# AHC

**Repository Path**: AGIROS_Team/ahc

## Basic Information

- **Project Name**: AHC
- **Description**: No description available
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2025-09-29
- **Last Updated**: 2026-03-13

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## Overview
This repository contains the code implementation and video demonstration of the paper `Agile Hauler Curriculum: Learning High-Speed Locomotion for Robots
under Demanding Payloads`, which proposes a new curriculum learning method (**Agile Hauler Curriculum, AHC**) to help robots achieve agile locomotion under high loads. 

More detailed information about AHC and the experiments on real-world deployment are introduced in the video below.
<div align="center">
  <video src="https://gitee.com/AGIROS_Team/ahc/raw/master/video.mp4" controls width="600"></video>
</div>


## Requirements
* miniconda
* pytorch 1.10 with cuda-11.3
* Isaac Gym
* Nvidia GPU with at least 8GB of VRAM

## Build Environments

### Create new conda environment and activate
```bash
conda create env -n ahc python=3.8
conda activate ahc
```

### Install pytorch 1.10 with cuda-11.3:
```bash
pip3 install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio==0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
```
### Install Isaac Gym
1.  Download and install Isaac Gym Preview 4 from https://developer.nvidia.com/isaac-gym
2. Unzip file.
    ```bash
    tar -xf IsaacGym_Preview_4_Package.tar.gz
    ```
3. Insatll python package.
    ```bash
    cd isaacgym/python 
    pip install -e .
    ```
4. Verify the installation by try running an example.
    ```bash
    python examples/1080_balls_of_solitude.py
    ```

### Train and Play
Clone this repository and install:
```bash
git clone https://gitee.com/AGIROS_Team/ahc.git
cd AHC
pip install -e .
```

Start training:
```bash
python scripts/train.py
```
the log, video and  checkpoints files are saved in `/run` dir during training.

Evaluate policy:
```bash
python scripts/play.py
```