Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Human following robot application #23

Open
AswinP7 opened this issue Dec 8, 2020 · 3 comments
Open

Human following robot application #23

AswinP7 opened this issue Dec 8, 2020 · 3 comments

Comments

@AswinP7
Copy link

AswinP7 commented Dec 8, 2020

Is it possible to implement human following robot with this leg_tracker source. We can only do the detection and tracking legs by using this source code .
Is there any possibility of implementing human following application with this source.
Please do respond

Thank you in advance,
Aswin P

@pmirabel
Copy link

pmirabel commented Jan 8, 2024

Hi, we implemented such functionnality with a former coworker.
From what I recall, we follow that path :

  • Train model with our own datasets as described in README
  • implemented leg_tracker with people_tracker to get /people_tracked
  • tuned params to get decent information regarding our usecase
  • created a node that use /people_tracked to issue /cmd_vel (basic PID control)

Depending on the quality of your odomframe, you can do that in odom frame or robot frame.
Let me know if you succeed !

@wikigust
Copy link

Hi, we implemented such functionnality with a former coworker. From what I recall, we follow that path :

  • Train model with our own datasets as described in README
  • implemented leg_tracker with people_tracker to get /people_tracked
  • tuned params to get decent information regarding our usecase
  • created a node that use /people_tracked to issue /cmd_vel (basic PID control)

Depending on the quality of your odomframe, you can do that in odom frame or robot frame. Let me know if you succeed !

Hey I would like to ask on how you worked around the robot moving through narrow aisle, how I'm doing it currently is by using the people tracked position and calculating the distance and angle to get the velocity needed by the robot to move to the person. What I'm facing right now is when going through narrow aisle, the angle that the robot takes in makes it hit the aisle itself. I'm curious if you've ever encountered this issue and if you did, did you overcome them?

@pmirabel
Copy link

Hey I would like to ask on how you worked around the robot moving through narrow aisle, how I'm doing it currently is by using the people tracked position and calculating the distance and angle to get the velocity needed by the robot to move to the person. What I'm facing right now is when going through narrow aisle, the angle that the robot takes in makes it hit the aisle itself. I'm curious if you've ever encountered this issue and if you did, did you overcome them?

Sorry for the late reply.
From what I recall:

  • we started by tuning the control to minimize occurence (eg. shorten target distance to people, modify cmd_vel control to privilege linear move ...)
  • then, we implemented a hybrid control that toggle between this control and navigation stack autonavigation (to follow waypoints based on the people tracked positions + eventually persisted one).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants