You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am currently working on modeling a jump action between two predefined elevated platforms. I followed your excellent bipedal gaits tutorial which allowed me to setup a planner around the jump action (for the talos leg robot). However, I am struggling to incorporate the pair collision residual into the cost function.
Below, I've shared my attempt. Specifically, the additional cost is implemented in the _get_collision_model function, which I call each time a contact occurs—such as when the robot is positioned on the platform at both the start and end of the jump. After running this code several times, with and without the _get_collision_model function calls, I unfortunately observe no significant difference in the results from Crocoddyl...that is, the L2 norm of the initial and final force vectors remains almost identical in both cases.
Could you please advise on what I am missing? What am I doing wrong?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hello!
I am currently working on modeling a jump action between two predefined elevated platforms. I followed your excellent bipedal gaits tutorial which allowed me to setup a planner around the jump action (for the talos leg robot). However, I am struggling to incorporate the pair collision residual into the cost function.
Below, I've shared my attempt. Specifically, the additional cost is implemented in the
_get_collision_model
function, which I call each time a contact occurs—such as when the robot is positioned on the platform at both the start and end of the jump. After running this code several times, with and without the_get_collision_model
function calls, I unfortunately observe no significant difference in the results from Crocoddyl...that is, the L2 norm of the initial and final force vectors remains almost identical in both cases.Could you please advise on what I am missing? What am I doing wrong?
Thank you so much :)
Beta Was this translation helpful? Give feedback.
All reactions