Comments (3)
In general, you can test out the arm manipulation environment using the command
python3 -m assistive_gym --env "ArmManipulationSawyer-v1"
The figure you linked to is an example in which human preferences are disabled. This is done by commenting out this line: https://github.com/Healthcare-Robotics/assistive-gym/blob/main/assistive_gym/envs/arm_manipulation.py#L28
and then training a new robot control policy (see the Wiki: https://github.com/Healthcare-Robotics/assistive-gym/wiki/5.-Training-New-Policies).
The human arms have two types of joint limits. The first is pose-independent hard limits, which are set here: https://github.com/Healthcare-Robotics/assistive-gym/blob/main/assistive_gym/envs/human_creation.py#L217
The second type of joint limits that are applied to the arms are pose-dependent limits (put your hand behind your back and you will likely notice it is more difficult to fully bend your elbow). Pose-dependent joint limits are applied here: https://github.com/Healthcare-Robotics/assistive-gym/blob/main/assistive_gym/envs/agents/human.py#L129
from assistive-gym.
For Google Colab, you can edit this notebook to use the environment ArmManipulationSawyer-v1
https://colab.research.google.com/drive/1PAY5HnLKRB-TBsPaevRr6myMfpVt_yzF?usp=sharing
Here is an example of training a new policy in Google Colab.
https://colab.research.google.com/drive/1P6zYEL2Pfq7GOCtmoLlRNGrKkPQTVAQF?usp=sharing
from assistive-gym.
Thank you for your messages. How can we use this Assistive Gym Arm Manipulation example in ROS?
from assistive-gym.
Related Issues (20)
- Strange issue with training cooperative scratch environment HOT 3
- Reproducing Cooperative ItchScratch results HOT 2
- Issue with creating a new environment HOT 2
- ValueError when using SAC with co-optimization HOT 1
- About p.setGravity HOT 1
- Issue Create New Environment HOT 1
- Transfer learned policy to actual robot
- Action space for FeedingSawyer HOT 3
- Import Custom 3D Objects HOT 2
- Run trained policies for active human environments on static human environments HOT 2
- Can't load "human" environments HOT 1
- Hi, I can't train ppo on tutorial HOT 1
- Hi, i can't run the env_viewer.py HOT 2
- Add a new type of robot HOT 2
- ('Observation ({}) outside given space ({})!' Error when trying to train model HOT 4
- When I do "env = gym.make", I get an error "PicklingError: Could not pickle object as excessively deep recursion required. HOT 2
- Issue running Assistive_Gym_Basics.ipynb colab notebook HOT 2
- Unable to build Dockerfile
- ValueError: high - low < 0 for env.reset()
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from assistive-gym.