Generalizable, Scalable, Real-time, End-to-end Local Planner
for Unstructured & Dynamic Environments
The video can be found here.
numpy>=1.24.4
scipy>=1.10.1
pygame>=2.5.2
torch>=2.2.0 # GPU version is recommended
torchaudio>=2.2.0
torchvision>=0.17.0
tensorboard>=2.18.0python play_with_keyboard.pypython play_with_mouse.pyThen, use your mouse to set target points:
python train_ColorDynamic.pyDuring training, the model will be saved in model at a fixed frequency.
After training, you can use the following command to select the best model, where the evaluation results will be saved in Evaluation_result and runs.
python evaluate_and_plot.py
Please refer to the OPCD Navigation System.
To cite this repository in publications:
@article{ColorDynamic,
title={ColorDynamic: Generalizable, Scalable, Real-time, End-to-end Local Planner for Unstructured and Dynamic Environments},
author={Jinghao Xin, Zhichao Liang, Zihuan Zhang, Peng Wang, and Ning Li},
journal={arXiv preprint arXiv:2502.19892},
year={2025}
}