TY - JOUR
T1 - Reinforcement Learning Tracking Control for Robotic Manipulator with Kernel-Based Dynamic Model
AU - Hu, Yazhou
AU - Wang, Wenxue
AU - Liu, Hao
AU - Liu, Lianqing
N1 - Funding Information:
This work was supported in part by the National Key R&D Program of China under Grant 2016YFE0206200 and in part by the Key R&D and Technology Transfer Program of Shenyang Science and Technology Plan under Grant 18-400-6-16.
Publisher Copyright:
© 2019 IEEE.
PY - 2020/9
Y1 - 2020/9
N2 - Reinforcement learning (RL) is an efficient learning approach to solving
control problems for a robot by interacting with the environment to
acquire the optimal control policy. However, there are many challenges
for RL to execute continuous control tasks. In this article, without the
need to know and learn the dynamic model of a robotic manipulator, a
kernel-based dynamic model for RL is proposed. In addition, a new tuple
is formed through kernel function sampling to describe a robotic RL
control problem. In this algorithm, a reward function is defined
according to the features of tracking control in order to speed up the
learning process, and then an RL tracking controller with a kernel-based
transition dynamic model is proposed. Finally, a critic system is
presented to evaluate the policy whether it is good or bad to the RL
control tasks. The simulation results illustrate that the proposed
method can fulfill the robotic tracking tasks effectively and achieve
similar and even better tracking performance with much smaller inputs of
force/torque compared with other learning algorithms, demonstrating the
effectiveness and efficiency of the proposed RL algorithm.
AB - Reinforcement learning (RL) is an efficient learning approach to solving
control problems for a robot by interacting with the environment to
acquire the optimal control policy. However, there are many challenges
for RL to execute continuous control tasks. In this article, without the
need to know and learn the dynamic model of a robotic manipulator, a
kernel-based dynamic model for RL is proposed. In addition, a new tuple
is formed through kernel function sampling to describe a robotic RL
control problem. In this algorithm, a reward function is defined
according to the features of tracking control in order to speed up the
learning process, and then an RL tracking controller with a kernel-based
transition dynamic model is proposed. Finally, a critic system is
presented to evaluate the policy whether it is good or bad to the RL
control tasks. The simulation results illustrate that the proposed
method can fulfill the robotic tracking tasks effectively and achieve
similar and even better tracking performance with much smaller inputs of
force/torque compared with other learning algorithms, demonstrating the
effectiveness and efficiency of the proposed RL algorithm.
KW - Kernel function
KW - reinforcement learning (RL)
KW - reward function
KW - robotics tracking control
UR - http://www.scopus.com/inward/record.url?scp=85090252250&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2019.2945019
DO - 10.1109/TNNLS.2019.2945019
M3 - Journal article
C2 - 31689218
AN - SCOPUS:85090252250
SN - 2162-237X
VL - 31
SP - 3570
EP - 3578
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 9
M1 - 8890006
ER -