search

qgallouedec / panda-gym

Set of robotic environments based on PyBullet physics engine and gymnasium.
MIT License
548 stars 115 forks source link

Question regarding end-effector control #62

Closed Bargez908 closed 1 year ago

Bargez908 commented 1 year ago

In a previous answer (https://github.com/qgallouedec/panda-gym/issues/53) you said: "First, the raw action is scaled by 0.05. The result is added to the current joint position to obtain the target angles of the joints". Can you explain how you obtain the target angles of the joint from a displacement on the end-effector? I can't find anywhere in the code. thank you in advance!

qgallouedec commented 1 year ago

There are two types of environment, the environment where we control the displacement of the end-effector (PandaReach-v3, PandaPush-v3, ...), and those where we control the displacement of the joints (PandaReachJoints-v3, PandaPushJoints-v3, ...). Your question was about the environments where we control the displacement of the joints. The answer is here. For the environments where we control the end-effector displacement, the answer is here.