pwhjy/port_simulation

🚢 Port Simulation 🚛

"A platform used for researching the coordination of autonomous vehicles to optimize the efficiency of transport and other collaborative tasks."

Install SUMO latest version:

sudo add-apt-repository ppa:sumo/stable
sudo apt-get update
sudo apt-get install sumo sumo-tools sumo-doc

Don't forget to set SUMO_HOME variable (default sumo installation path is /usr/share/sumo)

echo 'export SUMO_HOME="/usr/share/sumo"' >> ~/.bashrc
source ~/.bashrc

Important: for a huge performance boost (~8x) with Libsumo, you can declare the variable:

export LIBSUMO_AS_TRACI=1
export SUMO_HOME="/opt/homebrew/opt/sumo/share/sumo"

Notice that you will not be able to run with sumo-gui or with multiple simulations in parallel if this is active (more details).

Experiments

Check experiments for examples on how to instantiate an environment.

python3 experiments/simulator.py -config config/port.ini

| **[SUMO]** | | | | ------------------- | ----------------------------- | ----------- | | nets | 路网定义文件路径 | ： .net.xml | | route | 路由定义文件路径 | ： .rou.xml | | num_seconds | 仿真时间步step | ：int | | | | | | delta_time | Env执行action的step间隔时间步 | default = 1 | | edges_start_default | 车辆默认初始位置（边） | | | begin_time | sumo仿真起始时间步 | default = 0 | | | | | | | | | | **[RENDER]** | | | | gui | 是否可视化sumo | ：bool |

MDP - Observations, Actions and Rewards

Observation

The default observation for each traffic signal agent is a vector:

obs = []

You can define your own observation by implementing a class that inherits from ObservationFunction and passing it to the environment constructor.

Action

The action space is discrete.

Rewards

It is also possible to implement your own reward function:

env = SumoEnvironment(..., reward_fn=my_reward_fn)