/FETCH_SERVER

avoid obstacle in gazebo

Primary LanguagePython

training fetch reach the certain goal in gazebo

we had used the DQN for fetch reach trail

but the performance don't well

Using DDPG for training fetch reach goal

you can find fetch and environment class in here

DDPG algorithm in here

main function entrance in here

RGB+D to xyz

we have trained a network which can get xyz in simulate(gazebo) for img with deep.

there have a fetch_gazebo world (including obstacle model, fetch and the world)

if you are ubuntu you can try

sudo apt-get install ros-indigo-fetch_*

then you will install fetch package in /opt/ros/indigo/share/...(i copy the package from here);

you can get xyz from img by:

python demo.py

Using Multi-GPU:

Except put your data and model in GPU, you need to using follow coda:

device_ids = [0, 1]
net = Net().cuda(device_ids[0])
net = nn.DataParallel(net, device_ids=device_ids)
optimizer = torch.optim.Adam(eval_net.parameters(), lr=LR) 
optimizer = nn.DataParallel(optimizer, device_ids=device_ids)
optimizer.module.step()