Human Motion Prediction using Semi-adaptable Neural Networks
This work addresses the need for robots to safely and efficiently collaborate with humans by enhancing motion prediction, though it is incremental as it builds on existing deep learning approaches with adaptation and uncertainty quantification.
The paper tackles the problem of predicting human motion for human-robot interaction by proposing a semi-adaptable neural network that adapts to time-varying behaviors and provides uncertainty bounds, resulting in significant improvements in prediction accuracy and computational efficiency over state-of-the-art methods.
Human motion prediction is an important component to facilitate human robot interaction. Robots need to accurately predict human's future movement in order to safely plan its own motion trajectories and efficiently collaborate with humans. Many recent approaches predict human's movement using deep learning methods, such as recurrent neural networks. However, existing methods lack the ability to adapt to time-varying human behaviors, and many of them do not quantify uncertainties in the prediction. This paper proposes an approach that uses a semi-adaptable neural network for human motion prediction, and provides uncertainty bounds of the predictions in real time. In particular, a neural network is trained offline to represent the human motion transition model, and then recursive least square parameter adaptation algorithm (RLS-PAA) is adopted for online parameter adaptation of the neural network and for uncertainty estimation. Experiments on several human motion datasets verify that the proposed method significantly outperforms the state-of-the-art approach in terms of prediction accuracy and computation efficiency.