TY - GEN
T1 - Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks
AU - Katyal, Kapil
AU - Wang, I. Jeng
AU - Burlina, Philippe
PY - 2017/8/22
Y1 - 2017/8/22
N2 - This work leverages Deep Reinforcement Learning (DRL) to make robotic control immune to changes in the robot manipulator or the environment and to perform reaching, collision avoidance and grasping without explicit, prior and fine knowledge of the human arm structure and kinematics, without careful hand-eye calibration, solely based on visual/retinal input, and in ways that are robust to environmental changes. We learn a manipulation policy which we show takes the first steps toward generalizing to changes in the environment and can scale and adapt to new manipulators. Experiments are aimed at a) comparing different DCNN network architectures b) assessing the reward prediction for two radically different manipulators and c) performing a sensitivity analysis comparing a classical visual servoing formulation of the reaching task with the proposed DRL method.
AB - This work leverages Deep Reinforcement Learning (DRL) to make robotic control immune to changes in the robot manipulator or the environment and to perform reaching, collision avoidance and grasping without explicit, prior and fine knowledge of the human arm structure and kinematics, without careful hand-eye calibration, solely based on visual/retinal input, and in ways that are robust to environmental changes. We learn a manipulation policy which we show takes the first steps toward generalizing to changes in the environment and can scale and adapt to new manipulators. Experiments are aimed at a) comparing different DCNN network architectures b) assessing the reward prediction for two radically different manipulators and c) performing a sensitivity analysis comparing a classical visual servoing formulation of the reaching task with the proposed DRL method.
UR - http://www.scopus.com/inward/record.url?scp=85030230222&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85030230222&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2017.71
DO - 10.1109/CVPRW.2017.71
M3 - Conference contribution
AN - SCOPUS:85030230222
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 490
EP - 491
BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PB - IEEE Computer Society
T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Y2 - 21 July 2017 through 26 July 2017
ER -