Fall Risk Reduction for the Elderly by Using Mobile Robots Based on Deep Reinforcement Learning

Abstract

Slip-induced fall is one of the main factors causing serious fracture injuries among the elderly. In this paper, we propose a fall risk reduction measures for the elderly, based on deep reinforcement learning using mobile assistant robots. Our method involves online real-time risk analysis and risk reduction. The results suggest that our method is applicable to the prevention of not only slip-induced fall, but also other factors related to falling and other cases of accidents.