A Pytorch implementation of Generative Adversarial Network for Heuristics of Sampling-based Path Planning
.
├── assets # Images, results
├── data # Dataset location & data generation
│ ├── movingai
│ ├── map_augmentator.py
│ ├── task_generator.py
│ ├── roi_generator.py
│ ├── rrt.py
│ ├── utils.py
│ └── dataset
├── gan # Scripts for GANs (original & pix2pix)
│ ├── generator.py
│ ├── discriminator.py
│ ├── modules.py
│ ├── checkpoint
│ ├── utils
| | ├── data.py
| | ├── criterion.py
| | ├── metrics.py
| | └── trainer.py
│ └── pix2pix
| ├── blocks.py
| ├── trainer.py
| └── utils.py
├── path # Scripts for pathfinding
│ ├── rrt.py
│ ├── rrt_star.py
│ ├── RRT_updated.py
│ └── RRT_.py
├── train.py # To train GAN from the paper
├── train_pix2pix.py # To tran our Pix2Pix GAN
├── roi_generation.ipynb # To generate ROIs
├── LICENSE
└── README.md
The overall structure of the PathGAN consists of two things:
- RRT* searching algorithm and
- Generative Aversarial Network for promising region generation
Path searching by RRT*
Dataset consists of 10,000 samples (Map
, Point
, ROI
):
- train set (8,000 samples)
- test set (2,000 samples)
GAN | Generated ROI's | mIoU | mDICE | mFID | mIS | # of params * | Checkpoint * |
---|---|---|---|---|---|---|---|
Original (from paper) | Link | 70.2% | 82.0% | 79.7 | 1.019 | 21,231,827 | Link |
Pix2Pix (ours) | Link | 58.1% | 72.2% | 91.2 | 1.017 | 4,170,477 | Link |
*-
of Generator
-
mIoU -
average Intersection over Union
for all 2,000 samples intest set
-
mDICE -
average DICE
for all 2,000 samples intest set
-
mFID -
average Frechet Inception Distance
for all 2,000 samples intest set
-
mIS -
average Inception Score
for all 250 batches (2,000 samples/8 samples per batch) intest set
Original Generator (from paper)
RRT result-->
True ROI -->
Pred ROI -->
True ROI ∩ Pred ROI
Pix2Pix Generator (ours)
RRT result-->
True ROI -->
Pred ROI -->
True ROI ∩ Pred ROI
GAN | Generated ROI's | mIoU | mDICE | mFID | mIS |
---|---|---|---|---|---|
Original (from paper) | Link | 38.4% | 53.8% | 88.1 | 1.014 |
Pix2Pix (ours) | Link | 30.8% | 46.3% | 100.1 | 1.012 |
*-
of Generator
-
mIoU -
average Intersection over Union
for all 699 samples -
mDICE -
average DICE
for all 699 samples -
mFID -
average Frechet Inception Distance
for all 699 samples -
mIS -
average Inception Score
for all 88 batches (699 samples/8 samples per batch)
Original Generator (from paper)
True ROI -->
Pred ROI -->
True ROI ∩ Pred ROI
Pix2Pix Generator (ours)
True ROI -->
Pred ROI -->
True ROI ∩ Pred ROI
This project is licensed under MIT.
- Generative Adversarial Network based Heuristics for Sampling-based Path Planning (arXiv article)
- Dataset (generated)
- MovingAI Dataset
- Results (ROI's) of Original Generator (from paper)
- Results (ROI's) of Pix2Pix Generator (ours)
- MovingAI results (ROI's) of Original Generator (from paper)
- MovingAI results (ROI's) of Pix2Pix Generator (ours)