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

arm[RRTConnectkConfigDefault]: Unable to sample any valid states for goal tree #38

Closed
kctoayo88 opened this issue Apr 29, 2019 · 3 comments

Comments

@kctoayo88
Copy link

Hi,

I am using ROS Kinetic, KInect V2 and Motoman MH5 Robot and trying to use the easy_handeye in my project.

When I click the check starting pose button, I got this error.

[ERROR] [1556533936.017165846]: arm[RRTConnectkConfigDefault]: Unable to sample any valid states for goal tree

I already check my urdf and didn't find any problem, and it works fine in demo.launch file.

2019-04-29 18-35-36 的螢幕擷圖

Hope you cloud help me with this trouble.

Thanks a lot !

@marcoesposito1988
Copy link
Collaborator

Hi @kctoayo88,

this means that the planner does not manage to move the robot in one direction starting from the current position of the robot.

You might try positioning the robot in a way such that its "hand" can rotate a bit about all axis, and translate in all directions, without reaching a joint limit.

The GUI automatically tries to move the robot in all directions before starting the procedure, to avoid giving an error in the middle of the calibration procedure (or at the end, which would be even more infuriating).

@kctoayo88
Copy link
Author

kctoayo88 commented Apr 30, 2019

@marcoesposito1988 thanks for your reply.

I already tried to change the direction and angle of robot in many cases, but still can't work.
Is it any other solution could help me complete it?

I was trying to operate it manually, but result is poor.
Hope you could give me more tips of it.

Thanks a lot.

Edit:
I searched the some tutorials about this.
I guess it may be a joint limit problem, could you check it for me?
PS. My robot is not the same type of UR5.

@marcoesposito1988
Copy link
Collaborator

I think that the problem is not the orientation, but the fact that the robot is already at the edge of its workspace (i.e. it is almost fully elongated).

You may try again moving the end effector towards the base of the robot.

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

2 participants