Positional data of soft robots with diverse actuations types

Soft robots are a promising area of research due to their potential use in various applications. Learning the kinematics of soft robots is crucial for their advancement and application. This dataset is designed to provide training data for the development of machine learning models that can learn the kinematics of soft robots with different actuation types. The dataset includes the positional data of three soft robots, specifically the simulated pneumatic soft robot, simulated tendon-driven soft robot, and real-world tendon-driven soft robot. The paired data for each robot is provided in ".json" format, and each file contains the paired data from different soft robots. The actuation commands in this dataset are sorted by L1 norm and divided into interpolation and extrapolation data. Interpolation data is used to estimate the positional data between the actuation commands, while extrapolation data is used to predict the positional data beyond the range of actuation commands. This allows for the training of machine learning models that can accurately predict the kinematics of soft robots in a variety of scenarios. The dataset can be used to develop machine learning models that can learn the kinematics of soft robots with various actuation types. It can also be used to evaluate the performance of different machine-learning algorithms on this task. The dataset can contribute to the advancement of the field of soft robotics and can be of interest to researchers, engineers, and students working in the field of robotics and machine learning.