sarl_star

ROS implementation of the paper SARL*: Deep Reinforcement Learning based Human-Aware Navigation for Mobile Robot in Indoor Environments presented in ROBIO 2019. This mobile robot navigation framework is implemented on a Turtlebot2 robot platform with lidar sensors (Hokuyo or RPlidar), integrating SLAM, path planning, pedestrian detection and deep reinforcement learning algorithms.

Video demonstration can be found on Youtube or bilibili. Original work can be found here.

Build & Install

1. Activate poetry shell

cd arena-rosnav # navigate to the arena-rosnav directory
poetry shell

2. Make sure to source the workspace environment

cd ../.. # navigate to the catkin_ws directory
source devel/setup.zsh # if you use bash: source devel/setup.bash 

3. Install Python-RVO2

roscd sarl_star_ros
cd ../Python-RVO2
pip install Cython
python setup.py build
python setup.py install

4. Install Python dependencies

roscd sarl_star_ros
cd CrowdNav/
pip install -e .

Usage

This planner can be chosen using the local_planner argument like so:

roslaunch arena_bringup start_arena.launch local_planner:=sarl # Make sure that your virtual env/poetry is activated

For more details regarding usage, please refer to our documentation