A Robotic System for Elderly Care and Monitoring using Human-Robot Interaction

A Robotic System for Elderly Care and Monitoring using Human Robot Interaction

Table of Contents





 Abstract

Human-Robot Interaction is an emerging field in the area of robotics and growth in this field finds application in several areas of society. In this paper, the initial progress of the design of a robotic system for elderly care is proposed. The paper describes the basic architecture of this proposed system and presents an initial implementation of this robot. This is a work in progress, and the robotic system will be updated and developed as the research progresses when more sensors and other components are interfaced providing more functionalities to the robot. Also, another goal of the project is a contribution to undergraduate electrical and computer engineering education where students understand and learn to work on both hardware and software aspects in the design of an assistive robotic system.

  • Author Keywords

    • Human-Robot Interaction,
    • Robotic System Architecture,
    • Motion Control,
    • Social Robotics,
    • Machine Learning,
    • Sensors
  • IEEE Keywords

    • Educational robots,
    • Robot sensing systems,
    • Senior citizens,
    • Field programmable gate arrays,
    • Cameras

Introduction

Many robots today have pre-programmed commands and responses which listen for keywords in a very particular order. The robot we propose to create, however, will use better natural language processing to understand the intent of any command rather than using command-response dictionaries which are often found in robots today. This would give robots the ability to be social and fit in better in society and be perfect especially for elderly people who are lonely and in need of companionship [1]. Figure 1 shows Rosie, a robot maid created by Toyota [2].

BACKGROUND AND MOTIVATION

The inspiration for social robots comes from biology [3] [4] [5]. In [3], there a description of a social robot, socially interactive robots, and sociable robots. Also, [3] clearly mentions that social robots combine technical and social aspects with more emphasis on social aspects. Hence, a social robot contains a robot and a social interface [3]. A survey of social robots can be found in [4]. In [6], the authors present the categories of assistive robots for elderly care. Also, [6] mention several assistive social robots including examples such as Care-o-bot [7] and Robocare [8]

ARCHITECTURAL DESIGN AND IMPLEMENTATION

Figure 2 shows the architectural description at a high level on how the robot will combine the information and using the FPGA for processing. For this project, a Xilinx Zynq UltraScale+ MPSoC ZCUl04 Evaluation Kit FPGA [9] is planned to be used to accelerate machine learning algorithms which would be vital to receive quick responses from the robot during the interaction. This FPGA would be dedicated to machine learning algorithms that would execute almost instantaneously as opposed to a software solution which would be very slow and inconvenient. In addition, a TUL PYNQ-Z2 FPGA [10] [11] is planned to be used as the main operating system which would control the other modules including the Xilinx Zynq.

Language processing would utilize Microsoft’s language understanding algorithms. In terms of computer vision, a tracking camera would be used for analyzing and remembering objects and people through tensor flow machine learning algorithms. This camera could compute all of the tracking information on-board, so there would be a much lower load on the FPGA itself. The software of the robot would enable it to be very modular and highly scalable. The future scope of this project could use a loT and is capable of more than its social and assistive abilities. One could imagine a framework or API to allow any developer to add apps with additional capabilities (for example, an app that enables the robot to play audiobooks). For the mechanical aspect of the robot, the chassis would be semi-humanoid. It would have arms and a pseudo-head, however, to keep things simple, the bottom would be a simple wheel-driven mechanism. The FPGAs would run Python code allowing the use of Tensor Flow Python libraries [12] for machine learning. This would also allow easy prototyping and implementation due to its ease of readability.

Conclusion

The paper presented a current work in progress of a semi-humanoid helper robot that can understand language and carry out tasks based on the intent of a given command. The robot will have a humanoid appearance except for the wheel-driven base. Technology that will be used in this project includes FPGA ZYNQ [11] development boards from Xilinx, tracking cameras, machine learning algorithms, and Machine vision accelerator FPGAs also made by Xilinx. The system will also consist of a learnable object database. This will allow the robot to learn what objects look like using the tracking camera on the robot. Advantages to this include the ability to find and retrieve objects it has learned, such as glasses or keys. The tracking camera can also be used to maintain eye contact during conversation. These features will be added to the robot as the project develops and the research progresses when more sensors and additional components will be interfaced with the system. Once the robot is developed it will be tested for scenarios such as monitoring and reporting elderly health and care as needed by the application. The scope of this research can help to improve the quality of living for elderly people, enable a better standard of living and assistance, and provide emotional support and care as needed. Another goal of this research is to help undergraduate students in Electrical and Computer Engineering gain knowledge and experience working with both hardware and software thus improving their technical and analytical skills. The next steps of this research are to continue the implementation on the PYNQ board and interface with additional sensors such as camera, microphone, and similar input modules and extend this towards communication with the human user such as eye-tracking, interpreting voice commands, etc.

About KSRA

The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.

KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.

Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.

The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.

FULL Paper PDF file:

A Robotic System for Elderly Care and Monitoring using Human Robot Interaction

Bibliography

author

J. Andrews, M. Lad and B. Chandrasekaran

Year

2020

Title

A Robotic System for Elderly Care and Monitoring using Human-Robot Interaction

Publish in

2020 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 2020, pp. 0576-0579

Doi

10.1109/CCWC47524.2020.9031215

PDF reference and original file: Click here

 

 

 

 

+ posts

Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.

Website | + posts

Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.

Website | + posts

Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.