AUTHOR=Li Jie , Zhong Junpei , Yang Jingfeng , Yang Chenguang 

TITLE=An Incremental Learning Framework to Enhance Teaching by Demonstration Based on Multimodal Sensor Fusion

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 14 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00055

DOI=10.3389/fnbot.2020.00055

ISSN=1662-5218

ABSTRACT=Though a robot can reproduce the demonstration trajectory from the human demonstrator by teleoperation, there is a certain error between the reproduced trajectory and the desired trajectory. To minimize this error, we propose a multi-modal incremental learning framework based on a teleoperation strategy that can enable the robot to reproduce the demonstration task accurately. The multi-modal demonstration data is collected from two different kinds of sensors in the demonstration phase. Then the Kalman filter (KF) and dynamic time warping (DTW) algorithm are used to data preprocessing for the multiple sensor signals. The KF algorithm is mainly used to fuse sensor data of different modalities, and the DTW algorithm is used to align the data in the same timeline. The preprocessed demonstration data is further trained and learned by the incremental learning network and sent to a Baxter robot for reproducing the task demonstrated by the human. Comparative experiments have been performed to verify the effectiveness of the proposed method.