One of the central challenges facing modern robotics is developing robots that behave more like humans. Although advances in AI technology are giving machines a better sense of how to navigate their surroundings, there is still a large disconnect in the way they work in conjunction with humans.

A European initiative called RoboHow, founded in 2012, is responding to that challenge by creating systems that would help robots learn and communicate (sometimes using actual language), akin to human beings. The point is to try and do away with preprogramming these machines to perform certain tasks and give them the ability to put information together, use it, and then remember it for the future.

The German robot PR2 – backed by the RoboHow team – is an example of a step in the right direction. The PR2 is engineered to process written instructions from websites like WikiHow and then physically perform the associated tasks. For now, the robot testing is interested in the kitchen – specifically pancakes – which may seem like a small task, but it requires an intricate framework of prior knowledge of micro-tasks that humans take for granted — such as the amount of pressure required to open a container.

Ideally, the PR2 would gain that knowledge, use it in its environment, and communicate what it has learned to an online database called OpenEase. This would create an open, ubiquitous repository of growing knowledge for any robot to access and learn from. 

According to the MIT Technology Review, researchers are also considering techniques that would help robots learn from physically watching humans perform certain tasks. This would include studying virtual-reality data after humans have performed these tasks wearing tracking gloves.

The ultimate goal would be creating a set of robots that could adapt to changing environments and instructions and react in an appropriate manner. The biggest barrier is relaying the semiotics of language into algorithm. Bridging that gap would be a giant step forward in developing robots that learn and grow like humans.

ⓒ 2024 TECHTIMES.com All rights reserved. Do not reproduce without permission.
Join the Discussion