TY - GEN
T1 - Detecting features of tools, objects, and actions from effects in a robot using deep learning
AU - Saito, Namiko
AU - Kim, Kitae
AU - Murata, Shingo
AU - Ogata, Tetsuya
AU - Sugano, Shigeki
N1 - Funding Information:
This work was supported in part by a JSPS Grant-in-Aid for Scientific Research (S) (No. 25220005), a JST CREST Grant (No. JPMJCR15E3), and the “Fundamental Study for Intelligent Machine to Coexist with Nature” program of the Research Institute for Science and Engineering, Waseda University, Japan.
Funding Information:
This work was supported in part by a JSPS Grant- in-Aid for Scientific Research (S) (No. 25220005), a JST CREST Grant (No. JPMJCR15E3), and the Fundamen- tal Study for Intelligent Machine to Coexist with Nature" program of the Research Institute for Science and Engi- neering, Waseda University, Japan.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/9
Y1 - 2018/9
N2 - We propose a tool-use model that can detect the features of tools, target objects, and actions from the provided effects of object manipulation. We construct a model that enables robots to manipulate objects with tools, using infant learning as a concept. To realize this, we train sensory-motor data recorded during a tool-use task performed by a robot with deep learning. Experiments include four factors: (1) tools, (2) objects, (3) actions, and (4) effects, which the model considers simultaneously. For evaluation, the robot generates predicted images and motions given information of the effects of using unknown tools and objects. We confirm that the robot is capable of detecting features of tools, objects, and actions by learning the effects and executing the task.
AB - We propose a tool-use model that can detect the features of tools, target objects, and actions from the provided effects of object manipulation. We construct a model that enables robots to manipulate objects with tools, using infant learning as a concept. To realize this, we train sensory-motor data recorded during a tool-use task performed by a robot with deep learning. Experiments include four factors: (1) tools, (2) objects, (3) actions, and (4) effects, which the model considers simultaneously. For evaluation, the robot generates predicted images and motions given information of the effects of using unknown tools and objects. We confirm that the robot is capable of detecting features of tools, objects, and actions by learning the effects and executing the task.
KW - Cognitive Robotics
KW - Development of Infants
KW - Neural Network
KW - Tool-use
UR - http://www.scopus.com/inward/record.url?scp=85070383722&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85070383722&partnerID=8YFLogxK
U2 - 10.1109/DEVLRN.2018.8761029
DO - 10.1109/DEVLRN.2018.8761029
M3 - Conference contribution
AN - SCOPUS:85070383722
T3 - 2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2018
SP - 91
EP - 96
BT - 2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - Joint 8th IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2018
Y2 - 16 September 2018 through 20 September 2018
ER -