Efficient and Goal-Directed Oscillations in Articulated Soft Robots: the Point-to-Point Case

Introducing elasticity in the mechanical design can endow robots with the ability of performing efficient and effective periodic motions. Yet, devising controllers that can take advantage of such elasticity is still an open challenge. This letter tackles an instance of this general problem, by proposing a control architecture for executing...

Selecting Informative Data Samples for Model Learning Through Symbolic Regression

Continual model learning for nonlinear dynamic systems, such as autonomous robots, presents several challenges. First, it tends to be computationally expensive as the amount of data collected by the robot quickly grows in time. Second, the model accuracy is impaired when data from repetitive motions prevail in the training set and outweigh...