https://github.com/alan-turing-institute/t-reg-hmi
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
✓Committers with academic emails
3 of 5 committers (60.0%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.3%) to scientific vocabulary
Keywords from Contributors
Repository
Basic Info
- Host: GitHub
- Owner: alan-turing-institute
- License: mit
- Language: C#
- Default Branch: main
- Size: 1.62 GB
Statistics
- Stars: 1
- Watchers: 14
- Forks: 0
- Open Issues: 2
- Releases: 0
Metadata Files
README.md
T-REG-HMI
T-REG-HMI (Turing Reinforcement learning EGxperiment/ Human Machine Interaction) is a project arising from REG Hack Week 2023. It is a companion to T-REG which uses Reinforcement Learning to try to teach a 3D model of a T.rex to walk.
The goal of T-REG-HMI is to produce a Unity scene containing the same 3D T.rex model as is used in T-REG, but to have it human-controlled, with the aim of creating a "beat-the-AI" game, where people can attempt to make the dinosaur walk further than the best effort from the RL agent.
This game can be deployed as either a browser-based web app, a VR app on the Oculus/Meta Quest 2, or (soon) as a remotely controlled webapp that could be played (for example) on a big screen, while controlled by a phone app. Details of each of these are below:
Webapp
The main branch of this repo represents the baseline Unity scene that can be build as a WebGL app that can be played on a browser, and controlled via a keyboard.
The keys to control the dinosaur are as follows:
"q": move left leg forward.
"w": move left leg back.
"o": move right leg forward.
"p": move right leg back.
"d": move tail left.
"f": move tail right.
"z": open jaw.
"x": close jaw.
Instructions on how to build and deploy this game on Azure can be found here.
VR app
The VR2 branch of this repo includes the Unity "XR Interaction Toolkit" and the "Open XR" plugin, to allow it to work on the Oculus/Meta Quest 2.
The controls here are as follows:
left stick: move
right stick: turn (snap turns left and right)
trigger buttons: move leg forward (left and right)
grip buttons: move leg back (left and right)
"X", "A" buttons: move tail.
"Y", "B" buttons: open/close jaw.
Remotely controlled app
TBD.
Owner
- Name: The Alan Turing Institute
- Login: alan-turing-institute
- Kind: organization
- Email: info@turing.ac.uk
- Website: https://turing.ac.uk
- Repositories: 477
- Profile: https://github.com/alan-turing-institute
The UK's national institute for data science and artificial intelligence.
GitHub Events
Total
Last Year
Committers
Last synced: over 2 years ago
Top Committers
| Name | Commits | |
|---|---|---|
| Rosie Wood | r****d@t****k | 17 |
| Oliver Strickson | o****n@t****k | 9 |
| nbarlowATI | n****w@t****k | 7 |
| Rosie Wood | r****d@g****m | 3 |
| mastoffel | m****l@g****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: over 1 year ago
All Time
- Total issues: 2
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 1
- Total pull request authors: 0
- Average comments per issue: 0.5
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- nbarlowATI (2)