Multi-Step Prediction of Dynamic Systems with Recurrent Neural Networks
This work addresses multi-step prediction accuracy for dynamic systems like aerial vehicles, which is incremental as it builds on existing RNN methods with a novel initialization and hybrid modeling approach.
The paper tackles the state initialization problem for training RNNs in multi-step prediction of dynamic systems, specifically for aerial vehicles like a helicopter and quadrotor, showing that an NN-based initialization method outperforms state-of-the-art approaches and a hybrid model achieves predictions within 9 cm/s and 0.12 rad/s of measured velocities over 1.9 seconds with 99% confidence.
Recurrent Neural Networks (RNNs) can encode rich dynamics which makes them suitable for modeling dynamic systems. To train an RNN for multi-step prediction of dynamic systems, it is crucial to efficiently address the state initialization problem, which seeks proper values for the RNN initial states at the beginning of each prediction interval. In this work, the state initialization problem is addressed using Neural Networks (NNs) to effectively train a variety of RNNs for modeling two aerial vehicles, a helicopter and a quadrotor, from experimental data. It is shown that the RNN initialized by the NN-based initialization method outperforms the state of the art. Further, a comprehensive study of RNNs trained for multi-step prediction of the two aerial vehicles is presented. The multi-step prediction of the quadrotor is enhanced using a hybrid model which combines a simplified physics-based motion model of the vehicle with RNNs. While the maximum translational and rotational velocities in the quadrotor dataset are about 4 m/s and 3.8 rad/s, respectively, the hybrid model produces predictions, over 1.9 second, which remain within 9 cm/s and 0.12 rad/s of the measured translational and rotational velocities, with 99\% confidence on the test dataset