6. Voice control multi-point navigation

The operating environment and software and hardware reference configurations are as follows:

• Reference model：ROSMASTER X3

• Robot hardware configuration: Arm series master, Slan A1 LiDAR, AstraPro Plus depth camera

• Robot system: Ubuntu (version not required) + docker (version 20.10.21 and above)

• PC VM: Ubuntu (20.04) + ROS2 (Foxy)

• Usage scenario: Used on a relatively clean 2D plane

   

6.1. Description

On the established map, voice control ROSMASTER to navigate to point1, point2, point3. The R2 key on the handle can stop/start this function at any time.

6.2. Steps

6.2.1. Configuration navigation point

1. Enter the docker, run the following command on the termina

   ros2 launch yahboomcar_nav laser_bringup_launch.py
   

2. Open VM, configure multiple machine communication, then run the following command to display the RIVZ node

   xxxxxxxxxx
   ros2 launch yahboomcar_nav display_nav_launch.py
   

3. Execute navigation nodes in docker

   xxxxxxxxxx
   ros2 launch yahboomcar_nav navigation_teb_launch.py
   

4. Click [2D Pose Estimate] on the rviz screen of the VM, compare the posture of the robot to mark the initial posture of the robot on the map

   

5. Compare the overlap between radar scan points and obstacles, the initial posture of the robot can be set several times until the radar scanning point and the obstacle roughly coincide

6. Open another terminal into the docker, then run the following command

   xxxxxxxxxx
   ros2 topic echo /goal_pose   # display /goal_pose topic
   

7. Click [2D Goal Pose], set the first navigation target point, at which point the car begins to navigate. In addition, the topic data is received in Step 6

   

8. Open the code in the following position

   xxxxxxxxxx
   /root/yahboomcar_ros2_ws/yahboomcar_ws/src/yahboomcar_voice_ctrl/yahboomcar_voice_ctrl/voice_Ctrl_send_mark.py
   

   Change the pose of the first navigation point to the one printed in step 7

   

9. Modify the pose of the other 4 navigation points in the same way

6.2.2. Use voice multi-point navigation

1. Enter the docker, run the following command on the terminal

   xxxxxxxxxx
   ros2 launch yahboomcar_nav laser_bringup_launch.py
   

2. Open VM, configure multiple machine communication, then run the following command to display the RIVZ node

   xxxxxxxxxx
   ros2 launch yahboomcar_nav display_nav_launch.py
   

3. Execute navigation nodes in docker

   xxxxxxxxxx
   ros2 launch yahboomcar_nav navigation_teb_launch.py
   

4. Click [2D Pose Estimate] on the rviz screen of the VM, compare the posture of the robot to mark the initial posture of the robot on the map

   

5. Compare the overlap between radar scan points and obstacles, the initial posture of the robot can be set several times until the radar scanning point and the obstacle roughly coincide

6. Open another terminal into the docker, then run the voice control navigation node

   xxxxxxxxxx
   ros2 run yahboomcar_voice_ctrl voice_Ctrl_send_mark
   

7. After calibrating the initial pose in rviz, we can say "Hi Yahboom" to wake up the voice module, until it replies "Hi, i'm here", indicating that the module has been woken up.

8. We say "Go to the point A", it will reply "OK, I'm going to the point A."

6.2.3. Topic graph

xxxxxxxxxx
rqt_graph

6.2.4. Voice control node details

6.3. Voice module communication protocol

You need to configuration navigation point then use voice control