Arena-sim-to-real is based on arena-rosnav, which is a flexible, high-performance 2D simulator for testing robotic navigation, and pedsim_ros, which is a pedestrian simulator implementing the social force model. The agent is trained to learn an object-specific navigation behavior, keeping different safety distances towards different types of humans such as adults, children, and elders. An efficient DRL approach called CPU/GPU asynchronous A3C using curriculum learning is utilized. Within the simulation, it is assumed that the agent knows the accurate position and type of humans in the vicinity for understanding the interaction between the robot and humans. In real-world experiments, this information can be acquired using computer vision approaches.
 |
|---|
| normal |
| In addition to the normal task of navigating in a complex environment, auxiliary human guidance/following tasks have been introduced. |
 |
 |
|---|---|
| Guiding Human | Following Human |
We recommend starting with the start guide which contains all information you need to know to start off with this project including installation on Linux and Windows as well as tutorials to start with.
Please refer to Installation.md for detailed explanations about the installation process.
Please refer to DRL-Training.md for detailed explanations about agent, policy and training setups.
DRL agents are located in the agents folder.
- In one terminnal, start simulation
workon the_name_of_your_virtual_env
roslaunch arena_bringup start_training.launch num_envs:=1 show_pedsim_labels:=true republish_flatland_markers:=true
- In another terminal, load the pretrained agent
workon the_name_of_your_virtual_env
roscd arena_local_planner_drl && python scripts/training/train_agent.py --load name_of_pretrained_agent --config rule_03 --n_envs 1
...