# p_NTFileds

**Repository Path**: wuyixing2024/ntf

## Basic Information

- **Project Name**: p_NTFileds
- **Description**: p_ntfields
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2023-08-04
- **Last Updated**: 2023-08-15

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# p_NTFields

picture in gibson dataset:





## Introduction

This repository is the unofficial implementation of "pNTFields: Progressive learning for Neural Time Fields for Physics-Informed Robot Motion Planning". 

## Installation

Clone the repository into your local machine:

```
git clone https://github.com/ruiqini/NTFields --recursive
```

Install requirements:

```setup
conda env create -f NTFields_env.yml
conda activate NTFields
```

Download datasets and pretrained models, exact and put `datasets/` `Experiments/` to the repository directory:

[Datasets and pretrained model](https://drive.google.com/file/d/140W0iOJOwA-nku831mQgPIGGQmXAKtrz/view?usp=share_link)

>The repository directory should look like this:
```
NTFields/
├── datasets/
│   ├── arm/    # 4DOF and 6DOF robot arm, table environment
│   ├── c3d/    # C3D environment
│   ├── gibson/ # Gibson environment
│   └── test/   # box and bunny environment
├── Experiments
│   ├── 4DOF/   # pretrained model for 4DOF arm
│   └── Gib/    # pretrained model for Gibson
•   •   •
•   •   •
```

## Pre-processing

To prepare the Gibson data, run:

```
python dataprocessing/preprocess.py --config configs/gibson.txt
```

To prepare the arm data, run:

```
python dataprocessing/preprocess.py --config configs/arm.txt
```

## Testing

To visualize our path in a Gibson environment, run:

```eval
python test/gib_plan.py 
```

To visualize our path in the 4DOF arm environment, run:

```eval
python test/arm_plan_p.py 
```

To sample random starts and goals in Gibson environments, run:

```eval
python test/sample_sg.py 
```

To show our statistics result in Gibson environments, run:

```eval
python test/gib_stat.py 
```

## Training

To train our model in a Gibson environment, run:

```train
python train/train_gib_p.py
```

To train our model in the 4DOF arm environment, run:

```train
python train/train_arm_p.py 
```