Panda robot action units

[qgallouedec]

Panda robot action units

[qgallouedec]

Action is actually indirectly a force. The timestep only sets the time during which this pseudo-force is applied.

TLDR:
First, the action is multiplied by 0.05 (0.2 for the finger action). The output is the target displacement (e.g. if the action is [0.1, 0.0, 0.0] then the target position of the gripper is its position + 5mm in the x direction).
Then, the pybullet physics engine performs an inverse kinematics to obtain the target angles of the joints. Then, PyBullet uses a PD controller to compute the torque applied on each joint.
Thus, we can think of the action as a virtual force applied at the gripper.