Quantcast
Channel: ROS Answers: Open Source Q&A Forum - RSS feed
Viewing all articles
Browse latest Browse all 1441

[python] Planning and executing a trajectory with joint_states waypoints.

$
0
0
Hi people, I am using a neural network to generate a sequence of joint states which represent a trajectory for my robotic arm (7 DOF - franka emika panda). I have tried sending directly the joint states in each iteration with MoveGroupCommander.go() but this results in a really really slow execution (even if I have removed acceleration/speed limits in joint_limits.yaml). So I would like to generate a trajectory in advance and THEN execute it in one shot, hoping this will result in a faster/smoother execution (if you have other suggestions... they're welcome). How should I proceed? I have found nothing in the docs that helped me out. I have found cartesian waypoints trajectories but that's not what I need, I specifically need joint_states. I think I may use IK but given it's 7DOF I don't know if that would be as accurate. note: I am working only with moveit simulations. I have no access to the real robot. Thanks for the help. Best, Oliviero

Viewing all articles
Browse latest Browse all 1441

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>