walk-these-ways-go2/README.md

# Sim-to-Real project on Unitree Go2

## Overview 

This repository is forked from [walk-these-ways](https://github.com/Improbable-AI/walk-these-ways), which is a Go1 Sim-to-Real Locomotion Starter Kit. It seems that [walk-these-ways](https://github.com/Improbable-AI/walk-these-ways) can be untilized on Unitree [A1](https://github.com/fan-ziqi/dog_rl_deploy) with simple modifications, since those robots are base on [unitree-legged-sdk](https://github.com/unitreerobotics/unitree_legged_sdk). 

However, the brand-new architecture [unitree-sdk2 ](https://github.com/unitreerobotics/unitree_sdk2)is not base on UDP anymore, so this project aims to train and deploy walk-these-ways on Unitree Go2 by modifying SDK interfaces.

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

---
## Train
Clone this repository:

``` bash
git clone https://github.com/Teddy-Liao/walk-these-ways-go2.git
```

Start training: 
```bash
python scripts/train.py
```

For convenience, [urdf file path](go1_gym/envs/go1/go1_config.py) is directly swtitched from `go1.urdf` to [`go2.urdf`](https://support.unitree.com/home/zh/developer/rl_example).

Play the model:
```bash
python scripts/play.py
```
![Alt text](assets/go2_training.jpg)

Go2 pretrained model is provided in [./runs](runs/gait-conditioned-agility/pretrain-go2), you can choose whether to use provide pretrained model by modifying the label line `label = "gait-conditioned-agility/pretrain-go2/train"` to your own trained model.

### Known Issues
* `flip_visual_attachments` in [go1_config](go1_gym/envs/go1/go1_config.py) should be set to `True`, otherwise errors would occur when visualizing.
* To change configuration parameters of env or the robot, you should modify parameters in [go1_config](go1_gym/envs/go1/go1_config.py), not in [legged_robot_config](go1_gym/envs/base/legged_robot_config.py)


---
## Deploy
Trained policy is only supported to be deployed through your PC or laptop now, because I am not familiar with Jetson Orin, and hope I can fix it and deploy on Jetson Orin.

### Requirements
#### Install LCM
Since [walk-these-ways](https://github.com/Improbable-AI/walk-these-ways) implement an interface based on Lightweight Communications and Marshalling ([LCM](https://github.com/lcm-proj/lcm)) to pass sensor data, motor commands, and joystick state between their code and the low-level control SDK provided by Unitree, LCM should be installed firstly in your PC or laptlop.

Clone LCM repository to the path you usually place installed softwares, then install LCM:
```bash
git clone https://github.com/lcm-proj/lcm.git
mkdir build
cd build
cmake ..
make
sudo make install
```

#### Build unitree_sdk2
unitree_sdk2 has been inclued in `go2_gym_deploy/unitree_sdk2_bin/library/unitree_sdk2`,  you can also clone from [Unitree Robotics](https://github.com/unitreerobotics/unitree_sdk2) to make sure the sdk is updated version.

```bash
cd go2_gym_deploy
```
Delete build file
```bash
rm -r build
```
Install and build:
```bash
sudo ./install.sh
mkdir build
cd build
cmake ..
make
```

### Build lcm_position_go2
`go2_gym_deploy/unitree_sdk2_bin/lcm_position_go2.cpp` is the core file of this project, which is similar to `lcm_position.cpp` in [walk-these-ways](https://github.com/Improbable-AI/walk-these-ways), but replace unitree_legged_sdk with unitree_sdk2.

Build lcm_position_go2 and generate runfile `lcm_position_go2`
```bash
cd go2_gym_deploy
rm -r build
mkdir build
cd build
cmake ..
make -j
```

All LCM messages in `go2_gym_deploy/lcm_types` are set as the same format shown in [walk-these-ways](https://github.com/Improbable-AI/walk-these-ways) to ensure successful connection with python files.

`xxx_lcmt.hpp` files are generated by:
```bash
lcm-gen -x xxx.lcm
```

### Verify connection
Connect your PC/Laptop with Go2 robot with ethernet cable and check connection by:
```bash
ping 192.168.123.161
```

Check the network interface address, and copy the network interface address.
```bash
ifconfig
```
If error occurs, please check [Unitree Support](https://support.unitree.com/home/zh/developer/Quick_start) for details.

### Test communication between LCM and unitree_sdk2
```bash
cd go2_gym_deploy/build
sudo ./lcm_position_go2 enx10086
```
Aeplace `enx10086` with your own network interface address. According to the messages shown in terminal, press `Enter` for several times and the communication between LCM and unitree_sdk2 will set up.

This command will automatically shut down Unitree sport_mode Service and set the robot to LOW-LEVEL. Please make sure This will Go2 is hung up or lie on the ground.

You can verify LCM send by opening a new terminal:
```bash
cd go2_gym_deploy/build
sudo ./lcm_receive
```

### Load and run policy
Open a new terminate and run:
```bash
cd go2_gym_deploy/scripts
python deploy_policy.py
```

According to the hints shown in terminal, Press [R2] to start the controller. You can check RC mapping from [walk-these-ways](https://github.com/Improbable-AI/walk-these-ways) page.

**Caution**:
* Press [L2+B] if any unexpected situation occurs!!!
* This is research code; use at your own risk; we do not take responsibility for any damage.

Test Video on Unitree Go2: https://www.bilibili.com/video/BV1tQ4y1c7ZG/?spm_id_from=333.999.0.0&vd_source=07873ebe2a113dac57775e264a210929


**Please star this repository if it does help you! Thanks!**

## Acknowledgements
* Many thanks to [XiaoxiaoMeitou](https://github.com/Chicken-wings-programing), who provide Nvidia 3060ti and supporting.
* Many thanks to Jony for his support and encourage me to learn basic kownledge about RL.
* Many thanks to xxx, who provide Go2 pretrained model.

## TO DO
* Deploy on Jeston Orin Nano