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

46
/ 100
Emerging

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.

industrial-robotics robot-manipulation task-automation robot-learning sim-to-real-transfer
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

118

Forks

28

Language

Jupyter Notebook

License

BSD-2-Clause

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.