An important aspect in Human-Robot Interaction is responding to different kinds of touch stimuli. To date, several technologies have been explored to determine how a touch is perceived by a social robot, usually placing a large number of sensors throughout the robot's shell. In this work, we introduce a novel approach, where the audio acquired from contact microphones located in the robot's shell is processed using machine learning techniques to distinguish between different types of touches. The system is able to determine when the robot is touched (touch detection), and to ascertain the kind of touch performed among a set of possibilities: , , , and (touch classification). This proposal is cost-effective since just a few microphones are able to cover the whole robot's shell since a single microphone is enough to cover each solid part of the robot. Besides, it is easy to install and configure as it just requires a contact surface to attach the microphone to the robot's shell and plug it into the robot's computer. Results show the high accuracy scores in touch gesture recognition. The testing phase revealed that Logistic Model Trees achieved the best performance, with an -score of 0.81. The dataset was built with information from 25 participants performing a total of 1981 touch gestures.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5470814 | PMC |
| http://dx.doi.org/10.3390/s17051138 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Robotic Microcapsule Assemblies with Adaptive Mobility for Targeted Treatment of Rugged Biological Microenvironments.
ACS Nano
January 2025
Center for Innovation & Precision Dentistry, School of Dental Medicine, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States.
Microrobots are poised to transform biomedicine by enabling precise, noninvasive procedures. However, current magnetic microrobots, composed of solid monolithic particles, present fundamental challenges in engineering intersubunit interactions, limiting their collective effectiveness in navigating irregular biological terrains and confined spaces. To address this, we design hierarchically assembled microrobots with multiaxis mobility and collective adaptability by engineering the potential magnetic interaction energy between subunits to create stable, self-reconfigurable structures capable of carrying and protecting cargo internally.
View Article and Find Full Text PDFDSC-SeNet: Unilateral Network with Feature Enhancement and Aggregation for Real-Time Segmentation of Carbon Trace in the Oil-Immersed Transformer.
Sensors (Basel)
December 2024
State Grid Tianjin Electric Power Research Institute, Tianjin 300180, China.
Large oil-immersed transformers have metal-enclosed shells, making it difficult to visually inspect the internal insulation condition. Visual inspection of internal defects is carried out using a self-developed micro-robot in this work. Carbon trace is the main visual characteristic of internal insulation defects.
View Article and Find Full Text PDFNoble Metal Nanoparticle Assisted Mass Spectrometry for Metabolite-Based In Vitro Diagnostics.
Small
December 2024
State Key Laboratory of Systems Medicine for Cancer, School of Biomedical Engineering, Institute of Medical Robotics and Med-X Research Institute, Shanghai Jiao Tong University, Shanghai, 200030, P. R. China.
In vitro diagnostics (IVD) makes clinical diagnosis rapid, simple, and noninvasive to patients, playing a crucial role in the early diagnosis and monitoring of diseases. Metabolic biomarkers are closely correlated to the phenotype of diseases. However, most IVD platforms are constrained by the sensitivity and throughput of assay.
View Article and Find Full Text PDFLeveraging generative neural networks for accurate, diverse, and robust nanoparticle design.
Nanoscale Adv
January 2025
Department of Electrical and Electronic Engineering, University of Dhaka Dhaka-1000 Bangladesh
Tandem neural networks for inverse design can only make single predictions, which limits the diversity of predicted structures. Here, we use conditional variational autoencoder (cVAE) for the inverse design of core-shell nanoparticles. cVAE is a type of generative neural network that generates multiple valid solutions for the same input condition.
View Article and Find Full Text PDFBistable Soft Shells for Programmable Mechanical Logic.
Adv Sci (Weinh)
December 2024
Department of Mechanical Engineering (Robotics), Guangdong Technion-Israel Institute of Technology, Shantou, 515063, China.
Mechanical computing promises to integrate semiconductor-based digital logic in several applications, but it needs straightforward programmable devices for changing computing rules in situ. A methodology based on strain-governed, bistable soft shells that process digital information by interchanging their internal/external surfaces is proposed. This bistable behavior, explained via model-based design, safeguards robustness by working only once for each input pulse.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!