sayantanauddy/clfd
Code for the paper Continual Learning from Demonstration of Robotic Skills
This project helps robotics engineers train robots to perform a series of new movement tasks, like writing letters or manipulating objects, without forgetting previously learned skills. You provide the robot with kinesthetic demonstrations (guiding its movements), and it learns the trajectory for each task. The output is a robot capable of recalling and executing all learned movements, even after being taught many new ones.
No commits in the last 6 months.
Use this if you need a robot to continuously learn new physical tasks from human demonstrations and retain all prior skills without needing to store old training data.
Not ideal if your robot learns skills through methods other than kinesthetic demonstration or if it only needs to learn a single skill at a time.
Stars
34
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sayantanauddy/clfd"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aimagelab/mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of...
LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
GMvandeVen/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR,...
LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.