Here in this project we are trying to find inverse kinematics solution for PUMA560 using vanilla flavoured deep neural network. Eventhough the closed form solution exist for PUMA-560 we will be finding it using deep neural network to proove that DNN(deep neural network) can be used to find inverse kinematic solution of a robotic arm
There are two set of codes one where the data is generated using conventional methods and the other where the data is generated using forward kinematics with joint restraints
The first code There is a matlab code that gives inverse solution and writes it into a csv file using the piper solution for inverse kinematics for a 6R robot. This data generated will be used to train the model. The solution given by the matlab code is singular and if inverse kinematic solution does not exist it doesn't add it to the csv file. In this traied model the solution is biased towards the solution generated by the matlab code
- Install dependencies:
pip install -r requirements.txt
This project is licensed under the MIT License. See the LICENSE file for details.
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.