Robot Learning Manipulation Action Plans by “Watching” Unconstrained Videos from the World Wide Web

From Yezhou Yang, Yi Li, Cornelia Fermuller and Yiannis Aloimonos:

In order to advance action generation and creation in robots beyond simple learned schemas we need computational tools that allow us to automatically interpret and represent human actions. This paper presents a system that learns manipulation action plans by processing unconstrained videos from the World Wide Web. Its goal is to robustly generate the sequence of atomic actions of seen longer actions in video in order to acquire knowledge for robots. The lower level of the system consists of two convolutional neural network (CNN) based recognition modules, one for classifying the hand grasp type and the other for object recognition. The higher level is a probabilistic manipulation action grammar based parsing module that aims at generating visual sentences for robot manipulation.


The list of the grasping types.

Experiments conducted on a publicly available unconstrained video dataset show that the system is able to learn manipulation actions by “watching” unconstrained videos with high accuracy.... (article at Kurzweilai.net) (original paper)

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

Affordable Excellence: The Go-To Tool for Finding Compressed Air Leaks

Affordable Excellence: The Go-To Tool for Finding Compressed Air Leaks

Find compressed air leaks fast with FLIR's new cutting-edge Si1-LD acoustic imaging camera. Leveraging advanced ultrasonic technology and onboard analytics, this affordable camera pinpoints leaks and quantifies incurred losses even in the nosiest environments. Upgrade your maintenance routine with the cost-effective FLIR Si1-LD - significantly reduce energy costs and increase system uptime. Get Started Today.