Minor Fixes
TextZip opened this issue · comments
@gmargo11 thanks for the amazing repo, it was very intuitive to follow. Looking forward to updates on Deploying a Custom Model
. Here is a video of Go1 running around with the policy.
Here are some minor fixes that could make deployment easier:
Installing the Deployment Utility
- The
cd go1_gym_deploy/scripts && ./send_to_unitree.sh
downloads thedeployment_image.tar
to the scripts folder. While in the next stepcd ~/go1_gym/go1_gym_deploy/installer && ./install_deployment_code.sh
the script searches for thedeployment_image.tar
in/go1_gym/go1_gym_deploy/installer
.
Running the Controller
- There seems to be no safe way to exit the policy, the policy continued to run even after the script was terminated.
Some information that might be helpful for others
-
If you run out of disk space during
cd ~/go1_gym/go1_gym_deploy/installer && ./install_deployment_code.sh
consider changing the script to use 192.168.123.13 instead (at least in my Go1 Edu with 3 Jetson nano, I only had the required disk space to copy the tar and extract the image in only 192.168.123.13). Alternatively, consider deploying on an external PC. -
When deploying on an external PC/NUC, if you get the following error
➜ sudo ./start_unitree_sdk.sh
./lcm_position: 1: Syntax error: word unexpected (expecting ")")
It is likely because the ./lcm_position has been compiled for ARM aarch64
(to run on the jetson), please recompile it for your architecture(external PC/ NUC) using https://github.com/Improbable-AI/unitree_legged_sdk.
@TextZip Thrilled to see the policy running on your Go1! Thanks for sharing the video.
Will you consider submitting a pull request with these fixes and updates to the README? I would be happy to merge it so that you are attributed :)
-Gabe
@TextZip Thanks for your advice! I am trying to deploy on an external NUC too, when I run sudo make autostart
, I got an error
docker: Error response from daemon: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running hook #0: error running hook: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1: cannot open shared object file: no such file or directory: unknown.
make: *** [Makefile:25: autostart] Error 127
I tried to change the docker version, but still get the same error. Could you give me some suggestion to solve it?
Hi @MariaBana ,
I never faced this issue so I'm not entirely sure but did you check this out?
This is probably due to the fact that sudo privileges were used during the installation.
I was installing nvidia drivers and nvidia container toolkit with sudo and when I tried to run the docker container without sudo, I got the exact same error.
@TextZip Thanks for your help! According to the suggestion mentioned in this comment #31 (comment), I solved this problem by directly configuring the environment on the NUC.