Mujoco and MoveIt!

Question

I want to implement deep reinforcement learning using a UR5 robot. A little research told me nowadays researchers are using openAI gym, Mujoco, rllab as their frameworks. The thing is, I want to train my UR5 robot in virtual environment and transfer the learning to my real robot. The task can be peg insertion.

Previously I worked on a project using ROS with the UR5 robot and a Kinect. In that project, we are using MoveIt for motion planning. Everything has already been set up and I'm quite familiar with ROS and MoveIt.

Do you think I should bother myself modeling the UR5 robot and adding RGBD camera using Mujoco (I am not sure if I can do this in Mujoco), and after that training it using openAI gym framework, and finally transferring learning to the real robot using ROS? Or should I stick with ROS and MoveIt while incorporating openAI gym only as my reinforcement learning framework? I just don't see why I need Mujoco if I can use MoveIt and gazebo for modeling, which is already done. Thanks for your advice on this.

Answer 1

You will need MuJoCo if you care about robust physics predictions.

For UR5 robot, we have created a model for MuJoCo here. This is, however, a planar robot. We have removed the joints from UR5 and we are using it as a planar robot for now. You can use it as a starting point, however.

Another solution is to use OpenRAVE simulator. We wrote a controller for UR5 specifically. It's available here. OpenRAVE will probably be the best option given the controller mentioned. If you want physics-predictions it gets a bit tricky, however. But using OpenRAVE and the UR5Controller provided you will be able to plan in simulation and then execute on the real robot.

Answer 2

The question would have been easier to answer had you put links to the various packages you intended to use.

Is there a reason you don't want to use Gazebo (the simulator which is normally used with ROS)? You might be able to find the UR5 robot and RGBD camera already created for Gazebo.

I would do as you suggest in the last paragraph of your question. You can use whatever planner and learning you want to with ROS.