TY - GEN
T1 - Underwater human-robot interaction via biological motion identification
AU - Sattar, Junaed
AU - Dudek, Gregory
PY - 2010
Y1 - 2010
N2 - We present an algorithm for underwater robots to visually detect and track human motion. Our objective is to enable human-robot interaction by allowing a robot to follow behind a human moving in (up to) six degrees of freedom. In particular, we have developed a system to allow a robot to detect, track and follow a scuba diver by using frequencydomain detection of biological motion patterns. The motion of biological entities is characterized by combinations of periodic motions which are inherently distinctive. This is especially true of human swimmers. By using the frequency-space response of spatial signals over a number of video frames, we attempt to identify signatures pertaining to biological motion. This technique is applied to track scuba divers in underwater domains, typically with the robot swimming behind the diver. The algorithm is able to detect a range of motions, which includes motion directly away from or towards the camera. The motion of the diver relative to the vehicle is then tracked using an Unscented Kalman Filter (UKF), an approach for non-linear estimation. The efficiency of our approach makes it attractive for real-time applications onboard our underwater vehicle, and in future applications we intend to track scuba divers in real-time with the robot. The paper presents an algorithmic overview of our approach, together with experimental evaluation based on underwater video footage.
AB - We present an algorithm for underwater robots to visually detect and track human motion. Our objective is to enable human-robot interaction by allowing a robot to follow behind a human moving in (up to) six degrees of freedom. In particular, we have developed a system to allow a robot to detect, track and follow a scuba diver by using frequencydomain detection of biological motion patterns. The motion of biological entities is characterized by combinations of periodic motions which are inherently distinctive. This is especially true of human swimmers. By using the frequency-space response of spatial signals over a number of video frames, we attempt to identify signatures pertaining to biological motion. This technique is applied to track scuba divers in underwater domains, typically with the robot swimming behind the diver. The algorithm is able to detect a range of motions, which includes motion directly away from or towards the camera. The motion of the diver relative to the vehicle is then tracked using an Unscented Kalman Filter (UKF), an approach for non-linear estimation. The efficiency of our approach makes it attractive for real-time applications onboard our underwater vehicle, and in future applications we intend to track scuba divers in real-time with the robot. The paper presents an algorithmic overview of our approach, together with experimental evaluation based on underwater video footage.
UR - http://www.scopus.com/inward/record.url?scp=84959510786&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959510786&partnerID=8YFLogxK
U2 - 10.15607/rss.2009.v.024
DO - 10.15607/rss.2009.v.024
M3 - Conference contribution
AN - SCOPUS:84959510786
SN - 9780262514637
T3 - Robotics: Science and Systems
SP - 185
EP - 192
BT - Robotics
A2 - Trinkle, Jeff
A2 - Matsuoka, Yoky
A2 - Castellanos, Jose A.
PB - MIT Press Journals
T2 - International Conference on Robotics Science and Systems, RSS 2009
Y2 - 28 June 2009 through 1 July 2009
ER -