TY - JOUR
T1 - A survey on semantic-based methods for the understanding of human movements
AU - Ramirez-Amaro, Karinne
AU - Yang, Yezhou
AU - Cheng, Gordon
N1 - Funding Information:
Karinne Ramirez-Amaro and Gordon Cheng were partially supported by the German Research Foundation DFG, as part of Collaborative Research Center (Sonderforschungsbereich) 1320 “EASE - Everyday Activity Science and Engineering”, University of Bremen (http://www.ease-crc.org/). The research was conducted in subproject R01, “NEEM-based embodied knowledge framework”. Yezhou Yang was partially supported by US National Science Foundation NSF grant No. 1750082 and 1816039. No author associated with this paper has disclosed any potential or pertinent conflicts which may be perceived to have impending conflict with this work. For full disclosure statements refer to https://doi.org/10.1016/j.robot.2019.05.013.
Funding Information:
Karinne Ramirez-Amaro and Gordon Cheng were partially supported by the German Research Foundation DFG , as part of Collaborative Research Center (Sonderforschungsbereich) 1320 “EASE - Everyday Activity Science and Engineering”, University of Bremen ( http://www.ease-crc.org/ ). The research was conducted in subproject R01, “NEEM-based embodied knowledge framework”. Yezhou Yang was partially supported by US National Science Foundation NSF grant No. 1750082 and 1816039 .
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/9
Y1 - 2019/9
N2 - This paper presents semantic-based methods for the understanding of human movements in robotic applications. To understand human movements, robots need to first, recognize the observed or demonstrated human activities, and secondly, learn different parameters to execute an action or robot behavior. In order to achieve that, several challenges need to be addressed such as the automatic segmentation of human activities, identification of important features of actions, determine the correct sequencing between activities, and obtain the correct mapping between the continuous data and the symbolic and semantic interpretations of the human movements. This paper aims to present state-of-the-art semantic-based approaches, especially the new emerging approaches that tackle the challenges of finding generic and compact semantic models for the robotics domain. Finally, we will highlight potential breakthroughs and challenges for the next years such as achieving scalability, better generalization, compact and flexible models, and higher system accuracy.
AB - This paper presents semantic-based methods for the understanding of human movements in robotic applications. To understand human movements, robots need to first, recognize the observed or demonstrated human activities, and secondly, learn different parameters to execute an action or robot behavior. In order to achieve that, several challenges need to be addressed such as the automatic segmentation of human activities, identification of important features of actions, determine the correct sequencing between activities, and obtain the correct mapping between the continuous data and the symbolic and semantic interpretations of the human movements. This paper aims to present state-of-the-art semantic-based approaches, especially the new emerging approaches that tackle the challenges of finding generic and compact semantic models for the robotics domain. Finally, we will highlight potential breakthroughs and challenges for the next years such as achieving scalability, better generalization, compact and flexible models, and higher system accuracy.
KW - Human activity recognition
KW - Intelligent systems
KW - Robot action execution
KW - Semantic representations
KW - Understanding human movements
UR - http://www.scopus.com/inward/record.url?scp=85067241613&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85067241613&partnerID=8YFLogxK
U2 - 10.1016/j.robot.2019.05.013
DO - 10.1016/j.robot.2019.05.013
M3 - Article
AN - SCOPUS:85067241613
SN - 0921-8890
VL - 119
SP - 31
EP - 50
JO - Robotics and Autonomous Systems
JF - Robotics and Autonomous Systems
ER -