Intelligent Evacuation Route Planning Algorithm Based on Maximum Flow.

This paper focuses on the problem of intelligent evacuation route planning for emergencies, including natural and human resource disasters and epidemic disasters, such as the COVID-19 pandemic. The goal of this study was to quickly generate an evacuation route for a community for victims to be evacuated to safe areas as soon as possible. The evacuation route planning problem needs to determine appropriate routes and allocate a specific number of victims to each route. This paper formulates the problem as a maximum flow problem and proposes a binary search algorithm based on a maximum flow algorithm, which is an intelligent optimization evacuation route planning algorithm for the community. Furthermore, the formulation is a nonlinear optimization problem because each route's suggested evacuation time is a convex nonlinear function of the number of victims assigned to that route. Finally, numerical examples and Matlab simulations demonstrate not only the algorithm's effectiveness, but also that the algorithm has low complexity and high precision. The study's findings offer a practical solution for nonlinear models of evacuation route planning, which will be widely used in human society and robot path planning schemes.

Impacts of Human Robot Proxemics on Human Concentration-Training Games with Humanoid Robots.

The use of humanoid robots within a therapeutic role, that is, helping individuals with social disorders, is an emerging field, but it remains unexplored in terms of concentration training. To seamlessly integrate humanoid robots into concentration games, an investigation into the impacts of human robot interactive proxemics on concentration-training games is particularly important. In the case of an epidemic diffusion especially-for example, during the COVID-19 pandemic-HRI games may help in the therapeutic phase, significantly reducing the risk of contagion. In this paper, concentration games were designed by action imitation involving 120 participants to verify the hypothesis. Action-imitation accuracy, the assessment of emotional expression, and a questionnaire were compared with analysis of variance (ANOVA). Experimental results showed that a 2 m distance and left-front orientation for a human and a robot are optimal for human robot interactive concentration training. In addition, females worked better than males did in HRI imitation games. This work supports some valuable suggestions for the development of HRI concentration-training technology, involving the designs of friendlier and more useful robots, and HRI game scenarios.