TY - GEN
T1 - Inferring guidance information in cooperative human-robot tasks
AU - Berger, Erik
AU - Vogt, David
AU - Haji-Ghassemi, Nooshin
AU - Jung, Bernhard
AU - Amor, Heni Ben
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2015/2/3
Y1 - 2015/2/3
N2 - In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.
AB - In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.
UR - http://www.scopus.com/inward/record.url?scp=84937855652&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84937855652&partnerID=8YFLogxK
U2 - 10.1109/HUMANOIDS.2013.7029966
DO - 10.1109/HUMANOIDS.2013.7029966
M3 - Conference contribution
AN - SCOPUS:84937855652
T3 - IEEE-RAS International Conference on Humanoid Robots
SP - 124
EP - 129
BT - 2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013
PB - IEEE Computer Society
T2 - 2013 13th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2013
Y2 - 15 October 2013 through 17 October 2013
ER -