Please refer to instructions.md for in-depth instructions on how to run the code and replicate our experiments.
Represented by x (lateral) and z (forward) displacements of 6 closest (sorted by z displacement) Aruco markers relative to robot position.
Linear Speed = Constant 0.5 m/s for both models.
DQN - Discrete Action Space +/- 0.2 rad/s rotatational speed. TD3 - Continuous Action Space from +0.4 rad/s to -0.4 rad/s rotational speed.
Both models trained and tested in simulation. Example of simulation POV of robot shown below.
Results of training:
A video showing the robot executing the tasks during the training process can be found at this youtube link.
If you use either the code or data in your paper, please kindly star this repo and cite our paper Cite this paper as: Coming soon
Please feel free to contact us or open an issue if you have questions or need additional explanations.