Multiplierless multilayer feedforward neural network design suitable for continuous input-output mapping

1993 ◽  
Vol 29 (14) ◽  
pp. 1259 ◽  
Author(s):  
H.K. Kwan ◽  
C.Z. Tang
Keyword(s):  
Neural Network ◽  
Network Design ◽  
Feedforward Neural Network ◽  
Input Output ◽  
Output Mapping ◽  
Multilayer Feedforward Neural Network ◽  
Continuous Input

Neural Network Design for Manipulator Collision Detection Based Only on the Joint Position Sensors

Robotica ◽  
2019 ◽  
Vol 38 (10) ◽  
pp. 1737-1755 ◽  
Author(s):  
Abdel-Nasser Sharkawy ◽  
Panagiotis N. Koustoumpardis ◽  
Nikos Aspragathos
Keyword(s):  
Neural Network ◽  
Network Design ◽  
Collision Detection ◽  
Industrial Robot ◽  
Feedforward Neural Network ◽  
Joint Position ◽  
Coupled Dynamics ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Multilayer Feedforward Neural Network

SUMMARYIn this paper, a multilayer feedforward neural network (NN) is designed and trained, for human–robot collisions detection, using only the intrinsic joint position sensors of a manipulator. The topology of one NN is designed considering the coupled dynamics of the robot and trained, with and without external contacts, by Levenberg–Marquardt algorithm to detect unwanted collisions of the human operator with the manipulator and the link that is collided. The proposed approach could be applied to any industrial robot, where only the joint position signals are available. The designed NN is compared quantitatively and qualitatively with an NN, where both the intrinsic joint position and the torque sensors of the manipulator are used. The proposed method is evaluated experimentally with the KUKA LWR manipulator, which is considered as an example of the collaborative robots, using two of its joints in a planar horizontal motion. The results illustrate that the developed system is efficient and fast to detect the collisions and identify the collided link.

Sign in / Sign up

Export Citation Format

Share Document