I am working on the distance between a robot (defined by its joints angles) and its configuration space. I want to defined a simple distance to be able to get in which configuration the robot is too close from the environment, and a distance based on joints angles.

I'm working in 6 dimensions (with a 6 DOF robot).

If we fix the last 3 joints of a 6DOF robot, to become a 3 DOF robot, I can used euclidean distance because we can defining most of the angles configuration only with the 3 first joints. But if I take all of the 6 angles, the distance is wrong : the value is too big and I don't know how to define if the robot is under collision or not.

The last 3 joints do not defined the position of the robot but only the TCP but I need them to be sure that the end effector do not touch the envrionement.

I hope my explanations are understanable,

Do you have any clue ?

Thank you in advance

  • $\begingroup$ A continuous cost function maps the robot's angle configuration to a value from 0 to 1. The probability defines how likely it is that the robot will collide with an obstacle in the configuration space. In most cases the cost function can be realized with manually encoded constraints which are summed up and normalized. $\endgroup$ May 3 at 20:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.