Dynamics Estimation Using Recurrent Neural Network
This work addresses a specific robotics task (pouring) but is incremental, as it applies existing RNN methods to a new dataset without broad generalization.
The paper tackles the problem of dynamic estimation in robotics, specifically predicting water amount changes during pouring motions using recurrent neural networks, achieving a loss of 4.5920 on test data with similar cup dimensions.
There is a plenty of research going on in field of robotics. One of the most important task is dynamic estimation of response during motion. One of the main applications of this research topics is the task of pouring, which is performed daily and is commonly used while cooking. We present an approach to estimate response to a sequence of manipulation actions. We are experimenting with pouring motion and the response is the change of the amount of water in the pouring cup. The pouring motion is represented by rotation angle and the amount of water is represented by its weight. We are using recurrent neural networks for building the neural network model to train on sequences which represents 1307 trails of pouring. The model gives great results on unseen test data which does not too different with training data in terms of dimensions of the cup used for pouring and receiving. The loss obtained with this test data is 4.5920. The model does not give good results on generalization experiments when we provide a test set which has dimensions of the cup very different from those in training data.