Data-driven calibration of RAVEN-II surgical robot with ground truth joint positions

Accurate joint position estimation is crucial for the control of cable-driven laparoscopic surgical robots like the RAVEN-II. However, any slack and stretch in the cable can lead to errors in kinematic estimation, complicating precise control. This work proposes an efficient data-driven calibration method, requiring no additional sensors post-training. This dataset was collected from a RAVEN-II surgical robot, including different calibration trajectories, 6-hour continuous idle, unloaded, and loaded operating. Ground truth joint positions for positional joints are also collected from high-resolution optical encoders., Please refer to our paper \"Efficient Data-driven Joint-level Calibration of Cable-driven Surgical Robots\" for more details.
This data set is collected on a RAVEN-II surgical robot. Only the left arm of the robot was used.
Ground truth of joint positions Avago Technologies AEDA- 3300 encoders were installed on the rotational joints 1 and 2, with a resolution of 80000 PPR. Mercury II 1600 was installed on the translational joint 3, with a resolution of 5 µm. The external encoders were registered during the initialization of RAVEN-II to register the offsets. 
Robot states \"ravenstate\" are also recorded, which includes time, pose, velocity, force, torque, and so on.
The robot states and ground truth joint positions are synchronized and the frequency is around 30 Hz.
This dataset is collected for data-driven calibration of cable-driven surgical robots. Training trajectories are zig-zag trajectories for their even distribution in the workspace, while testing trajectories are random trajectori..., , # Data-driven Calibration of RAVEN-II Surgical Robot with Ground Truth Joint Positions

[https://doi.org/10.5061/dryad.tqjq2bw84](https://doi.org/10.5061/dryad.tqjq2bw84)

## Description of the data and file structure

Please do not hesitate to contact Haonan Peng ([[e-mail]](mailto:[e-mail])) if you need any help using this dataset.

All code about utilizing this dataset, including neural networks and regressions can be found at GitHub repo: 

[https://github.com/HaonanPeng/Efficient-Data-driven-Joint-level-Calibration-of-Cable-driven-Surgical-Robots](https://github.com/HaonanPeng/Efficient-Data-driven-Joint-level-Calibration-of-Cable-driven-Surgical-Robots)

as well as index, preprocessing.

Each recording .zip file contains training and testing trajectories as .csv files. \"rand1200\" in the file name indicates this is a random trajectory, otherwise indicating a zig-zag trajectory. \"x\", \"y\", or \"z\" in the file name indicates the direction of zig-zag traj...