Context
Inverse kinematics of robotic manipulators can be complex to determine analitically. Inverse kinematics are extremelly important, as they allow us to determine the position of the robot joints needed to position the robot end-effector at a certain point in space. But, direct kinematics are much simpler to determine. To obtain the shared dataset, direct kinematics of a IRB 120 robotic manipulator have been determined. This allows us to use robot coordinates in the joint-coordinate space (the angles of each individual robot joint) to determine the tool-coordinate space (x, y, z with the origin in the base of the robotic manipulator).
For more details please refer to papers in "Citations" section
Citations
- Baressi Šegota S, Anđelić N, Mrzljak V, Lorencin I, Kuric I, Car Z. Utilization of multilayer perceptron for determining the inverse kinematics of an industrial robotic manipulator. International Journal of Advanced Robotic Systems. 2021 Aug 13;18(4):1729881420925283.
- Car Z, Baressi Šegota S, Anđelić N, Lorencin I, Musulin J, Štifanić D, Mrzljak V. Determining Inverse Kinematics of a Serial Robotic Manipulator Through the Use of Genetic Programming Algorithm. 8th International Congress of the Serbian Society of Mechanics. 2021 July 21.
We kindly ask you to cite at least one of the papers in any research based on this dataset!
Content
The data is generated by uniformely randomly generating values of joints within possible ranges (please refer to "IRB 120 Product Manual" by ABB) for each of the six joints of the robotic manipulator - in radians. With these values generated, the direct kinematic equations are used to determine the x, y, and z coordinate for the given joint coordinates. This pair of vectors constitutes a single datapoint, while the entire dataset consists of 15,000 datapoints generated in this manner.
Acknowledgements
This research was (partly) supported by the CEEPUS network CIII-HR-0108, European Regional Development Fund under the grant KK.01.1.1.01.0009 (DATACROSS), project CEKOM under the grant KK.01.2.2.03.0004, CEI project “COVIDAi” (305.6019-20), University of Rijeka scientific grant uniri-tehnic-18-275-1447.
Inspiration
We have already performed research in regression based on the dataset using Multilayer Perceptron and Genetic Programming (please see the "Citations" section of this document) - can you achieve better results? Or compare and contrast with a novel regression method? We're looking forward to your work!