Explores Variational Autoencoders and Generative Adversarial Networks for deep generative modeling.

Non-Linear Dimensionality Reduction