Abstract:
Remote controlling robots without any automated help is difficult due to various limitations. Autocomplete enhances teleoperation by recognizing operator intentions from the input of the user and automating motions when instructed. Such an approach can improve the system performance and reduce the load on the operator. Usually, recognizing operator-intended motions is achieved using pre-trained Deep Learning (DL) models. In this thesis, we introduce personalization to the autocomplete teleoperation framework when new operators take over by customizing the DL model using incremental learning with partial feedback. This approach allows the model to adapt to the specific operator in a relatively short period. Also, we tackle the problem of concept drift that arises in real-life applications; the data distribution of already learned classes may change in unforeseen ways as new observations of these classes come sequentially over time. We create and update an exemplar set using new observations of the classes online so that the model can be trained to adapt to the new observations. Several scenarios have been evaluated to balance the speed of learning with the accuracy of the model. The results demonstrate the effectiveness of the proposed models and their advantage in adapting to the specific operator where the personalization framework reduced the prediction mistakes of the DL model by 46\% while maintaining the advantages of autocomplete by reducing teleoperation speed and enhancing motion smoothness.
