Abstract
With the advancement of robotics, the importance of service robots in society is increasing. It is crucial for service robots to understand their environment so that they can offer suitable responses to humans. To realize the use of space, robots primarily use an environment model. This paper is focused on the development of an environment model based on human behaviors. In this model, a new neural network structure called dynamic highway networks is applied to recognize humans’ behaviors. In addition, a two-dimensional pose estimator, Laban movement analysis, and the fuzzy integral are employed. With these methods, two new behavior-recognition algorithms are developed, and a method to record the relationship between behavior and environment is proposed. Based on the proposed environmental model, robots can identify abnormal behavior, provide an appropriate response and guide a person toward the desired normal behavior by identifying abnormal behavior. Simulations and experiments justify the proposed method with satisfactory results.
Highlights
With the rapid development of robots nowadays, service robots are becoming increasingly popular in ageing societies
Semantic labels are recorded for the object in the environment so that the map can provide a semantic level of understanding of the environment
We focus on developing a behavior cognitive map that can recognize and record human behaviors
Summary
With the rapid development of robots nowadays, service robots are becoming increasingly popular in ageing societies. We devise a method to enable robots to understand an environment through human behavior on physical information alone This method records human behaviors in each cell of map and describes the human behaviors that are suitable for the specific location. The aforementioned system has several functional components, including two-dimensional (2D) pose estimator using part affinity fields (PAFs), body behavior recognition using gated-recurrent-units (GRU)-based dynamic highway network (DHN), behavior-identification using Laban movement analysis, and behavior cognitive map. The remaining parts of this paper are organized as follows: Section 2 presents two modules for human behavior recognition and introduce the 2D pose estimator using PAFs and the GRU-based DHN. Human behavior recognition and introduce the 2D pose estimator using PAFs and the GRU-based With these two functional components, a behavior-recognition model is constructed. Equation (9) shows that y is a linear combination of input x and the output of the transform
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
