# ParkingE2E
## ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning
Autonomous parking is a crucial task in the intelligent driving field.
Traditional parking algorithms are usually implemented using rule-based schemes.
However, these methods are less effective in complex parking scenarios due to the intricate design of the algorithms.
In contrast, neural-network-based methods tend to be more intuitive and versatile than the rule-based methods.
By collecting a large number of expert parking trajectory data and emulating human strategy via learning-based methods, the parking task can be effectively addressed.
We employ imitation learning to perform end-to-end planning from RGB images to path planning by imitating human driving trajectories.
The proposed end-to-end approach utilizes a target query encoder to fuse images and target features, and a transformer-based decoder to autoregressively predict future waypoints.
**Video:**
<img src="resource/video_show.gif" height="250">
Supplementary video material is available at: [\[Link\]](https://youtu.be/urOEHJH1TBQ).
**Related Papers:**
- Changze Li, Ziheng Ji, Zhe Chen, Tong Qin and Ming Yang. "ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning." 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2024. [\[Link\]](https://arxiv.org/pdf/2408.02061)
- Yunfan Yang, Denglon Chen, Tong Qin, Xiangru Mu, Chunjing Xu, Ming Yang. "E2E Parking: Autonomous Parking by the End-to-end Neural Network on the CARLA Simulator." 2024 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2024. [\[Link\]](https://ieeexplore.ieee.org/abstract/document/10588551)
## 1. Prerequisites
Ubuntu 20.04, CUDA, ROS Noetic and OpenCV 4.
## 2. Setup
Clone the code:
```Shell
git clone https://github.com/ChauncyLeee/e2e_parking_imitation.git
cd e2e_parking_imitation/
```
Install virtual environment:
```Shell
conda env create -f environment.yml
```
Setup interface:
```shell
conda activate ParkingE2E
PARKINGE2E_PYTHON_PATH=`which python`
cd catkin_ws
catkin_make -DPYTHON_EXECUTABLE=${PARKINGE2E_PYTHON_PATH}
source devel/setup.bash
```
## 3. Run
#### Download pretrained model and test data:
Firstly, you should download the [pretrained model](https://drive.google.com/file/d/1rZ4cmgXOUFgJDLFdnvAI6voU9ZkhsmYV/view?usp=drive_link) and [test data](https://drive.google.com/file/d/11kA-srYa6S30OqyCdyg3jGNZxBMsUHYC/view?usp=drive_link). Then, you need to modify inference config `model_ckpt_path` in `./config/inference_real.yaml`.
#### Run driven program:
```Shell
roslaunch core driven_core.launch
```
When the command is executed for the first time, a progress bar will appear (used to calculate the distortion map). After the four (fisheye camera) progress bars are completed, subsequent operations can be carried out.
#### Start inference using E2E algorithm:
```shell
conda activate ParkingE2E
python ros_inference.py
```
When the command is executed for the first time, the `EfficientNet` pretrained model will be downloaded.
#### Run test demo:
```shell
unzip demo_scene.zip
cd demo_scene
# scene_index = 1, 2, 3, 4, 5, 6, 7. For example: sh ./demo.sh 1
sh ./demo.sh ${scene_index}
```
In rviz, you can also select the parking trarget using `2D nav goal` on the rviz pannel.
<img src="resource/demo.gif" height="250">
## 4. Train
We provide the [demo rosbag](https://drive.google.com/file/d/1jIG1iRMeW9XXdWP7eEJKnZP1gC0xvG7o/view?usp=drive_link) to create a mini dataset and train a model.
#### Generate dataset
First, you need to create a dataset.
```
python toolkit/dataset_generation.py --bag_file_path ${DEMO_BAG_PATH} --output_folder_path ./e2e_dataset
```
If you use your own rosbag, please confirm the rosbag topic in `./catkin_ws/src/core/config/params.yaml` and modify the camera configuration.
#### Train your model
```Shell
python train.py --config ./config/training_real.yaml
```
You can modify the training configuration in `./config/training_real.yaml`.
## 5. License
The source code is released under [GPLv3](http://www.gnu.org/licenses/) license.
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
几个改动代码的合集111
(237个子文件)
car.dae 142KB
car.dae 142KB
car.dae 142KB
car.dae 142KB
demo.gif 13.32MB
demo.gif 13.32MB
demo.gif 13.32MB
demo.gif 13.32MB
video_show.gif 1.91MB
video_show.gif 1.91MB
video_show.gif 1.91MB
video_show.gif 1.91MB
.gitignore 47B
.gitignore 47B
.gitignore 47B
preprocess.iml 493B
park_bev.iml 491B
park_new.iml 334B
camera_config_right_hand.json 1KB
camera_config_right_hand.json 1KB
camera_config_right_hand.json 1KB
camera_config_right_hand.json 1KB
LICENSE 34KB
LICENSE 34KB
LICENSE 34KB
LICENSE 34KB
README.md 4KB
README.md 4KB
README.md 4KB
README.md 4KB
lss_bev_model.py 24KB
lss_bev_model.py 24KB
lss_bev_model.py 18KB
lss_bev_model.py 18KB
onnx_export.py 17KB
bev_gemb.py 16KB
bev_gemb.py 16KB
bev_gemb.py 16KB
bev_gemb.py 16KB
onnx_export.py 13KB
dataset_generation.py 13KB
dataset_generation.py 13KB
dataset_generation.py 13KB
dataset_generation.py 13KB
bev_utils.py 13KB
bev_utils.py 13KB
bev_utils.py 13KB
bev_utils.py 13KB
_LocalizationEstimate.py 11KB
_LocalizationEstimate.py 11KB
_LocalizationEstimate.py 11KB
_LocalizationEstimate.py 11KB
dataset_real.py 9KB
dataset_real.py 9KB
dataset_real.py 9KB
dataset_real.py 9KB
inference_real.py 9KB
inference_real.py 9KB
inference_real.py 9KB
inference_real.py 9KB
trajectory_utils.py 7KB
trajectory_utils.py 7KB
trajectory_utils.py 7KB
trajectory_utils.py 7KB
parking_model_real.py 6KB
parking_model_real.py 6KB
parking_model_real.py 6KB
parking_model_real.py 6KB
bev_encoder.py 6KB
bev_encoder.py 6KB
bev_encoder.py 6KB
bev_encoder.py 6KB
onnx_export.py 6KB
onnx_export.py 6KB
pose_utils.py 6KB
pose_utils.py 6KB
pose_utils.py 6KB
pose_utils.py 6KB
planning_ui.py 5KB
planning_ui.py 5KB
planning_ui.py 5KB
planning_ui.py 5KB
ros_interface.py 5KB
ros_interface.py 5KB
ros_interface.py 5KB
ros_interface.py 5KB
camera_utils.py 4KB
camera_utils.py 4KB
camera_utils.py 4KB
camera_utils.py 4KB
fish_eye_camera.py 4KB
fish_eye_camera.py 4KB
fish_eye_camera.py 4KB
fish_eye_camera.py 4KB
metrics.py 4KB
metrics.py 4KB
metrics.py 4KB
metrics.py 4KB
trajectory_decoder.py 3KB
trajectory_decoder.py 3KB
共 237 条
- 1
- 2
- 3
资源评论
qq_39583670
- 粉丝: 0
- 资源: 164
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- C#ASP.NET大型制造业进销存管理系统源码数据库 SQL2008源码类型 WebForm
- liunx project 2
- (源码)基于ROS框架的智能无人机作业系统.zip
- 网页打包封装器V1.0支持苹果IOS/安卓/分发打包
- (源码)基于BERT的KBQA问答系统.zip
- (源码)基于Java和Python的笔声语音识别系统.zip
- 网络安全基础实验1-使用python中cryptography库进行对称加密和解密实验
- Python数电的课程设计网络同步时钟.zip
- (源码)基于Arduino的天文数据库管理系统.zip
- C#餐饮管理系统源码 触摸屏餐饮管理系统源码数据库 SQL2008源码类型 WinForm
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功