Comments (6)
Self-driving cars obtain surrounding environment information through perception modules. That is to say, the perception module will detect vehicles and pedestrians and provide feedback to the self-driving car to avoid them.
Back to your question, you can parse the autonomous car's perception messages(topic: /apollo/perception/obstacles) to see if another car is detected.
go further
I think you may need to identify it automatically. You can use the simulator to obtain the position of the self-driving vehicle, and then compare it with the perceived results. For example, use IOU to determine whether it is the same car.
from apollo.
https://github.com/Software-Aurora-Lab/DoppelTest This project allows multiple Apollo instances to be simulated in SimControl. The underlying mechanism passes one Apollo's localization as perception to other instances, so all the instances can see each other.
from apollo.
https://github.com/Software-Aurora-Lab/DoppelTest This project allows multiple Apollo instances to be simulated in SimControl. The underlying mechanism passes one Apollo's localization as perception to other instances, so all the instances can see each other.
So are there no other NPCs? All vehicles are Apollo self-driving cars?
from apollo.
https://github.com/Software-Aurora-Lab/DoppelTest This project allows multiple Apollo instances to be simulated in SimControl. The underlying mechanism passes one Apollo's localization as perception to other instances, so all the instances can see each other.
So are there no other NPCs? All vehicles are Apollo self-driving cars?
Not exactly. In this implementation, all vehicles are Apollo self driving cars, pedestrians can be included and they walk around crosswalks (didn’t have a better way to simulate realistic pedestrian), no bicycle, with valid traffic lights (conflicting ones won’t be green at the same time).
from apollo.
What I want to express is that there will be conflicts between groundtruth and perception modules. It is best for them to choose 1 from 2.
from apollo.
I see. Yes, in the project linked above, perception module is replaced by ground truth perception messages generated by the project.
from apollo.
Related Issues (20)
- orin tensorrt crash on apollo 9.0 docker HOT 1
- read buffer overflow and drop message when cyber_recorder record HOT 11
- 如何进入手动驾驶模式? HOT 5
- Reflectance map folder is invalid! and Localization Status Is Missing HOT 5
- Apollo9.0;40系感知camera_tracking报错 HOT 3
- why cyber rt use for (;;) here? HOT 2
- 使用buildtool时发生错误 HOT 3
- Is it possible to have multiple versions of protobuf? HOT 1
- how to get `trtexec`? HOT 1
- Member call on misaligned address Bug HOT 2
- 启动canbus时,使用cyber_moniter的先后顺序会影响通道的数据类型 HOT 1
- why timing_wheel.cc using current_work_wheel_index_mutex_ HOT 1
- IDL file for underlay message
- [buildtool] ERROR hint: planning-gpu-dev have been occupied HOT 2
- Data loss in the inter-device communication
- reeds_shepp_path cost computation bug HOT 2
- 在打开dreamview_plus时,网页无法加载成功,再刷新一次全部No data HOT 3
- Perception network - Python API request HOT 1
- Perception network: Camera - BEV 3D Object Detection HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from apollo.