Predicting human motion intention for pHRI assistive control

TL;DR

This paper presents a method using LSTM neural networks with transfer learning to accurately predict human motion intentions in pHRI, improving assistive robot control across different users and objects.

Contribution

It introduces an iterative training and transfer learning approach for intention prediction, enhancing adaptability and reducing prediction error in human-robot interaction.

Findings

Iterative training reduces prediction error.

Transfer learning adapts the model to new users and objects.

Enhanced controller improves pHRI performance.

Abstract

This work addresses human intention identification during physical Human-Robot Interaction (pHRI) tasks to include this information in an assistive controller. To this purpose, human intention is defined as the desired trajectory that the human wants to follow over a finite rolling prediction horizon so that the robot can assist in pursuing it. This work investigates a Recurrent Neural Network (RNN), specifically, Long-Short Term Memory (LSTM) cascaded with a Fully Connected layer. In particular, we propose an iterative training procedure to adapt the model. Such an iterative procedure is powerful in reducing the prediction error. Still, it has the drawback that it is time-consuming and does not generalize to different users or different co-manipulated objects. To overcome this issue, Transfer Learning (TL) adapts the pre-trained model to new trajectories, users, and co-manipulated objects by freezing the LSTM layer and fine-tuning the last FC layer, which makes the procedure faster. Experiments show that the iterative procedure adapts the model and reduces prediction error. Experiments also show that TL adapts to different users and to the co-manipulation of a large object. Finally, to check the utility of adopting the proposed method, we compare the proposed controller enhanced by the intention prediction with the other two standard controllers of pHRI.