update version v0.1.1

opendilab · Aug 16, 2021 · 32b4b80 · 32b4b80
1 parent ade3c9d
commit 32b4b80
Show file tree

Hide file tree

Showing 53 changed files with 4,841 additions and 68 deletions.
diff --git a/CHANGELOG b/CHANGELOG
@@ -1,3 +1,19 @@
+## v0.1.1 (2021.8.16)
+
+- Update AutoPolicy: better performance in multi-lane maps
+- Add bike avoidance and agent state in behavior planner
+- Add CICT IL method: data, train, eval and test
+- Add CICT doc
+- Add LBC: eval and test
+- Add LBC: doc
+- Add common PID controller
+- Add LBC planner
+- Add transform obs for evaluator
+- Add velocity, angular velocity and rotation in simulator's navigation and data provider
+- Modify initialization of AutoPolicy
+- Fix bugs in default config of all modules
+- Add overview for Implicit Affordance doc
+
 ## v0.1.0.1 (2021.7.21)
 
 - Fix import error in scenario files.

diff --git a/README.md b/README.md
@@ -1,3 +1,5 @@
+# DI-drive
+
 <img src="./docs/figs/DI-drive.png" width="200" alt="icon"/>
 
 ---
@@ -11,7 +13,7 @@
 [![Contributors](https://img.shields.io/github/contributors/opendilab/DI-drive)](https://github.com/opendilab/DI-drive/graphs/contributors)
 [![GitHub license](https://img.shields.io/github/license/opendilab/DI-drive)](https://github.com/opendilab/DI-drive/blob/master/LICENSE)
 
-Updated on 2021.07.23 DI-drive-v0.1.0.1 (beta)
+Updated on 2021.08.16 DI-drive-v0.1.1 (beta)
 
 DI-drive - Decision Intelligence Platform for Autonomous Driving simulation.
 
@@ -21,7 +23,6 @@ DI-drive is application platform under [OpenDILab](http://opendilab.org/)
 
 ## 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.
 It aims to
 
@@ -51,10 +52,14 @@ Please refer to [FAQ](https://opendilab.github.io/DI-drive/faq/index.html) for f
 
 ## Model Zoo
 
-#### Imitation Learning
-- [Conditional Imitation Learning](http://vladlen.info/papers/conditional-imitation.pdf)
+### Imitation Learning
+
+- [Conditional Imitation Learning](https://arxiv.org/abs/1710.02410)
+- [Learning by Cheating](https://arxiv.org/abs/1912.12294)
+- [from Continuous Intention to Continuous Trajectory](https://arxiv.org/abs/2010.10393)
+
+### Reinforcement Learning
 
-#### Reinforcement Learning
 - BeV Speed RL
 - [Implicit Affordance](https://arxiv.org/abs/1911.10868)
 
@@ -73,14 +78,15 @@ We appreciate all contributions to improve DI-drive, both algorithms and system
 ## License
 
 DI-drive released under the Apache 2.0 license.
+
 ## Citation
 
 ```latex
 @misc{didrive,
     title={{DI-drive: OpenDILab} Decision Intelligence platform for Autonomous Driving simulation},
     author={DI-drive Contributors},
     publisher = {GitHub},
-    howpublished = {\url{https://github.com/opendilab/DI-drive}},
+    howpublished = {\url{`https://github.com/opendilab/DI-drive`}},
     year={2021},
 }
 ```
diff --git a/core/data/base_collector.py b/core/data/base_collector.py
@@ -3,6 +3,7 @@
 from typing import Any, Dict
 from easydict import EasyDict
 
+from core.utils.others.config_helper import deep_merge_dicts
 from ding.utils import EasyTimer
 
 
@@ -18,7 +19,7 @@ def __init__(
     ) -> None:
         if 'cfg_type' not in cfg:
             self._cfg = self.__class__.default_config()
-            self._cfg.update(cfg)
+            self._cfg = deep_merge_dicts(self._cfg, cfg)
         else:
             self._cfg = cfg
         self._end_flag = False