In 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.

In this paper, two methods are proposed and implemented for collision detection between the robot and a human based on fuzzy identification and time series modelling. Both methods include a collision detection system for each joint of the robot that is trained to approximate the external torque. In addition, the proposed methods are able to detect the occurrence of a collision, the link that collided and to some extent the magnitude of the collision without using the explicit model of the robot. Since the speed of the detection is of critical importance for mitigating the danger, attention is paid to recognise a collision as soon as possible. Experimental results conducted with a KUKALWR manipulator using two joints in planar motion, verify the validity on both methods.