抄録
This report describes a head position estimation method for a variety of recumbent positions for a care robot. First, the robot detects a falling person using a laser range finder and moves there for getting a point cloud. The obtained point cloud is matched with those with head positions in the database using the ICP (iterative closest point) algorithm for estimating the current head position. Next, extracted head positions with matching scores above a threshold are clustered, and the center of the cluster with the highest accumulated scores is determined to he the head position. Finally, robot moves to the position near the estimated final head position and measures the carbon dioxide level to check if the person is breathing. We validated that the proposed system can detect the human vital sign for various recumbent positions.
