DS.01.ULUND.TransientDetection

Dataset used for evaluation of a recurrent neural network (RNN) for recognition of transients, in order to detect events during robotic assembly. Inputs are robot joint torque data. Outputs are probabilities that the event is occurring, as estimated by the RNN. Possible to use for detection models other than RNNs.

Used as experimental results in the paper Martin Karlsson, Anders Robertsson, Rolf Johansson, Detection and Control of Contact Force Transientsin Robotic Manipulation without a Force Sensor, by to be presented at ICRA, Brisbane, May 2018.