This website uses its own and third-party cookies. Some of these cookies are used to develop analytical statistics of visits to the webpage, others to manage advertising or even others are necessary for the correct management of the site. If you continue to browse or click in accept we consider you accept the conditions for their use. You can get more information, or learn how to change the settings in our cookies policy?
Versión Española Versión Mexicana Ibercampus English Version Version française Versione italiana

17/10/2017  
    Ibercampus  | Editorial Board | Who we are | Ideology | Contact | Advertising rates | Subscription | RSS RSS
Policies
Inclusion policies
R&D
Employment
Economics
Culture
Green strategies
Health
Society and consumer
Sports
Debates
Interviews
Education
Grants & internships
Training
Trends
Enterprises & CSR
 Enterprises & CSR
AEGON
AIR LIQUIDE
ALCATEL-LUCENT
ALLIANZ
ARCELORMITTAL
ASSICURAZIONI GENERALI
AXA
BANCO SANTANDER
BASF
BAYER
BBVA
BNP PARIBAS
CARREFOUR
DAIMLER AG
DEUTSCHE BANK
DEUTSCHE BRSE
DEUTSCHE TELEKOM
E.ON
ENEL
ENI
FORTIS
FRANCE TLCOM
GROUPE DANONE
IBERDROLA
INDITEX
ING GROUP
INTESA SANPAOLO
L'ORAL
LVMH
MUNICH RE
NOKIA
PHILIPS
RENAULT
REPSOL YPF
RWE
SAINT GOBAIN
SANOFI-AVENTIS
SAP AG
SCHNEIDER ELECTRIC
SIEMENS AG
SOCIT GNRALE
SUEZ
TELECOM ITALIA
TELEFNICA
TOTAL S.A.
UNICREDIT
UNILEVER
VINCI
VIVENDI
VOLKSWAGEN

EDUCATION
Brown University

Research makes robots better at following spoken instructions


A new software system helps robots to more effectively act on instructions from people, who by nature give commands that range from simple and straightforward to those that are more complex and imply a myriad of subtasks.
Ibercampus 17/7/2017 Send to a friend
Comparte esta noticia en TwitterFacebookTwitterdel.icio.usYahooRSS
A new system based on research by Brown University computer scientists makes robots better at following spoken instructions, no matter how abstract or specific those instructions may be. The development, which was presented this week at the Robotics: Science and Systems 2017 conference in Boston, is a step toward robots that are able to more seamlessly communicate with human collaborators.
The research was led by Dilip Arumugam and Siddharth Karamcheti, both undergraduates at Brown when the work was performed (Arumugam is now a Brown graduate student). They worked with graduate student Nakul Gopalan and postdoctoral researcher Lawson L.S. Wong in the lab of Stefanie Tellex, a professor of computer science at Brown.
"The issue we're addressing is language grounding, which means having a robot take natural language commands and generate behaviors that successfully complete a task," Arumugam said. "The problem is that commands can have different levels of abstraction, and that can cause a robot to plan its actions inefficiently or fail to complete the task at all."
For example, imagine someone in a warehouse working side-by-side with a robotic forklift. The person might say to the robotic partner, "Grab that pallet." That's a highly abstract command that implies a number of smaller sub-steps -- lining up the lift, putting the forks underneath and hoisting it up. However, other common commands might be more fine-grained, involving only a single action: "Tilt the forks back a little," for example.

Those different levels of abstraction can cause problems for current robot language models, the researchers say. Most models try to identify cues from the words in the command as well as the sentence structure and then infer a desired action from that language. The inference results then trigger a planning algorithm that attempts to solve the task. But without taking into account the specificity of the instructions, the robot might overplan for simple instructions, or underplan for more abstract instructions that involve more sub-steps. That can result in incorrect actions or an overly long planning lag before the robot takes action.

But this new system adds an additional level of sophistication to existing models. In addition to simply inferring a desired task from language, the new system also analyzes the language to infer a distinct level of abstraction.

"That allows us to couple our task inference as well as our inferred specificity level with a hierarchical planner, so we can plan at any level of abstraction," Arumugam said. "In turn, we can get dramatic speed-ups in performance when executing tasks compared to existing systems."

To develop their new model, the researchers used Mechanical Turk, Amazon's crowdsourcing marketplace, and a virtual task domain called Cleanup World. The online domain consists of a few color-coded rooms, a robotic agent and an object that can be manipulated -- in this case, a chair that can be moved from room to room.

Mechanical Turk volunteers watched the robot agent perform a task in the Cleanup World domain -- for example, moving the chair from a red room to an adjacent blue room. Then the volunteers were asked to say what instructions they would have given the robot to get it to perform the task they just watched. The volunteers were given guidance as to the level of specificity their directions should have. The instructions ranged from the high-level: "Take the chair to the blue room" to the stepwise-level: "Take five steps north, turn right, take two more steps, get the chair, turn left, turn left, take five steps south." A third level of abstraction used terminology somewhere in between those two.

The researchers used the volunteers' spoken instructions to train their system to understand what kinds of words are used in each level of abstraction. From there, the system learned to infer not only a desired action, but also the abstraction level of the command. Knowing both of those things, the system could then trigger its hierarchical planning algorithm to solve the task from the appropriate level.

Having trained their system, the researchers tested it in both the virtual Cleanup World and with an actual Roomba-like robot operating in a physical world similar to the Cleanup World space. They showed that when a robot was able to infer both the task and the specificity of the instructions, it responded to commands in one second 90 percent of the time. In comparison, when no level of specificity was inferred, half of all tasks required 20 or more seconds of planning time.
"We ultimately want to see robots that are helpful partners in our homes and workplaces," said Tellex, who specializes in human-robot collaboration. "This work is a step toward the goal of enabling people to communicate with robots in much the same way that we communicate with each other."

Other issues Education
Fourth Regional SDG4-Education 2030 Partners Meeting
4th Youth Summit highlights crucial role of youth within the Africa-EU Partnership
Downward trend in the share of persons at risk of poverty or social exclusion in the EU
Sakharov Prize 2017 finalists announced
How dance can helps students to develop skills
House prices up by 3.8% in the euro area
4th Africa-Europe Youth Summit opens in Abidjan
Graphene set to go from the lab to the marketplace
Googles unveils AI technology devises
9 October World Post Day

Subscribe free to our newsletter
Vanity Fea
Let them have it?
Jos ngel Garca Landa
Financial inclusion
Financial Education For All!
Carlos Trias
Brusselian Lights
European elections (I): which words are more used in the European political manifestos?
Ral Muriel Carrasco
Humor and Political Communication
Comisin de Arbitraje, Quejas y Deontologa (Spain) (3) You cant be too careful
Felicsimo Valbuena
Want your own blog? Want to be read by universities?
Find out here
Books
Originals: How Non-Conformists Move the World (Adam Grant)
The Econocracy "On the Perils of Leaving Economics to the Experts"
The Sum of Small Things "A Theory of the Aspirational Class"
Signals "How Everyday Signs Can Help Us Navigate the Worlds Turbulent Economy "
Millionaire Teacher "The Nine Rules of Wealth You Should Have Learned in School"
​​​​​​​Alvin Roth: "Who Gets What ― and Why"
Theses and dissertations
1 Most Europeans believe being in EU benefits their country
2 South Summit 2017, the leading entrepreneur event launched in Madrid
3 Fourth Regional SDG4-Education 2030 Partners Meeting
4 Europe publishes assessment of offers to host European Banking Authority & European Medicine Agency
5 Downward trend in the share of persons at risk of poverty or social exclusion in the EU
6 4th Youth Summit highlights crucial role of youth within the Africa-EU Partnership
7 International Day for the Eradication of Poverty 17 October
8 Six nominees are for this years Sakharov Prize
9 9 October World Post Day
10 Commission sets out path towards fair taxation of the Digital Economy
Legal Advise | Privacy Policy | Editorial Board | Who we are | Ideology | Contact | Advertising rates | RSS RSS