H2020Индивидуална стипендия2021–2023

Dr VCoach · Employment of Advanced Deep Learning and Human-Robot Interaction for Virtual Coaching

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2021-09-01 → 2023-12-31
Финансиране от ЕС: 171 473 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Роботи-треньори с изкуствен интелект се разработват, за да показват гимнастически упражнения и да коригират грешките на възрастни хора чрез камери. Това помага за поддържане на независимостта и здравето на възрастните, като намалява нуждата от постоянен надзор от болногледач.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Employment of Advanced Deep Learning and Human-Robot Interaction for Virtual Coaching

The rise in global wealth and well-being has led to an increased percentage of the elderly population, requiring daily assistance and monitoring for a safe and productive life. Technologies that promote active aging appear to be the right solution to enhance elders' independence and well-being. Regular physical activity is critical for maintaining independence, but often elders require the presence of a caregiver for monitoring. Researchers aim to automate the teaching and monitoring process, proposing virtual coaches capable of suggesting exercises, monitoring execution, and sending results to a doctor. While a computer, screen, and camera are sufficient to implement a virtual coach, humanoid robots present a promising solution. A humanoid robot can demonstrate exercises, making movements easier to understand for the elderly. The output of our project is a robotic coach designed to assist the elderly during their daily physical training. The robot can: 1 - understand verbal commands from the user through a conversational module 2 - define the sequence of exercises and show them to the user through a control module 3 - monitor the user performing exercises using RGB cameras and identify errors through a video action recognition module. Although several datasets for video action recognition exist, none completely cover the movements and labels needed for this project. Hence, a new dataset was created by collecting RGB videos of people performing soft gymnastic exercises in a lab environment. This core dataset was augmented in simulation using a synthetic image generator implemented in Unity. Simulated avatars, moved with the originally recorded data, and added randomization to motion, background, lighting, and camera position, resulting in a large augmented dataset. The system has been implemented on the Nao robot. The research focus of the project includes: 1 - defining a set of gentle gymnastic actions 2 - introducing a new Unity synthetic data generator 3 - creating a novel dataset to train the action recognition and prediction models 4 - integrating all project modules into the final robotic coach implementation 5 - deploying and testing the robotic coach on subjects in a real-life scenario.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

The main objective of this project (DR VCoach) will be the following: “Design and implement a robotic coach able to propose a proper exercise schedule based on human directives, monitor the exercise performed by the patient/elder and correct it in case of mistakes”. The output of the project will be a robotic coach to assist the elders during their daily physical training. The robot will be able to understand verbal commands from the user (e.g. what will be the training schedule of today? Today I feel tired, can we do a lighter training?), to define the sequence of exercises to be performed, to show the exercises to the user (with a verbal description and performing them by it-self), to monitor the user performing the exercises using RGB cameras, to eventually find some errors in the execution and to suggest a correction to the mistake.The whole system can be divided into four modules:- Speech module: This is the module in charge of the vocal interaction between the robot and the elders. - Exercise scheduler: The role of this module is to break the selected exercise into atomic actions, and send these actions to the Error detector and Action recognition and prediction modules. - Error detector: The Error detector module analyses the results coming from the Action recognition and prediction module based on the required actions received by the Exercise scheduler. After evaluating the performed action, the module sends an evaluation report to the speech module in order to inform the elder. - Action recognition and prediction: This module has the dual task of recognising the action performed by the elder using the RGB videos coming from its embedded camera, and predicting the future viso-proprioceptive stimuli based on the action that is being performed.The system will be implemented on Zora (a NAO robot with a software layer to make it usable by non ICT people).

Оригинален текст от CORDIS (на английски).

Участници

UNIVERSITA DEGLI STUDI DI CAGLIARI · CagliariКоординаторИталия