nqanh/affordance-net

AffordanceNet - Multiclass Instance Segmentation Framework - ICRA 2018

48
/ 100
Emerging

This helps robots understand how to interact with objects by identifying what actions can be performed on them. You input images from a camera, and it outputs detected objects along with their 'affordances' (like 'grasp' for a bottle), which can then guide robotic manipulation tasks such as picking up items. Roboticists, automation engineers, or researchers developing intelligent robotic systems would find this useful.

134 stars. No commits in the last 6 months.

Use this if you are developing robotic systems that need to perceive objects in their environment and understand how to interact with them, particularly for tasks like grasping or pouring.

Not ideal if you are looking for a general-purpose object detection tool without the need for detailed interaction capabilities or if you do not have access to GPU hardware.

robotics robotic-grasping computer-vision automation human-robot-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

134

Forks

52

Language

Jupyter Notebook

License

Last pushed

Sep 12, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nqanh/affordance-net"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.