Merge pull request #16 from opendilab/gl-dev

update 0.3.3

.gitignore

@@ -1402,10 +1402,16 @@ htmlcov
 *.lock
 .coverage*
 
-project_test.py
+## DI-engine
+*total_config.py
+openaigym*
+
+## Carla
 *.csv
 *.avi
+
+.vscode
+project_test.py
 *episode_metainfo.json
 *measurements.lmdb
 *index.txt
-openaigym*

CHANGELOG

@@ -1,3 +1,9 @@
+## v0.3.3 (2022.6.5)
+- Update readme, reorganize info
+- Add MetaDriveTrajEnv and doc
+- Add utils for MetaDrive
+- Modify utils for macro env
+
 ## v0.3.2 (2022.4.24)
 - Update banner logo
 - Update to DI-engine 0.3, modify env properties

README.md

@@ -2,44 +2,73 @@
 
 <img src="./docs/figs/di-drive_banner.png" alt="icon"/>
 
-Updated on 2022.4.16 DI-drive-v0.3.2 (beta)
-
-DI-drive - Decision Intelligence Platform for Autonomous Driving simulation.
-
-DI-drive is application platform under [OpenDILab](http://opendilab.org/)
-
-![icon](./docs/figs/big_cam_auto.png)
-
-## Introduction
-
-**DI-drive** is an open-source application platform under **OpenDILab**. DI-drive applies different simulator/datasets/cases in **Decision Intelligence** Training & Testing for **Autonomous Driving** Policy.
+**DI-drive** is an open-source Decision Intelligence Platform for Autonomous Driving simulation. DI-drive applies different simulators/datasets/cases in **Decision Intelligence** Training & Testing for **Autonomous Driving** Policy.
 It aims to
 
 - run Imitation Learning, Reinforcement Learning, GAIL etc. in a single platform and simple unified entry
-- apply Decision Intelligence in any parts of driving simulation
+- apply Decision Intelligence in any part of the driving simulation
 - suit most of the driving simulators input & output
 - run designed driving cases and scenarios
 
 and most importantly, to **put these all together!**
 
 **DI-drive** uses [DI-engine](https://github.com/opendilab/DI-engine), a Reinforcement Learning
 platform to build most of the running modules and demos. **DI-drive** currently supports [Carla](http://carla.org),
-an open-source Autonomous Drining simulator to operate driving simualtion, and [MetaDrive](https://decisionforce.github.io/metadrive/),
-a diverse driving scenarios for Generalizable Reinforcement Learning. Users can specify any of them to run in global config under `core`.
+an open-source Autonomous Driving simulator to operate driving simulation, and [MetaDrive](https://decisionforce.github.io/metadrive/),
+a diverse driving scenarios for Generalizable Reinforcement Learning. DI-drive is an application platform under [OpenDILab](http://opendilab.org/)
+
+![icon](./docs/figs/big_cam_auto.png)
+<p align="center"> Visualization of Carla driving in DI-drive </p>
+
+## Outline
+
+ * [Installation](#installation)
+ * [Quick Start](#quick-start)
+ * [Model Zoo](#model-zoo)
+ * [Casezoo](#di-drive-casezoo)
+ * [File Structure](#file-structure)
+ * [Contributing](#contributing)
+ * [License](#license)
+ * [Citation](#citation)
 
 ## Installation
 
-**DI-drive** needs to have the following modules installed:
+**DI-drive** runs with **Python >= 3.5** and **DI-engine >= 0.3.1** (Pytorch is needed in DI-engine). You can install DI-drive from the source code:
+
+```bash
+git clone https://gitlab.bj.sensetime.com/open-XLab/cell/xad.git
+cd xad
+pip install -e .
+```
+
+DI-engine and Pytorch will be installed automatically.
+
+In addition, at least one simulator in Carla and MetaDrive need to be able to run in DI-drive. [MetaDrive](https://decisionforce.github.io/metadrive/) can be easily installed via `pip`.
+If [Carla](http://carla.org) server is used for simulation, users need to install 'Carla Python API' in addition. You can use either one of them or both. Make sure to modify the activated simulators in `core.__init__.py` to avoid import error.
 
-- Pytorch
-- DI-engine
+Please refer to the [installation guide](https://opendilab.github.io/DI-drive/installation/index.html) for details about the installation of **DI-drive**.
 
-[MetaDrive](https://decisionforce.github.io/metadrive/) can be easily installed via `pip`.
-If [Carla](http://carla.org) server is used for simulation, users need to install 'Carla Python API' in addition.
-Please refer to the [documentation](https://opendilab.github.io/DI-drive/) for details about installation and user guide of **DI-drive**.
-We provide IL and RL tutorials, and full guidance for quick run existing policy for beginners.
+## Quick Start
 
-Please refer to [FAQ](https://opendilab.github.io/DI-drive/faq/index.html) for frequently asked questions.
+### Carla
+
+Users can check the installation of Carla and watch the visualization by running an 'auto' policy in provided town map. You need to start a Carla server first and modify the Carla host and port in `auto_run.py` into yours. Then run:
+
+```bash
+cd demo/auto_run
+python auto_run.py
+```
+
+### MetaDrive
+
+After installation of MetaDrive, you can start an RL training in MetaDrive Macro Environment by running the following code:
+
+```bash
+cd demo/metadrive
+python macro_env_dqn_train.py.
+```
+
+We provide detail guidance for IL and RL experiments in all simulators and quick run of existing policy for beginners in our [documentation](https://opendilab.github.io/DI-drive/). Please refer to it if you have further questions.
 
 ## Model Zoo
 
@@ -58,15 +87,99 @@ Please refer to [FAQ](https://opendilab.github.io/DI-drive/faq/index.html) for f
 
 ## DI-drive Casezoo
 
-**DI-drive Casezoo** is a scenario set for training and testing of Autonomous Driving policy in simulator.
-**Casezoo** combines data collected by real vehicles and Shanghai Lingang road license test Scenarios.
-**Casezoo** supports both evaluating and training, whick makes the simulation closer to real driving.
+**DI-drive Casezoo** is a scenario set for training and testing the Autonomous Driving policy in simulator.
+**Casezoo** combines data collected from actual vehicles and Shanghai Lingang road license test Scenarios.
+**Casezoo** supports both evaluating and training, which makes the simulation closer to real driving.
 
 Please see [casezoo instruction](docs/casezoo_instruction.md) for details about **Casezoo**.
 
-## Contributing
+## File Structure
+
+```
+DI-drive
+|-- .gitignore
+|-- .style.yapf
+|-- CHANGELOG
+|-- LICENSE
+|-- README.md
+|-- format.sh
+|-- setup.py
+|-- core
+|   |-- data
+|   |   |-- base_collector.py
+|   |   |-- benchmark_dataset_saver.py
+|   |   |-- bev_vae_dataset.py
+|   |   |-- carla_benchmark_collector.py
+|   |   |-- cict_dataset.py
+|   |   |-- cilrs_dataset.py
+|   |   |-- lbc_dataset.py
+|   |   |-- benchmark
+|   |   |-- casezoo
+|   |   |-- srunner
+|   |-- envs
+|   |   |-- base_drive_env.py
+|   |   |-- drive_env_wrapper.py
+|   |   |-- md_macro_env.py
+|   |   |-- md_traj_env.py
+|   |   |-- scenario_carla_env.py
+|   |   |-- simple_carla_env.py
+|   |-- eval
+|   |   |-- base_evaluator.py
+|   |   |-- carla_benchmark_evaluator.py
+|   |   |-- serial_evaluator.py
+|   |   |-- single_carla_evaluator.py
+|   |-- models
+|   |   |-- bev_speed_model.py
+|   |   |-- cilrs_model.py
+|   |   |-- common_model.py
+|   |   |-- lbc_model.py
+|   |   |-- model_wrappers.py
+|   |   |-- mpc_controller.py
+|   |   |-- pid_controller.py
+|   |   |-- vae_model.py
+|   |   |-- vehicle_controller.py
+|   |-- policy
+|   |   |-- auto_policy.py
+|   |   |-- base_carla_policy.py
+|   |   |-- cilrs_policy.py
+|   |   |-- lbc_policy.py
+|   |-- simulators
+|   |   |-- base_simulator.py
+|   |   |-- carla_data_provider.py
+|   |   |-- carla_scenario_simulator.py
+|   |   |-- carla_simulator.py
+|   |   |-- fake_simulator.py
+|   |   |-- srunner
+|   |-- utils
+|       |-- data_utils
+|       |-- env_utils
+|       |-- learner_utils
+|       |-- model_utils
+|       |-- others
+|       |-- planner
+|       |-- simulator_utils
+|-- demo
+|   |-- auto_run
+|   |-- cict
+|   |-- cilrs
+|   |-- implicit
+|   |-- latent_rl
+|   |-- lbc
+|   |-- metadrive
+|   |-- simple_rl
+|-- docs
+|   |-- casezoo_instruction.md
+|   |-- figs
+|   |-- source
+```
+
+## Join and Contribute
+
+We appreciate all contributions to improve DI-drive, both algorithms and system designs. Welcome to OpenDILab community! Scan the QR code and add us on Wechat:
+
+<div align=center><img width="250" height="250" src="./docs/figs/qr.png" alt="qr"/></div>
 
-We appreciate all contributions to improve DI-drive, both algorithms and system designs.
+Or you can contact us with [slack](https://opendilab.slack.com/join/shared_invite/zt-v9tmv4fp-nUBAQEH1_Kuyu_q4plBssQ#/shared-invite/email) or email ([email protected]).
 
 ## License
 

core/__init__.py

@@ -1,5 +1,5 @@
 __TITLE__ = "DI-drive"
-__VERSION__ = "0.3.2"
+__VERSION__ = "0.3.3"
 __DESCRIPTION__ = "Decision AI Auto-Driving Platform"
 __AUTHOR__ = "OpenDILab Contributors"
 __AUTHOR_EMAIL__ = "[email protected]"

core/envs/__init__.py

@@ -22,8 +22,10 @@
 
 if 'metadrive' in SIMULATORS:
     from .md_macro_env import MetaDriveMacroEnv
+    from .md_traj_env import MetaDriveTrajEnv
     env_map.update({
         "Macro-v1": 'core.envs.md_macro_env:MetaDriveMacroEnv',
+        "Traj-v1": 'core.envs.md_traj_env:MetaDriveTrajEnv'
     })
 
 for k, v in env_map.items():

core/envs/md_macro_env.py

@@ -6,14 +6,12 @@
 from gym import spaces
 from collections import defaultdict
 from typing import Union, Dict, AnyStr, Tuple, Optional
-from gym.envs.registration import register
 import logging
 
 from ding.utils import ENV_REGISTRY
 from core.utils.simulator_utils.md_utils.discrete_policy import DiscreteMetaAction
 from core.utils.simulator_utils.md_utils.agent_manager_utils import MacroAgentManager
-from core.utils.simulator_utils.md_utils.engine_utils import initialize_engine, close_engine, \
-    engine_initialized, set_global_random_seed, MacroBaseEngine
+from core.utils.simulator_utils.md_utils.engine_utils import MacroEngine
 from core.utils.simulator_utils.md_utils.traffic_manager_utils import TrafficMode
 
 from metadrive.envs.base_env import BaseEnv
@@ -22,7 +20,7 @@
 # from metadrive.manager.traffic_manager import TrafficMode
 from metadrive.component.pgblock.first_block import FirstPGBlock
 from metadrive.constants import DEFAULT_AGENT, TerminationState
-from metadrive.component.vehicle.base_vehicle import BaseVehicle
+from metadrive.engine.base_engine import BaseEngine
 from metadrive.utils import Config, merge_dicts, get_np_random, clip
 
 from metadrive.envs.base_env import BASE_DEFAULT_CONFIG
@@ -142,7 +140,7 @@ def __init__(self, config: dict = None) -> None:
         #self.action_space = self.action_type.space()
 
         # lazy initialization, create the main vehicle in the lazy_init() func
-        self.engine: Optional[MacroBaseEngine] = None
+        self.engine: Optional[BaseEngine] = None
         self._top_down_renderer = None
         self.episode_steps = 0
         # self.current_seed = None
@@ -446,9 +444,10 @@ def lazy_init(self):
         :return: None
         """
         # It is the true init() func to create the main vehicle and its module, to avoid incompatible with ray
-        if engine_initialized():
+        if MacroEngine.singleton is not None:
             return
-        self.engine = initialize_engine(self.config)
+        MacroEngine.singleton = MacroEngine(self.config)
+        self.engine = MacroEngine.singleton
         # engine setup
         self.setup_engine()
         # other optional initialization