jhu-lcsr/good_robot
"Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer
This project provides methods for making industrial robots smarter and more adaptable for complex, multi-step tasks. It takes in visual input (like camera feeds) and natural language commands, enabling robots to learn new manipulation tasks quickly from just a few human demonstrations or simple instructions, without extensive re-training. It's designed for robotics engineers and researchers working with real-world robotic arms in manufacturing or logistics.
118 stars. No commits in the last 6 months.
Use this if you need to rapidly train industrial robots for new, multi-step assembly, sorting, or rearrangement tasks using minimal demonstrations or natural language instructions.
Not ideal if your robot tasks are simple, repetitive, and already well-defined, or if you are not working with robot arms and visual perception.
Stars
118
Forks
28
Language
Jupyter Notebook
License
BSD-2-Clause
Category
Last pushed
Mar 25, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jhu-lcsr/good_robot"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
OpenQuadruped/spot_mini_mini
Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.