Dataset Description
The data relates to an inverse dynamics problem for a seven degrees-of-freedom
SARCOS anthropomorphic robot arm. The task is to map from a 21-dimensional
input space (7 joint positions, 7 joint velocities, 7 joint accelerations) to
the corresponding 7 joint torques. Usually, the first of those (V22) is used as
the target variable and is therefore set as the default target variable, while
the other 6 joint torques are excluded from the model.
NOTE
This dataset contains only the corresponding training data, as there is data leakage between
the original training and test data. This was described in
[this article](https://www.datarobot.com/blog/running-code-and-failing-models/) by Rajiv Shah.
Related Studies
* LWPR: An O(n) Algorithm for Incremental Real Time Learning in High
Dimensional Space, S. Vijayakumar and S. Schaal, Proc ICML 2000, 1079-1086
* (2000). Statistical Learning for Humanoid Robots, S. Vijayakumar, A.
D'Souza, T. Shibata, J. Conradt, S. Schaal, Autonomous Robot, 12(1) 55-69
* (2002) Incremental Online Learning in High Dimensions S. Vijayakumar, A.
D'Souza, S. Schaal, Neural Computation 17(12) 2602-2634 (2005)
* (2019) Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning,
Sahand Rezaei-Shoshtari, David Meger, Inna Sharf, https://arxiv.org/pdf/1910.02291.pdf
* (2019) TabNet: Attentive Interpretable Tabular Learning,
Sercan Oe. Arik, Tomas Pfister, https://arxiv.org/pdf/1908.07442.pdf
Citation
LWPR: An O(n) Algorithm for Incremental Real-Time Learning in High Dimensional Space, S. Vijayakumar and S. Schaal, Proc ICML 2000, 1079-1086 (2000).
The data was obtained from: http://www.gaussianprocess.org/gpml/data/