Publication

Artificial Neural Networks for Impact Position Detection in Haptic Surfaces

Yves Perriard, Paolo Germano, Camilo Hernandez Mejia
2019
Conference Papers

Abstract

Recently, the interest in haptic feedback is growing thanks to its ability to enhance the interaction with Human Machine Interfaces (HMIs). This research project is exploring the potential of machine learning combined with piezoelectric actuators to generate localized vibrational feedback over a thin rigid surface. With this goal in mind, this paper studied the potential of neural networks and machine learning algorithms to extract the position, where an impact has occurred. A data-set with 5310 stress signals labeled with the position at which the impact has occurred, was obtained using an automated Linear Impact Generator (LIG). Each signal was transformed into a spectrogram using the Fast Fourier Transform. During the study, different neural networks and machine learning algorithms were implemented and a supervised training process was carried out. At the end of the paper, the results of the different models are compared. The best model has an error (Validation MAE) of 4% and (Test MAE) of 8% in the impact position detection over an aluminum thin plate.

Official source

https://infoscience.epfl.ch/entities/publication/7918793f-5aec-4146-ae5e-1465ba907962

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Yves Perriard, Paolo Germano, Camilo Hernandez Mejia
2019
Conference Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/7918793f-5aec-4146-ae5e-1465ba907962

About this result

Related concepts (28)

Supervised learning

Supervised learning (SL) is a paradigm in machine learning where input objects (for example, a vector of predictor variables) and a desired output value (also known as human-labeled supervisory signal) train a model. The training data is processed, building a function that maps new data on expected output values. An optimal scenario will allow for the algorithm to correctly determine output values for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way (see inductive bias).

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Machine learning

Machine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.

Related publications (29)

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Romain Christophe Rémy Fleury, Janez Rus

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

2024

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Mathieu Salzmann, Sabine Süsstrunk, Tong Zhang, Yi Wu

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

2024