carla无人驾驶模拟中文项目 carla_simulator_Chinese

https://github.com/xfqbuaa/carla_simulator_Chinese

CARLA Self Driving Car Simulator in Chinese Traffic Scenes

Introduction

To build a self driving car simulator for Chinese traffic, which based on intel open source simulator Carla.

There are several targets show below:

  • Integrate perception, localization, path planning and control in Carla simulator.
  • Setup Chinese city traffic map
  • Verify multi-camera + radar solution feasibility
  • Setup metrics to evaluate self driving car algorithm

Status

Reproduce Carla modular pipeline

questions

Tasks and plans

  1. Carla installation and learning
  • Receive measurement data from server
  • Send control data to control vehicle
  • Define radar sensor
  • Reproduce Carla team modular pipeline.
  1. Integrate perception, localization, path planning and control
  • Lane detection
  • Traffic Signs detection
  • Vehicles, pedestrian detection
  • Localization
  • Path planning
  • Vehicle control
  • Integrating
  1. Customize Chinese city map
  2. Verify multi-camera + radar solution feasibility
  3. Evaluate self driving car algorithm

Environment

  • Ubuntu 16.04
  • ROS
  • Python 3.5
  • Anaconda
  • Tensorflow 1.4.0

Resources

  • Carla github
  • Carla document
  • Carla 0.7 baidu pan 链接: https://pan.baidu.com/s/1eSuBh5K 密码: dgqz
  • Carla introduction zhihu
  • Carla paper
  • Carla tutorial
  • Udacity self driving car simulator
  • Airsim

Roadmap

  • Traffic lights filter if there are several detections.

Examples: if model detects two green lights from front camera images, there should be a pipeline to determine which light should be used.

  • Vehicle dynamics simulation improvements
  • Vehicle customization

Core contributors

The core contributors are a team including several Chinese Udacity self driving car Nanodegree graduates.

Licenses

CARLA Self Driving Car Simulator in Chinese Traffic Scenes specific code is distributed under MIT License.

Related assets follows CARLA Licenses

原文发布于微信公众号 - CreateAMind(createamind)

原文发表时间:2018-01-30

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

发表于

我来说两句

0 条评论
登录 后参与评论

相关文章

来自专栏CreateAMind

carla无人驾驶模拟中文项目 carla_simulator_Chinese

2141
来自专栏GreenLeaves

EF基础知识小记五(一对多、多对多处理)

本文主要讲EF一对多关系和多对多关系的建立 一、模型设计器 1、一对多关系 右键设计器新增关联 ? ? 导航属性和外键属性可修改 2、多对多关系 右键设计器新增...

4678
来自专栏HansBug's Lab

1589: [Usaco2008 Dec]Trick or Treat on the Farm 采集糖果

1589: [Usaco2008 Dec]Trick or Treat on the Farm 采集糖果 Time Limit: 5 Sec  Memory L...

2665
来自专栏C语言及其他语言

【每日一题】问题 1146: 舍罕王的失算

关注我们 题目描述 相传国际象棋是古印度舍罕王的宰相达依尔发明的.舍罕王十分喜爱象棋,决定让宰相自己选择何种赏赐.这位聪明的宰相指着8*8共64格的象棋说:陛...

35111
来自专栏青青天空树

2018-母牛的故事

 有一头母牛,它每年年初生一头小母牛。每头小母牛从第四个年头开始,每年年初也生一头小母牛。请编程实现在第n年的时候,共有多少头母牛?

3492
来自专栏王磊的博客

经典面试题SALES TAXES思路分析和源码分享

题目: SALES TAXES Basic sales tax is applicable at a rate of 10% on all goods, ex...

3066
来自专栏ACM算法日常

PAT-CCCC练习:L2-020.功夫传人(并查集)

题目:https://www.patest.cn/contests/gplt/L2-020

1302
来自专栏ccylovehs

JavaScript模拟自由落体

但是实际呈现的效果却不尽人意,应该是反弹位移计算有误,经反复思考无果(若哪位大拿有更好的实现方式欢迎评论告知)

1171
来自专栏大数据挖掘DT机器学习

使用R语言构造投资组合

原作者: 邓一硕 来自: 格物堂 构造投资组合是金融投资分析中历久弥新的问题。多年以来,学界、业界提出诸多对投资组合进行优化的方法。比如,最经典的基于收益率均...

5706
来自专栏章鱼的慢慢技术路

牛客网2018年全国多校算法寒假训练营练习比赛(第二场)

3634

扫码关注云+社区

领取腾讯云代金券