Adaptive control of robotic servo system with friction compensation

D Zheng; J Na; X M Ren; G Herrmann; S Longo

Adaptive control of robotic servo system with friction compensation

D Zheng, J Na, X M Ren, G Herrmann, S Longo

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper presents the implementation (real time and simulation) of a model-free Q-learning based discrete model reference compliance controller for a humanoid robot arm. The Reinforcement learning (RL) scheme uses a recently developed Q-learning scheme to develop an optimal policy on-line. The RL Cartesian (x and y) tracking controller with model reference compliance was implemented using two links (shoulder flexion and elbow flexion joints) of the right arm of the humanoid Bristol-Elumotion-Robotic-Torso II (BERT II) torso.

Original language	English
Pages	285-290
Number of pages	6
Publication status	Published - Sept 2011
Event	5th International Conference on Robotics, Automation and Mechatronics (RAM) - Qingdao, China Duration: 17 Sept 2011 → 19 Sept 2011

Conference

Conference	5th International Conference on Robotics, Automation and Mechatronics (RAM)
Country/Territory	China
City	Qingdao
Period	17/09/11 → 19/09/11

Keywords

Adaptive control
friction compensation
Neural network
robotic turntable

Cite this

@conference{d8cc02dc83c546589d8df32243d9b7e5,

title = "Adaptive control of robotic servo system with friction compensation",

abstract = "This paper presents the implementation (real time and simulation) of a model-free Q-learning based discrete model reference compliance controller for a humanoid robot arm. The Reinforcement learning (RL) scheme uses a recently developed Q-learning scheme to develop an optimal policy on-line. The RL Cartesian (x and y) tracking controller with model reference compliance was implemented using two links (shoulder flexion and elbow flexion joints) of the right arm of the humanoid Bristol-Elumotion-Robotic-Torso II (BERT II) torso.",

keywords = "Adaptive control, friction compensation, Neural network, robotic turntable",

author = "D Zheng and J Na and Ren, {X M} and G Herrmann and S Longo",

note = "Conference Organiser: IEEE; 5th International Conference on Robotics, Automation and Mechatronics (RAM) ; Conference date: 17-09-2011 Through 19-09-2011",

year = "2011",

month = sep,

language = "English",

pages = "285--290",

}

TY - CONF

T1 - Adaptive control of robotic servo system with friction compensation

AU - Zheng, D

AU - Na, J

AU - Ren, X M

AU - Herrmann, G

AU - Longo, S

N1 - Conference Organiser: IEEE

PY - 2011/9

Y1 - 2011/9

N2 - This paper presents the implementation (real time and simulation) of a model-free Q-learning based discrete model reference compliance controller for a humanoid robot arm. The Reinforcement learning (RL) scheme uses a recently developed Q-learning scheme to develop an optimal policy on-line. The RL Cartesian (x and y) tracking controller with model reference compliance was implemented using two links (shoulder flexion and elbow flexion joints) of the right arm of the humanoid Bristol-Elumotion-Robotic-Torso II (BERT II) torso.

AB - This paper presents the implementation (real time and simulation) of a model-free Q-learning based discrete model reference compliance controller for a humanoid robot arm. The Reinforcement learning (RL) scheme uses a recently developed Q-learning scheme to develop an optimal policy on-line. The RL Cartesian (x and y) tracking controller with model reference compliance was implemented using two links (shoulder flexion and elbow flexion joints) of the right arm of the humanoid Bristol-Elumotion-Robotic-Torso II (BERT II) torso.

KW - Adaptive control

KW - friction compensation

KW - Neural network

KW - robotic turntable

M3 - Paper

SP - 285

EP - 290

T2 - 5th International Conference on Robotics, Automation and Mechatronics (RAM)

Y2 - 17 September 2011 through 19 September 2011

ER -

Adaptive control of robotic servo system with friction compensation

Abstract

Conference

Keywords

Fingerprint

Cite this