pathak22/modular-assemblies
[NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"
This project helps researchers and developers explore how to design and control complex, self-assembling robotic systems. It takes in specifications for modular "agent" parts and training parameters, then outputs policies for how these parts can combine and move to achieve tasks. This is ideal for robotics researchers, AI developers, and those working on adaptive systems or virtual creature design.
117 stars. No commits in the last 6 months.
Use this if you are researching how to create intelligent, adaptable systems from simple components that can dynamically assemble and coordinate to perform new functions without explicit pre-programming.
Not ideal if you need a plug-and-play solution for controlling an existing physical robot or a general-purpose reinforcement learning library without a focus on self-assembly.
Stars
117
Forks
16
Language
Python
License
—
Category
Last pushed
Dec 13, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pathak22/modular-assemblies"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
enactic/openarm
A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.
Shuijing725/awesome-robot-social-navigation
A curated list of robot social navigation.
thomashiemstra/fred
This my 3d printed robot arm project
jstmn/ikflow
Open source implementation to the paper "IKFlow: Generating Diverse Inverse Kinematics Solutions"
sizhe-li/neural-jacobian-field
Controlling diverse robots by inferring jacobian fields with deep networks! Let's make robots...