.png){kind=icon}
.png){kind=icon}
Return
Face Memorization System Using the Mathematical AIM Model for Mobile Robot
.png){kind=icon}
PRE
AI
DOI：10.1109/sii.2019.8700362.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we present a bio-inspired method to help make efficient utilization of computing resource and battery of a robot system, and at the same time, help a robot to draw people's attention and leave a friendly impression. To achieve the goals described above, firstly, the mathematical Activation-Input-Modulation (AIM) model is applied to the robot, which can emulate the human states of consciousness (e.g., waking, sleeping). By using it, the robot will be able to switch state according to the external environment. When there is nobody around the robot, it turns the state from waking to sleeping, cutting down a part of information processing to economize the utilization of computing resource and battery. Secondly, we propose to develop a face memorization system which enables the robot to recognize the human face by using deep/machine learning methods. When the robot meets a person whose face was memorized, it greets that person by calling his/her name to draw people's attention and leave a friendly impression on them. Besides, in order to make effective use of the sleeping time, when the robot is in the sleeping state, we propose to assign works to the robot that are difficult or unnecessary to be processed when in the waking state, such as image pre-processing and classifier training. These works are also necessary to implement a face recognition function that can achieve high accuracy. Finally, experiments using the mathematical AIM model and the face memorization system together were conducted to demonstrate the effectiveness of the proposed method on the utilization of computing resource and battery.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
0
Papers:
4
Citations:
0