I am having a confusion with tf. So, I am working on a grasping project. my vision partner is giving me pose of an object in camera frame or when running robot, the robot's kinect frame. Now, in order to grasp that object, I need to get the pose in robot's baselink frame as this frame is used by moveit interface. Initially, my thinking was that I can do that using lookup transform method of tf but now I have come to know that this only gives transformation between different frames. In order to get what I need, which is object's location in baselink frame, I should use transformListener method. I am still confused about the difference between the two. I am working with python. If anyone could give me a sample working transformListener code, that would be helpful as well.