ROS.Taiwan 造訪社團 » Robot

完成大人交代的任務(整理書房)，建個3D map紀錄一下！

https://www.youtube.com/watch?v=_wMmGCZlx5E

Making robots with ROS : differential drive, Stereo 3D SLAM

1.Sensors:
1.1 optical encoder
1.2 Bosch IMU : bno055 usb stick
1.3 YDLidar X4
1.4 ZED stereo camera

2.Motor Drive:
2.1 Arduino Uno
2.2 Pololu Dual VNH5019 for Arduino(12A) or L298

3. ROS Package:
3.1 ros_arduino_bridge （Differential wheeled robot motor driver）
3.2 ydlidar （lidar driver）
3.3 bno055_usb_stick （IMU driver）
3.4 robot_localization （EKF Algorithm）
3.5 rtabmap_ros （SLAM Algorithm）
3.6 zed-ros-wrapper （ ZED stereo camera driver）

4. reference:
4.1 HyphaROS Workshop https://github.com/Hypha-ROS/hypharos_minibot
4.2 https://github.com/josephchen5/robot_sensors/wiki

翻譯年糕

[ROS Developers LIVE-Classes List]

Upcoming ROS LIVE streams:
http://www.theconstructsim.com/ros-developers-live-class-d…/
12 Jun | How to create an OpenAI environment for your robotic problem
19 Jun | Using Tensorflow with ROS

Previous ROS Developers LIVE-Class:
- #20: Simulate an Industrial Environment
http://www.theconstructsim.com/ros-developers-live-class-2…/

- #19: Let’s Use Gazebo Plugins
http://www.theconstructsim.com/ros-developers-live-class-1…/

- #18 : Let’s Simulate a World in Gazebo Simulator http://www.theconstructsim.com/ros-developers-live-class-1…/

- #17: Let's Simulate a Robotic Arm With Gazebo
https://youtu.be/DJwnZSaHy7s

- #16: How to build a Gazebo robot simulation
https://youtu.be/q01dDxeHTMs

- #15: Using ROS TF to transform sensor data
https://youtu.be/dBATvRhvGRI

- #14: How To Control Robot Joints With ROS
https://youtu.be/M4KF2c3OMSI

- #13: ROS Navigation Stack How To
https://youtu.be/fTizQneURWo

- #12: How to use ROS with industrial robots (ROS Industrial)
https://youtu.be/BCDFvMw6N-8

- #11: Visually Programming ROS State Machines (Round #3)
https://youtu.be/ZLv5iCSnR5c

- #10: Visually Programming ROS State Machines (Round #2)
https://youtu.be/lKkP5qhFbHQ

- #9: Visually Programming ROS State Machines (Round #1)
https://youtu.be/jrV5jRs1SJc

- #8: How to recognize faces with the ROS face recognition package
https://youtu.be/yENvskEKhJk

- #7: OpenAI+ROS Robot: Practical section
https://youtu.be/FYdS3-c2lKw

- #6: How to use OpenAI to train your robot
https://youtu.be/L7mlz7I8RbI

- #5: Simulating a Drone from Scratch
https://youtu.be/l6hVfVK_YWw

- #4: Carrot Navigation using AR Tags
https://youtu.be/QkUZWRe5f4I

- #3: rotating laser mounted on a vehicle
https://youtu.be/W2VNNMiiN-Q

- #2: Merging Odometry and IMU data for robot localization
https://youtu.be/nQZeAafDEJE

- #1: Building 3D pointclouds from rotating lasers
https://youtu.be/5CvqJ5EFbE4

翻譯年糕

[ROS resources about Gazebo]

-->Article | How to create a ROS Sensor Plugin for Gazebo
http://www.theconstructsim.com/create-a-ros-sensor-plugin-…/
There are magnificent tutorials about how to create plugins for Gazebo in the GazeboSim webpage. There are even some tutorials about how to create plugins for Gazebo + ROS. Those tutorials show that there are several types of plugins (world, model, sensor, system, visual), and indicate how to create a plugin for a world type plugin.

Recently I need to create a plugin for a light detector. Reading the tutorials, I missed a concrete example about how to create a sensor plugin. Hence, I had to investigate a little bit about it. The result is the content of this post.

-->Article | How to Build a Differential Drive Simulation
http://www.theconstructsim.com/how-to-build-a-differential…/
In this post you are going to learn:
- How to build a simple differential drive simulation in Gazebo simulator.
- How to add a plugin to the model to allow ROS commands to the robot
-How to move the robot through ROS topics

-->Article | All about Gazebo 9 with ROS
http://www.theconstructsim.com/all-about-gazebo-9-with-ros/
See how to install Gazebo 9 simulator to work with your ROS system. We are going to see how to replace the default version of Gazebo that comes with the installation of ROS and if previously existing simulations work (or not) with this new version of the simulator.

--> ROS Project | Create a Hopper Robot in Gazebo Step-by-Step
http://www.theconstructsim.com/ros-projects-create-hopper-…/

--> ROS LIVE-Classes about Gazebo
http://www.theconstructsim.com/ros-developers-live-class-d…/
#17 - Let's Simulate a Robotic Arm With Gazebo: learn how to build a Gazebo simulation model of a ROBOTIC ARM using URDF
# 18 - Let's Simulate a World in Gazebo: create a world in the Gazebo simulator for the differential drive manipulator
#19 - Let's Use Gazebo Plugins: learn how to create a Gazebo plugin for a robot simulated world
#20 - Simulate an Industrial Environment: we are going to execute ARIAC simulation made by the OSRF

翻譯年糕

"The number of robots used in the world is increasing exponentially, but not enough engineers… yet"

翻譯年糕

[Resources about Using OpenAI with ROS]
-> Article | Using OpenAI with ROS
http://www.theconstructsim.com/using-openai-ros/
OpenAI has released the Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. That toolkit is a huge opportunity for speeding up the progress in the creation of better reinforcement algorithms, since it provides an easy way of comparing them, on the same conditions, independently of where the algorithm is executed.

The toolkit is mainly aimed at the creation of RL algorithms for a general abstract agent. Here, we are interested in applying it to the control of robots (of course!). Specifically, we are interested in ROS based robots. That is why, in this post we describe how to apply the OpenAI Gym to the control of a drone that runs with ROS.

-> Machine Learning with OpenAI Gym on ROS Development Studio
http://www.theconstructsim.com/machine-learning-openai-gym…/
You can now train your robot to navigate through an environment filled with obstacles just based on the sensor inputs, with the help of OpenAI Gym. In April 2016, OpenAI introduced “Gym”, a platform for developing and comparing reinforcement learning algorithms. Reinforcement learning is an area of machine learning that allows an intelligent agent (for example, robot) to learn the best behaviors in an environment by trial-and-error. The agent takes actions in an environment so as to maximize its rewards. We have deployed the gym_gazebo package from Erle Robotics S.L. in the ROS Development Studio. It enables the users to test their reinforcement learning for their robots in Gazebo.

-> Video Tutorials
* [ROS tutorial] OpenAI Gym For ROS based Robots 101 Course: https://youtu.be/o9FpZ1QQqcc
* How to start with OpenAI + ROS fast: http://www.theconstructsim.com/start-openai-ros-fast/
* LIVE-Class: How to use OpenAI to train your robot (Part1): https://youtu.be/L7mlz7I8RbI
* LIVE-Class: How to use OpenAI to train your robot (Part2): https://youtu.be/FYdS3-c2lKw

翻譯年糕

分享一下ROS相關機器人平台與模組的經銷商~~
ROSComponents
由Robotnik Automation分立出來

網頁:
https://www.roscomponents.com/en/

這不是葉佩雯~

你可以在裡面找到很多ROS supported的模組
相關的spec還有建議售價~~~
某種程度上應該有參考價值 吧??XD

https://www.youtube.com/watch?v=8ksO0yNtpgo&t=17s

Making robots with ROS : differential drive, SLAM gmapping

1.Sensors:
1.1 optical encoder
1.2 Bosch IMU : bno055 usb stick
1.3 YDLidar X4
2.Motor Drive:
2.1 Arduino Uno
2.2 Pololu Dual VNH5019 for Arduino(12A) or L298
3. ROS Package:
3.1 ros_arduino_bridge(Differential robot motor driver)
3.2 rplidar_ros （lidar driver）
3.3 bno055_usb_stick（IMU driver）
3.4 robot_localization （EKF Algorithm）
3.5 slam_gmapping （2-d occupancy grid map Algorithm)

4. reference:
4.1 HyphaROS Workshop https://github.com/Hypha-ROS/hypharos_minibot
4.2 https://github.com/josephchen5/robot_sensors/wiki

翻譯年糕

Call for Contributions: ROS Developers Conference 2018

-----------------------------------------------------------------------
Date: July 7-8, 2018
Website: http://www.rosdevcon.com
-----------------------------------------------------------------------

[ OVERVIEW ]

The first **ROS Developers Online Conference** is a completely practical conference for ROS developers. The conference aims to connect ROS developers around the world without geographical restrictions and to advance ROS levels through real-time practice.

We will host eight top ROS developers to give tutorials of real ROS projects: during the conference, all participants will program together the projects at the same time with the speaker.

- All the participants will have to practice at the same time with the speaker along the conference.
- No installation of anything required. Only require a computer and internet connection. Any type of computer will work.
- All the participants will have full access to the ROS development studio for programming
- All participants will receive a pdf document with all the steps described during the conference
- All the participants will receive a copy of the ROS Developers Guide e-book.
- Each speech will be 30 minutes plus 10 minutes Q&A.

[ CALL FOR TUTORIALS ]

* The proposals must be sent to this address: tutorial@rosdevcon.com
* Submission deadline: April 30, 2018
* The tutorial should last 30 mins + 10 mins Q&A

Tutorial should target fields of robotics using ROS and focus on practice, in order to provide a real practical conference to participants and to exchange developing research results and ideas. The submission of a tutorial must contain the following information:
- Title
- Speaker Information
- Why do you prefer ROS?
- Statement of objectives: what is your speech about and what are you going to make attendants practice

If your tutorial is accepted, you will have to prepare the following material (with our support):
- A notebook with the tutorial
- Package with pre-defined code for participants

[ ORGANIZERS ]

The Construct ( http://www.theconstructsim.com/ )
You can contact us with questions and doubts here: info@rosdevcon.com

翻譯年糕

似乎沒人分享
所以貼一下~~
ROSCon2018 在馬德里
(依樣在IROS前幾天)
https://roscon.ros.org/2018/

今年是由Erle Robotics協辦
有興趣的人可以看看Sponsor區
可以看看目前有哪些機器人廠商贊助/使用ROS

有Google, Amazon, 還有凌華ADLINK !!

Hypha ROS Workshop 說這專頁讚 2018年4月2日

[HyphaROS] Legged Robot Simulation, Trajectory Optimization and Visualization

又是一個小編最近在進行的side project
這是用之前提到的ETHZ-RSL所有的開源ROS Package呈現出來的成果, 背後是套用ipopt去解nonlinear optimization的問題(效能與成果會與選用的CPU chip有關~)

目前支援多種model (1足, 2足, 4足 & 多旋翼)
可切換多種地形 (亦可自行建立model or 地形)

測試影片如下:
https://youtu.be/BXWUi822rKA

最後
對ROS有興趣的, 歡迎加入 # ROSTaiwan

LeggedRobot: 3D Simulation, Trajectory Optimization with Nonlinear Solvers (ROS) All source code are released by ETHZ (BSD) HyphaROS: https://hypharosworksho... 關於這個網站 youtube.com Legged Robot Simulation, Trajectory Optimization and Visualization LeggedRobot: 3D Simulation, Trajectory Optimization with Nonlinear Solvers (ROS) All source code are released by ETHZ (BSD) HyphaROS: https://hypharosworksho... LeggedRobot: 3D Simulation, Trajectory Optimization with Nonlinear Solvers (ROS) All source code are released by ETHZ (BSD) HyphaROS: https://hypharosworksho...