Automatic Learning of Cognitive Exercises for Socially Assistive Robotics
| Autor: | Antonio Andriella, Aleksandar Taranovic, Alejandro Suárez-Hernández, Javier Segovia-Aguas, Guillem Alenyà, Carme Torras |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Doctorat en Automàtica, Robòtica i Visió, Institut de Robòtica i Informàtica Industrial, Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI, European Commission, Ministerio de Economía y Competitividad (España) |
| Rok vydání: | 2021 |
| Předmět: |
Computational intelligence
Artificial intelligence Learning (artificial intelligence) Robòtica Computer science business.industry Intel·ligència artificial Planning (artificial intelligence) Healthcare Sorting Cognition Context (language use) Robotics Action (philosophy) Intel·ligència computacional aprenentatge automatic Human–computer interaction Machine learning Informàtica::Intel·ligència artificial [Àrees temàtiques de la UPC] Affect (linguistics) Set (psychology) business Rehabilitation robotics Knowledge engineering Graphical user interface |
| Zdroj: | RO-MAN UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) Digital.CSIC. Repositorio Institucional del CSIC instname 2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) |
| DOI: | 10.1109/ro-man50785.2021.9515433 |
| Popis: | Trabajo presentado en el 30th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), celebrada de forma virtual del 8 al 12 de agosto de 2021 In this paper, we present a learning approach to facilitate the teaching of new board exercises to assistive robotic systems. We formulate the problem as the learning of action models using Boolean predicates, disjunctive preconditions, and existential quantifiers from demonstrations of successful exercise executions. To be able to cope with exercises whose rules depend on a set of features that are initialized at the beginning of each play-out, we introduce the concept of dynamic context. Furthermore, we show how the learnt knowledge can be represented intuitively in a graphical interface that helps the caregiver understand what the system has learnt. As validation, we conducted a user study in which we evaluated whether and to which extent different types of feedback can affect the subjects¿ performance while teaching three types of exercises: (1) sorting numbers; (2) arranging letters; and (3) reproducing shapes sequences in reversed order. The results suggest that textual and graphical feedback are beneficial. A. Andriella, C. Torras and A. Suarez-Hernandez were partially funded ´ by the European Union´s Horizon 2020 under ERC Advanced Grant CLOTHILDE (no. 741930), G. Alenya by the EU H2020 research and ` innovation programme IMAGINE (no. 731761) and J. Segovia-Aguas by the programme TAILOR (no. 952215). The work was partially supported by the Spanish State Research Agency through the Mar´ıa de Maeztu Seal of Excellence to IRI (MDM-2016-0656). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|