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

ATI Industrial Automation at IMTS 2018

ATI Industrial Automation at IMTS 2018

ATI Industrial Automation's MC-10 Manual Tool Changer provides a cost-effective solution for quickly changing tools by hand. Its compact yet robust design is optimized for collaborative robot applications. The ergonomic twist-collar locking mechanism ensures a secure attachment of the tool and easy manual operation with tactile feedback. This Manual Tool Changer can carry payloads of up to 22 lbs and includes multiple fail-safe features that resist vibration and prevent loosening. The MC-10 Manual Tool Changer has integrated air pass-through connections and options to connect electrical utilities if needed. ATI will feature the new MC-10 along with a variety of other robotic demonstrations and product displays at this year's IMTS show in Chicago (Booth #236417).