Human-Robot Collision Detection Based on Neural Networks

Sharkawy, Abdel-Nasser; Aspragathos, Nikos Α.

doi:10.18178/ijmerr.7.2.150-157

Cited by 45 publications

(50 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, this proves the effectiveness of our proposed method presented in refs. [16,17] which uses signals from the measured joint torques. However, these signals are measured by a joint torque sensor which is not available in the current industrial robots.…”

Section: Nn Designmentioning

confidence: 99%

“…In our previous papers, 16,17 a multilayer feedforward NN was presented for collisions detection applied in 1-DOF and 2-DOF manipulators, respectively. In the latter, 17 the dynamics coupling between the joints of the manipulator was considered and showed that one NN, that couples the inputs from two joints, can be trained for detecting the collisions and identifying the collided link.…”

Section: Related Workmentioning

confidence: 99%

“…1and 2and from ref. [16], if an external force is applied to any link of the manipulator, the joints positions, velocities, and the accelerations are affected; then this effect can be detected in the actuator torques τ and also the measured joint torques τ msr ∈ R 2 . The effect on the actuator torque is lower compared with the effect on the measured joint torque since the controller tries to minimize the effect of the disturbances/external forces.…”

Section: Dynamics Of Joints Motionmentioning

confidence: 99%

“…It should be noted that the "actual joint velocity" stated in ref. [16] is derived, by ourselves, from the numeric differentiation of the measured joint position variables.…”

Section: Nn Designmentioning

confidence: 99%

“…From our previous papers, 16,17 it is deduced that the joints positions and velocities are rich signals, since they contain spikes which represent collisions when external forces are applied to the links of the manipulator during the motion. Also, from Eqs.…”

Section: Nn Designmentioning

confidence: 99%

See 4 more Smart Citations

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

2019

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Nn Designmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Dynamics Of Joints Motionmentioning

confidence: 99%

“…It should be noted that the "actual joint velocity" stated in ref. [16] is derived, by ourselves, from the numeric differentiation of the measured joint position variables.…”

Section: Nn Designmentioning

confidence: 99%

Section: Nn Designmentioning

confidence: 99%

See 3 more Smart Citations