Cognitive Impairment diseases such as Alzheimer influence millions of people around the world. One usual trait of such diseases is that patients may perform irrational behaviors, which may result in danger to family members or to the patient him/herself. An Intelligent Ambient Assisted Living Systems should provide solutions able to react to those situations in order to guarantee the safety of the patient. Unfortunately, the unpredictable and irrational nature of patient's behaviors makes the development of such systems hard and complex. In this paper, we address this issue by presenting a reinforcement-learning-based solution to define a recovery process from dangerous situations by dynamically defining a safety strategy. The definition of an intelligent recovery process is the final goal of our work. We are testing the first prototype of our solution into a simulated environment

A Reinforcement-Learning-Based Approach for the Planning of Safety Strategies in AAL Applications

Giovanni Paragliola;Antonio Coronato
2018

Abstract

Cognitive Impairment diseases such as Alzheimer influence millions of people around the world. One usual trait of such diseases is that patients may perform irrational behaviors, which may result in danger to family members or to the patient him/herself. An Intelligent Ambient Assisted Living Systems should provide solutions able to react to those situations in order to guarantee the safety of the patient. Unfortunately, the unpredictable and irrational nature of patient's behaviors makes the development of such systems hard and complex. In this paper, we address this issue by presenting a reinforcement-learning-based solution to define a recovery process from dangerous situations by dynamically defining a safety strategy. The definition of an intelligent recovery process is the final goal of our work. We are testing the first prototype of our solution into a simulated environment
2018
Istituto di Calcolo e Reti ad Alte Prestazioni - ICAR
Ambient Assisted Living
Reinforcement Learning
Machine Learning
Planning
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/344075
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact