bluerivertech / quanser-openai-driver Goto Github PK

Hello!

I am using Ubuntu 18.04 with Python 3.8.0, and managed to use the flip-controller with the QUBE 2 hardware succesfully. However, when I try to use it with the simulator (by running python tests/test.py --env QubeSwingupEnv --controller flip -s -r), it seems like the controller just immediately swings the arm all the way to the left or right, ending the episode. The same is seen when using other controllers such as "sw".

The simulator still seems to work on its own, though; I can train RL agents against it and get successful results. But there seems to be a deviation between the simulator and hardware due to the controllers not working.

Am I doing something wrong? Could it be that I am using incorrect versions of the required Python modules?

Thanks in advance!
Best Regards

Hi, i would like to create simulink blocks from your quanser openai driver. I know there are already block schemes for simulink from quanser: https://quanserinc.box.com/shared/static/08vjgurb59omat6s1xd9u42m1xhko199.zip
Quarc is needed to run those and since quarc is not available on ubuntu I would like to recreate those for simulink with quanser openai driver. I already sucessfully run 1 of yours examples as Sfunction from matlab with python:
import gym
from gym_brt import QubeSwingupEnv

num_episodes = 10
num_steps = 250

with QubeSwingupEnv() as env:
for episode in range(num_episodes):
state = env.reset()
for step in range(num_steps):
action = env.action_space.sample()
state, reward, done, _ = env.step(action)

How can i create and run basic experiments like those examples in hil sdk written in c using your driver? Is it even possible? I couldn't find any basic example like those in hil sdk.

Hi,
first of all, thanks a lot for providing this interface!

I am also trying to apply the baseline algorithm for PPO on the pendulum. Did you also encounter problems with the interface then? At the end of an episode the rotary arm sometimes crashes against the encoder cable and the program freezes in the reset function when trying to apply a voltage to the Qube. Could not find a solution for this. Did you have similar issues and how did you solve them?

Thanks so much!

Hi, i have qube servo 2 and ubuntu 20.4 server. I did ewrything according to setup and i could run examples from hil_sdk for qube servo 2 without any issue and sound or noise. When i tried command "python3 tests/test.py --env QubeSwingupEnv --controller flip" my qube 2 started to make weird sound so i quickly shut it off. Pendulum was moving but noise scared me so i rather shut it off. I am new in this and i want to be able to run experiments online on qube connected to server. Should it make that noise ? Did i do something wrong? I tried to run that command twice but it was still making the sound. I can still run examples from hil_sdk without problem. Thanks for answer.

Hi!
I am using the simulator to collect preliminary data before moving to the hardware.
I started working on the master branch when I realized that there is a simulator_debug branch. There, in test/check_simulator.py the test for the flip up and hold control returns a different results when using the simulator and the hardware (the hardware stabilizes at the top equilibrium while this does not happen in simulation).
Do you have an idea of what may be causing this problem?

Thanks a lot for your help.