visual-pushing-grasping
visual-pushing-grasping copied to clipboard
andyzeng
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
Hello, first of all thanks for sharing your amazing job. I want to know Why the generated real robot‘s color heightmap is not good？My color heightmaps are often deformed and...
# Problem describe Hello I have some problem which is ouccr in training section. I found that there is a certain chance that UR5 will get stuck after grabbing an...
Hello, Friends. When I train the Network, I meet the problem that the UR10 Robot Gripper(DH gripper) often collision with the Block, what should I set the Gripper's Position avoiding...
Excuse me, I opened the v-rep simulation and started to run it. Then I ran main.py on pycharm, but the simulation environment didn't work. This simulation environment was directly brought...
the model consist of four densenet, pushnet and grasp net. the author's paper say only need one Nvidia. its mean that pretrained model will no need to backward? we only...
Connected to simulation. CUDA detected. Running with GPU acceleration. /home/dell1804/ws_grasp/src/visual-pushing-grasping-master/models.py:203: UserWarning: nn.init.kaiming_normal is now deprecated in favor of nn.init.kaiming_normal_. nn.init.kaiming_normal(m[1].weight.data) /home/dell1804/.local/lib/python2.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please...
excuse，i'm the new CoppeliaSim, what directory should i run, my directory dong not have coppeliaSim.sh.
https://github.com/andyzeng/visual-pushing-grasping/blob/master/trainer.py#L363
Hello， Looked at your train.py file, the training data makes the model use the snapshot_file file. In addition, the files called in #def preload(self, transitions_directory): in the file are the...
Hi， I know you use realsence D415 to do this work，however，I only have realsence D435，I want to know if I can use this camera to do this work. Looking forward...
