Abstract: The present disclosure relates to a 4D printed gripper with flexible finger joints and a trajectory tracking control method thereof. The 4D printed gripper with flexible finger joints includes: a palm unit and five finger units connected to the palm unit, where each finger unit includes two flexible finger joints and two phalanges; each flexible finger joint is divided into one upper layer and one lower layer of liquid crystal elastomer (LCE), and each LCE is used to implement a bidirectional bending movement of the finger unit. The present disclosure can precisely control the gripper with flexible finger joints.

Abstract: Systems and methods for updating a classification model of a neural network. The methods include selecting, as a set of landmarks, a limited number of data from a set of historical data used to train a classification model. Additionally, the methods generate new training data from recently collected data. Further, the methods update the classification model with the new training data and the set of landmarks to obtain an updated classification model having a loss function configured to capture similarities in the new training data and remember similarities in the historical data represented by the set of landmarks within a predefined tolerance.

Abstract: Systems and methods for updating a classification model of a neural network are provided. The methods include selecting, as a set of landmarks, a limited number of data from a set of historical data used to train a classification model. Additionally, the methods generate new training data from recently collected data. Further, the methods update the classification model with the new training data and the set of landmarks to obtain an updated classification model having a loss function configured to capture similarities in the new training data and remember similarities in the historical data represented by the set of landmarks within a predefined tolerance.