Add pre-commit

.github/workflows/main.yml

@@ -8,8 +8,8 @@ jobs:
         runs-on: ubuntu-latest
         name: A job to automate contrib in readme
         permissions:
-          contents: write
-          pull-requests: write
+            contents: write
+            pull-requests: write
         steps:
             - name: Contribute List
               uses: akhilmhdh/[email protected]

.pre-commit-config.yaml

@@ -0,0 +1,59 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+
+  - repo: https://github.com/psf/black
+    rev: 24.8.0
+    hooks:
+      - id: black
+        args: [--line-length=150]
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black", "--line-length", "150"]
+
+  - repo: https://github.com/pycqa/flake8
+    rev: 7.1.1
+    hooks:
+      - id: flake8
+        args:
+          - --max-line-length=150
+          - --ignore=E203,E266,E501,W503,F401,E402,E731
+          - --per-file-ignores=__init__.py:F401,F403
+
+  - repo: https://github.com/adrienverge/yamllint
+    rev: v1.35.1
+    hooks:
+      - id: yamllint
+        args:
+          - --config-data
+          - |
+            extends: default
+            rules:
+              line-length:
+                max: 150
+              truthy: disable
+              document-start: disable
+              braces:
+                min-spaces-inside: 0
+                max-spaces-inside: -1
+              comments:
+                min-spaces-from-content: 1
+
+  - repo: https://github.com/google/yapf
+    rev: v0.40.2
+    hooks:
+      - id: yapf
+        args: ["--style", "{column_limit: 150, align_closing_bracket_with_visual_indent: true, dedent_closing_brackets: true}"]
+
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.17
+    hooks:
+      - id: mdformat

README.md

@@ -22,16 +22,15 @@
 
 </div>
 
----
-
+______________________________________________________________________
 
 Unleash the power of **imagination** and **generalization** of world models for self-driving cars.
 
-> [!NOTE]
+> \[!NOTE\]
+>
 > - **July 2024:** Created a stop-sign task and a traffic-light task!
 > - **July 2024:** Uploaded all the task checkpoints to [HuggingFace](https://huggingface.co/ucd-dare/CarDreamer/tree/main)
 
-
 ## **Can world models imagine traffic dynamics for training autonomous driving agents? The answer is YES!**
 
 Integrating the high-fidelity CARLA simulator with world models, we are able to train a world model that not only learns complex environment dynamics but also have an agent interact with the neural network "simulator" to learn to drive.
@@ -44,18 +43,17 @@ Dive into our demos to see the agent skillfully navigating challenges and ensuri
 
 **Explore** world model based autonomous driving with CarDreamer, an open-source platform designed for the **development** and **evaluation** of **world model** based autonomous driving.
 
-* 🏙️ **Built-in Urban Driving Tasks**: flexible and customizable observation modality and observability; optimized rewards
-* 🔧 **Task Development Suite**: create your own urban driving tasks with ease
-* 🌍 **Model Backbones**: integrated state-of-the-art world models
+- 🏙️ **Built-in Urban Driving Tasks**: flexible and customizable observation modality and observability; optimized rewards
+- 🔧 **Task Development Suite**: create your own urban driving tasks with ease
+- 🌍 **Model Backbones**: integrated state-of-the-art world models
 
 **Documentation:** [CarDreamer API Documents](https://car-dreamer.readthedocs.io/en/latest/).
 
 **Looking for more techincal details? Check our report here! [Paper link](https://arxiv.org/abs/2405.09111)**
 
-
 ## :sun_with_face: Built-in Task Demos
 
-> [!TIP]
+> \[!TIP\]
 > A world model is learnt to model traffic dynamics; then a driving agent is trained on world model's imagination! The driving agent masters diverse driving skills including lane merge, left turn, and right turn, to random roadming purely **from scratch**.
 
 We train DreamerV3 agents on our built-in tasks with a single 4090. Depending on the observation spaces, the memory overhead ranges from 10GB-20GB alongwith 3GB reserved for CARLA.
@@ -72,30 +70,26 @@ We train DreamerV3 agents on our built-in tasks with a single 4090. Depending on
 | :-----------: | :-------: |
 | ![Traffic Light](https://raw.githubusercontent.com/ucd-dare/cardreamer.github.io/main/static/gifs/bev/tl_right.gif) | ![Stop Sign](https://raw.githubusercontent.com/ucd-dare/cardreamer.github.io/main/static/gifs/bev/stop%20sign.gif) |
 
-
 ## :blossom: The Power of Intention Sharing
 
-> [!TIP]
+> \[!TIP\]
 > **Human drivers use turn signals to inform their intentions** of turning left or right. **Autonomous vehicles can do the same!**
 
 Let's see how CarDreamer agents communicate and leverage intentions. Our experiment have demonstrated that through sharing intention, the policy learning is much easier! Specifically, a policy without knowing other agents' intentions can be conservative in our crossroad tasks; while intention sharing allows the agents to find the proper timing to cut in the traffic flow.
 
-
 <!-- Table 1: Sharing waypoints vs. Without sharing waypoints -->
+
 | Sharing waypoints vs. Without sharing waypoints | Sharing waypoints vs. Without sharing waypoints |
 | :---------------------------------------------: | :---------------------------------------------: |
 | **Right turn hard**                                  | **Left turn hard**                                  |
-| ![Right turn hard](./.assets/right_turn_hard.gif) &emsp;&emsp;&emsp; ![Right turn hard no waypoint](./.assets/right_turn_raw_fail.gif) | ![Left turn hard](./.assets/left_turn_hard.gif) &emsp;&emsp;&emsp;<img src="./.assets/left turn raw.gif" style="width: 100%"> |
+| ![Right turn hard](./.assets/right_turn_hard.gif)     ![Right turn hard no waypoint](./.assets/right_turn_raw_fail.gif) | ![Left turn hard](./.assets/left_turn_hard.gif)    <img src="./.assets/left turn raw.gif" style="width: 100%"> |
 
 <!-- Table 2: Full observability vs. Partial observability -->
+
 | Full observability vs. Partial observability |
 | :------------------------------------------: |
 | **Right turn hard**                               |
-| ![Right turn hard](./.assets/right_turn_hard.gif) &emsp;&emsp;&emsp; ![Right turn hard FOV](./.assets/right_turn_hard_fov.gif) |
-
-
-
-
+| ![Right turn hard](./.assets/right_turn_hard.gif)     ![Right turn hard FOV](./.assets/right_turn_hard_fov.gif) |
 
 ## 📋 Prerequisites
 
@@ -108,14 +102,14 @@ git clone https://github.com/ucd-dare/CarDreamer
 cd CarDreamer
 ```
 
-Download [CARLA release](https://github.com/carla-simulator/carla/releases) of version ``0.9.15`` as we experiemented with this version. Set the following environment variables:
+Download [CARLA release](https://github.com/carla-simulator/carla/releases) of version `0.9.15` as we experiemented with this version. Set the following environment variables:
 
 ```bash
 export CARLA_ROOT="</path/to/carla>"
 export PYTHONPATH="${CARLA_ROOT}/PythonAPI/carla":${PYTHONPATH}
 ```
 
-Install the package using flit. The ``--symlink`` flag is used to create a symlink to the package in the Python environment, so that changes to the package are immediately available without reinstallation. (``--pth-file`` also works, as an alternative to ``--symlink``.)
+Install the package using flit. The `--symlink` flag is used to create a symlink to the package in the Python environment, so that changes to the package are immediately available without reinstallation. (`--pth-file` also works, as an alternative to `--symlink`.)
 
 ```bash
 conda create python=3.10 --name cardreamer
@@ -132,7 +126,7 @@ The model backbones are decoupled from CarDreamer tasks or the development sutie
 
 ### :mechanical_arm: Training
 
-Find ``README.md`` in the corresponding directory of the algorithm you want to use and follow the instructions. For example, to train DreamerV3 agents, use
+Find `README.md` in the corresponding directory of the algorithm you want to use and follow the instructions. For example, to train DreamerV3 agents, use
 
 ```bash
 bash train_dm3.sh 2000 0 --task carla_four_lane --dreamerv3.logdir ./logdir/carla_four_lane
@@ -170,7 +164,7 @@ Users can enable built-in observation handlers such as BEV, camera, LiDAR, and s
 To implement new handlers for different observation sources and modalities (e.g., text, velocity, locations, or even more complex data), `CarDreamer` provides two methods:
 
 1. Register a callback as a [SimpleHandler](https://github.com/ucd-dare/CarDreamer/blob/master/car_dreamer/toolkit/observer/handlers/simple_handler.py) to fetch data at each step.
-2. For observations requiring complex workflows that cannot be conveyed by a `SimpleHandler`, create an handler maintaining the full lifecycle of that observation, similar to our built-in message, BEV, spectator handlers.
+1. For observations requiring complex workflows that cannot be conveyed by a `SimpleHandler`, create an handler maintaining the full lifecycle of that observation, similar to our built-in message, BEV, spectator handlers.
 
 For more details on defining new observation sources, see [CarDreamer Docs: Defining a new observation source](https://car-dreamer.readthedocs.io/en/latest/customization.html#defining-a-new-observation-source).
 
@@ -197,7 +191,7 @@ your_task_name:
     observation.enabled: [camera, collision, spectator, birdeye_view]
 ```
 
-#### Environment \& Observer Communications
+#### Environment & Observer Communications
 
 One might need transfer information from the environements to a handler to compute their observations. E.g., a BEV handler might need a location to render the destination spot. These environment information can be accessed either through [WorldManager](https://car-dreamer.readthedocs.io/en/latest/api/toolkit.html#car_dreamer.toolkit.WorldManager) APIs, or through environment state management.
 
@@ -249,6 +243,7 @@ To easily customize your own driving tasks, and observation spaces, etc., please
 If you find this repository useful, please cite this paper:
 
 **[Paper link](https://arxiv.org/abs/2405.09111)**
+
 ```
 @article{CarDreamer2024,
   title = {{CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving}},
@@ -259,9 +254,10 @@ If you find this repository useful, please cite this paper:
 }
 ```
 
-
 # Suppliment Material
+
 ## World model imagination
+
 <p align="center">
   Birdeye view training
 </p>
@@ -275,12 +271,12 @@ If you find this repository useful, please cite this paper:
 </p>
 <img src="./.assets/right_turn_hard_pre_lidar.gif">
 
-
 # 👥 Contributors
 
 Special thanks to the community for your valuable contributions and support in making CarDreamer better for everyone! The contributor list is automatically generated based on commit history.
 
 <!-- readme: contributors -start -->
+
 <table>
 	<tbody>
 		<tr>

car_dreamer/__init__.py

@@ -9,18 +9,19 @@
 """
 
 from .carla_base_env import CarlaBaseEnv
-from .carla_roundabout_env import CarlaRoundaboutEnv
-from .carla_right_turn_env import CarlaRightTurnEnv
-from .carla_overtake_env import CarlaOvertakeEnv
-from .carla_navigation_env import CarlaNavigationEnv
-from .carla_left_turn_env import CarlaLeftTurnEnv
-from .carla_lane_merge_env import CarlaLaneMergeEnv
 from .carla_four_lane_env import CarlaFourLaneEnv
-from .carla_traffic_lights_env import CarlaTrafficLightsEnv
+from .carla_lane_merge_env import CarlaLaneMergeEnv
+from .carla_left_turn_env import CarlaLeftTurnEnv
+from .carla_navigation_env import CarlaNavigationEnv
+from .carla_overtake_env import CarlaOvertakeEnv
+from .carla_right_turn_env import CarlaRightTurnEnv
+from .carla_roundabout_env import CarlaRoundaboutEnv
 from .carla_stop_sign_env import CarlaStopSignEnv
-from .carla_wpt_fixed_env import CarlaWptFixedEnv
+from .carla_traffic_lights_env import CarlaTrafficLightsEnv
 from .carla_wpt_env import CarlaWptEnv
-__version__ = '0.2.0'
+from .carla_wpt_fixed_env import CarlaWptFixedEnv
+
+__version__ = "0.2.0"
 
 from . import toolkit
 
@@ -34,13 +35,15 @@ def load_task_configs(task_name: str):
 
     :return: the task configs
     """
-    import yaml
     import os
-    dir = os.path.join(os.path.dirname(__file__), 'configs')
-    with open(os.path.join(dir, 'common.yaml'), 'r') as f:
+
+    import yaml
+
+    dir = os.path.join(os.path.dirname(__file__), "configs")
+    with open(os.path.join(dir, "common.yaml")) as f:
         config = yaml.safe_load(f)
         config = toolkit.Config(config)
-    with open(os.path.join(dir, 'tasks.yaml'), 'r') as f:
+    with open(os.path.join(dir, "tasks.yaml")) as f:
         task_config = yaml.safe_load(f)
         config = config.update(task_config[task_name])
     return config
@@ -57,20 +60,23 @@ def create_task(task_name: str, argv=None):
     :return: a tuple of the created environment and the configs
     """
     import gym
+
     config = load_task_configs(task_name)
     config, _ = toolkit.Flags(config).parse_known(argv)
     return gym.make(config.env.name, config=config.env), config
 
 
 def _register_envs():
     import os
-    from gym.envs.registration import register
     from re import sub
 
+    from gym.envs.registration import register
+
     def toClassName(s):
         return sub(r"(_|-)+", " ", s).title().replace(" ", "")
+
     for file in os.listdir(os.path.dirname(__file__)):
-        if file.endswith('env.py') and file != '__init__.py':
+        if file.endswith("env.py") and file != "__init__.py":
             file_name = file[:-3]
             class_name = toClassName(file_name)
             exec(f"register(id='{class_name}-v0', entry_point='car_dreamer.{file_name}:{class_name}')")