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

Add ManipulabilityRatioSigmoidMoveIt #19

Open
wants to merge 1 commit into
base: master
Choose a base branch
from

Conversation

InigoMoreno
Copy link

Similar to ManipulabilityRatioMoveit but with an added sigmoid. The sigmoid makes it so that the score is almost always one except when the manipulability ratio is really bad, this makes the total score be the total number of reachable points, which is more understandable.

@marip8 marip8 closed this Jun 7, 2024
@marip8 marip8 reopened this Jun 7, 2024
Comment on lines +185 to +188
double manipulability = jacobian_singular_values.array().prod();
double manipulability_ratio = jacobian_singular_values.minCoeff() / jacobian_singular_values.maxCoeff();
double manipulability_scaled = std::sqrt(manipulability);
double manipulability_measure = std::sqrt(manipulability_ratio);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Remove unused variables

Suggested change
double manipulability = jacobian_singular_values.array().prod();
double manipulability_ratio = jacobian_singular_values.minCoeff() / jacobian_singular_values.maxCoeff();
double manipulability_scaled = std::sqrt(manipulability);
double manipulability_measure = std::sqrt(manipulability_ratio);
double manipulability_ratio = jacobian_singular_values.minCoeff() / jacobian_singular_values.maxCoeff();
double manipulability_measure = std::sqrt(manipulability_ratio);


double score = manipulability_measure;

double shifted_score = 50.0 * (score - 0.15);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why is score the square root of the manipulability ratio? Also what is the significance of the hard-coded numbers 50 and 0.15? It seems like these might need to be parameters to give the user some control over the "width" of the sigmoid

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

Successfully merging this pull request may close these issues.

2 participants