New Robot Can Ask for Clarification
Author(s): Scott Douglas Jacobsen
Publication (Outlet/Website): Conatus News/Uncommon Ground Media Inc.
Publication Date (yyyy/mm/dd): 2017/04/29
The World Economic Forum (WEF) reported on a new technology which is a combination of natural language processing, speech recognition, biometrics, video analytics, neural networks, and other computational processes. The novel algorithm allows robots to ask for clarification if unsure as to the request from a human operator. The algorithm permits robots to receive speech commands and information based on human gesturing. It is one form of information processing and commanding human beings use consistently.
Professor of computer science at Brown University, Stefanie Tellex, said, “Fetching objects is an important task that we want collaborative robots to be able to do…But it’s easy for the robot to make errors, either by misunderstanding what we want, or by being in situations where commands are ambiguous.”
It is non-verbal communication. When given the speech and gestural command, the robot was better at interpretation of the information than either one alone. Of course, computers can run into problems. This is one important reason for this new algorithm to allow computers to be able to understand human commands.
“When we ask someone for an object, we’ll often point to it at the same time. The new research shows that when robots received both speech commands and gestures, they got better at correctly interpreting user commands.” Tellex said.
If the computer is needed to only understand the question or query, and also to get information for the answer appropriately or to act accordingly, it needs to know what is being asked of it. Therefore, the speech and gesture command combination is important for computers now and into the future when given commands by human beings.
Now, the computer does not look to ask a question based on every single uncertainty. It will decipher, calculate, and then ask accordingly in an intelligent manner. The robot had performed so well in one experiment that participants in the study thought that the computer had capabilities that it did not in fact have.
One of the important features of the system is that the robot doesn’t ask questions with every interaction. It asks intelligently. And even though the system asks only a very simple question. The algorithm allows the robot to make inferences based on the answer.
The research was presented at the International Conference on Robotics and Automation in Singapore, and received funding from the Defense Advanced Research Projects Agency and NASA.
License
In-Sight Publishing by Scott Douglas Jacobsen is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Based on a work at www.in-sightpublishing.com.
Copyright
© Scott Douglas Jacobsen and In-Sight Publishing 2012-Present. Unauthorized use and/or duplication of this material without express and written permission from this site’s author and/or owner is strictly prohibited. Excerpts and links may be used, provided that full and clear credit is given to Scott Douglas Jacobsen and In-Sight Publishing with appropriate and specific direction to the original content. All interviewees and authors co-copyright their material and may disseminate for their independent purposes.
In-Sight Publishing 