National Edu News: IIT Hyderabad-NHAI sign MoU for Transportation Research  |  Cover Story: Elimination Round or Aptitude Test- How to Align CUET with NEP 2020 Goals  |  Life Inspirations: Master of a Dog House  |  Education Information: Climate Predictions: Is it all a Piffle!  |  Leadership Instincts: Raj Mashruwala Establishes CfHE Vagbhata Chair in Medical Devices at IITH   |  National Edu News: TiHAN supports a Chair for Prof Srikanth Saripalli at IIT Hyderabad  |  Teacher Insights: How To Build Competitive Mindset in Children Without Stressing Them  |  Parent Interventions: What Books Children Must Read this Summer Vacation   |  Policy Indications: CUET Mandatory for Central Universities  |  Teacher Insights: Classroom Dialogue for a Better World  |  Rajagiri Round Table: Is Time Ripe for Entrepreneurial Universities in India?  |  Life Inspirations: How to Overcome Fear of Public Speaking  |  Parent Interventions: Wide Ranging Problems of Preterm Infants  |  Technology Inceptions: Smart IoT-based, indigenously-developed, ICU Ventilator “Jeevan Lite” Launched  |  Parent Interventions: Meditation Reduces Guilt Feeling  |  
November 30, 2021 Tuesday 01:44:47 PM IST

Entangled Relations can be now Understood by Artificial Intelligence!

‘In my table there is my laptop and towards it right is a notepad and on top of it lies a pen’. This kind of relationships are easy for us to find. Without knowledge of these kind of relationships, a robot is designed to help someone in a kitchen which would have difficulty in following a command like “pick up the glass that is to the left of the stove and place it on top of a tray”. 

Understanding this problem, MIT researchers have developed a model that understands the relationships between objects in a scene. The new model represents individual relationships one at a time, then combines these representations to describe the overall scene. This enables the model to generate more accurate images from text descriptions, even when the scene includes several objects that are arranged in different relationships with one another. 

This work can be applied in situations where industrial robots need to perform intricate, multistep manipulation tasks, like stacking items in a warehouse or assembling appliances. It also moves the field one step closer to enabling machines that can learn from and interact with their environments more like humans do!


Comments