Skip to content

greet_demo_en

Jump to bottom
Juan Rojas edited this page Dec 2, 2016 · 1 revision

<< back to Mainpage

EN | 中文

#Demo 3 - Greet Demo

#####Navigation

  1. Summary
  2. Video
  3. Quickstart
  4. Structure
  5. FAQ




###Summary

Greet Demo is a function that let baxter can talk with people and react accordingly, such as showing a happy or sad face, shacking hands with people , looking at people and using voice to answer the questions.
#####Files Location:

  • ./demos/GreetDemo/voice_nav.py

###Video

IMAGE ALT TEXT

###Quickstart

Before you run this node, please make sure your computer have been connected to the baxter.Then launch:

1.let the baxter follow your face
$ roslaunch baxter_demos baxter_face_follower.launch


2.let the baxter hear and understand your words.
$ roslaunch rbx1_speech voice_nav_commands.launch


3.let the baxter react to your words.
$ rosrun baxter_examples voice_nav.py


4.allow the baxter to speak.
$ rosrun sound_play soundplay_node.py


5.allow the baxter to move.
$ rosrun baxter_interface joint_trajectory_action_server.py

Then you can say words like hello or byebye and it will react.

To read more detail or find the solutions to some problems, please refer to FAQ part below.


###Structure

Only one file, voice_nav.py.
1st it receives commands from recognizer.py which is used by voice_nav_commands.launch, and it reacts in different way according to the command.
2nd it runs many nodes: xdisplay_image.py for following face, soundplay_node.py for speaking, joint_trajectory_file_playback.py for moving its hands as plan.


###FAQ

Q1. Where is the face follower launch file?
A1. Its location is sysu_baxter/demos/face_tracker,more details can be found at https://github.com/sysurobotics/sysu_baxter/wiki/face_follower_en.

Q2. How to get the packages for speech recognition?
A2. install the ROS pocketsphinx package for speech recognition by running as follows:

  $ sudo apt-get install gstreamer0.10-pocketsphinx
  $ sudo apt-get install ros-indigo-pocketsphinx
  $ sudo apt-get install ros-indigo-audio-common
  $ sudo apt-get install libasound2
  $ sudo apt-get install gstreamer0.10-gconf

**Q3**. Where is the rbx1_speech?
**A3**. You can download it from github repository by typing this: ### $ git clone https://github.com/pirobot/rbx1.git
**Q4**. where does the package sound_play come from?
**A4**. It has been installed in Q2 by typing: ### $ sudo apt-get install ros-indigo-audio-common $ sudo apt-get install libasound2
**Q5**. The baxter can't understand my word successfully.
**A5**. You need to update your nav_command which is located in rbx1_speech/config,this can help your baxter know more vocabularies.
To do so,first open nav_command.txt and add the word you want to say at the end of the file.
Then upload it to http://www.speech.cs.cmu.edu/tools/lmtool-new.html where you can get a zip file.
Finally change every file's name to nav_command and put all of them into rbx1_speech/config.
### **Q6**. How can I get more details about sound recognition and sound play?
**A6**. The book *ros_by_example_indigo_volume_1*, chapter 9,it is a good guidance for studying about ros.
If you have any more questions,please contact 772018253@qq.com.

https://github.com/birlrobotics

Clone this wiki locally