# Robot Explore with LLM

**Repository Path**: mxueim/robot-explore-wit-llm

## Basic Information

- **Project Name**: Robot Explore with LLM
- **Description**: No description.
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2023-11-06
- **Last Updated**: 2023-11-15

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Robot Explore with LLM

This repo is from [mrasamu](https://gitee.com/mrasamu)'s project

## Prerequisites

- Ubuntu 20.04
- ROS Noetic
- Turtlebot3
- OpenCV 3
- Python 3.8

💼 Source code is [here](https://cloud.tsinghua.edu.cn/f/cdb0e6fa56314b77adb9/).

💼 We add our python package version in `PythonPkg.txt` for your reference.


If you have same issue like it, here is a [debug-solution](https://d2cu9wb3ad.feishu.cn/docx/CptsdEGplodSOUxNZxycAgiYnFc?from=from_copylink) doc.



## Installation

### 1. Cartographer-for-SMMR

Cartographer is a 2D/3D map-building method. It provides the submaps' and the trajectories' information when building the map.

We slightly modified the original Cartographer to make it applicable to multi-robot SLAM and exploration.

Please refer to [Cartographer-for-SMMR](https://github.com/efc-robot/Cartographer-for-SMMR) to install the modified Cartographer to carto_catkin_ws

and

```
source /PATH/TO/CARTO_CATKIN_WS/devel_isolated/setup.bash
```
**Note**: Cartographer-for-SMMR is build with ROS Melodic, you should build it with ROS Noetic.

### 2. Turtlebot3 Description and Simulation
(robot model for simulation)

```
sudo apt install ros-noetic-turtlebot3*
pip install future
sudo apt install ros-noetic-teb-local-planner
echo "export TURTLEBOT3_MODEL=burger" >> ~/.bashrc
```


or you can refer to [turtlebot3-quick-start](https://emanual.robotis.com/docs/en/platform/turtlebot3/quick-start/) and choose your ROS version for a full installation.


### 3. Build the current project on ROS

1. Clone the repository
2. Open `gpt_server.py`, and replace two OpenAI API keys with your own API keys: `openai.api_key = sk-***`

3. catkin build

```
cd ~/catkin_ws/src
put code here
cd ../
catkin build
source ~/catkin_ws/devel/setup.bash
```

**Note**: You can write `source ...` to `~/.bashrc` by
`echo "source ~/catkin_ws/devel/setup.bash" >> ~/.bashrc`


## Run project

Open three terminals, launch these files respectively.

```
roslaunch turtlebot3sim small_env_two_robots.launch

roslaunch turtlebot3sim two_robots_origin.launch

roslaunch ros_topoexplore single_robot_topo.launch
```