TY - JOUR
T1 - Estimation of body direction based on gait for service robot applications
AU - Yorozu, Ayanori
AU - Takahashi, Masaki
N1 - Funding Information:
This study was supported by JSPS KAKENHI Grant Number 17K14619 and “A Framework PRINTEPS to Develop Practical Artificial Intelligence” of the Core Research for Evolutional Science and Technology (CREST) of the Japan Science and Technology Agency (JST) under Grant Number JPMJCR14E3 .
Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2020/10
Y1 - 2020/10
N2 - Recently, there have been several studies on the research and development of service robots, such as reception or waiter robots for facilities and companion robots for support of baggage transportation or guidance in public spaces. Several experimental results in real environments have been reported. To realize socially acceptable human–robot interaction for service robots, human recognition, including not only position but also body direction, around the robot is important. Using an RGB-D camera, it is possible to detect the posture of a person. However, because the viewing angle of the camera is narrow, it is difficult to recognize the environment around the robot with a single device. This study proposes the estimation of the body direction based on the gait, that is, not only the position and velocity, but also the state of the legs (stance or swing phase), using laser range sensors installed at shin height. We verify the effectiveness of the proposed method for several patterns of movement, which are seen when a person interacts with the service robot and evaluate measurement accuracy.
AB - Recently, there have been several studies on the research and development of service robots, such as reception or waiter robots for facilities and companion robots for support of baggage transportation or guidance in public spaces. Several experimental results in real environments have been reported. To realize socially acceptable human–robot interaction for service robots, human recognition, including not only position but also body direction, around the robot is important. Using an RGB-D camera, it is possible to detect the posture of a person. However, because the viewing angle of the camera is narrow, it is difficult to recognize the environment around the robot with a single device. This study proposes the estimation of the body direction based on the gait, that is, not only the position and velocity, but also the state of the legs (stance or swing phase), using laser range sensors installed at shin height. We verify the effectiveness of the proposed method for several patterns of movement, which are seen when a person interacts with the service robot and evaluate measurement accuracy.
KW - Human–robot interaction
KW - Kalman filter
KW - Laser range sensor
KW - Pedestrian tracking
KW - Service robots
UR - http://www.scopus.com/inward/record.url?scp=85089481621&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089481621&partnerID=8YFLogxK
U2 - 10.1016/j.robot.2020.103603
DO - 10.1016/j.robot.2020.103603
M3 - Article
AN - SCOPUS:85089481621
SN - 0921-8890
VL - 132
JO - Robotics and Autonomous Systems
JF - Robotics and Autonomous Systems
M1 - 103603
ER -