Published By: Brown University, 3/6/2017

>> View the Article <<

Summary

Brown’s Humans to Robots Lab has developed an algorithm to reduce the errors a robot makes when it fetches an object. The robot asks questions and draws inferences from the answers, to make the correct decision on what object to fetch. The goal is to make robots more helpful to humans.

Flesch-Kincaid Grade Level of Article: 10

Extended Discussion Questions

• How could using this strategy improve accuracy on other tasks?
  • For example, if you’ve ever used a device with speech recognition, what kinds of tasks have you used it for? Were there accuracy problems? Would it have helped if the device could ask you questions? (Example to start with: What about voice-enabled search using your phone?)
  • What impact could this type of algorithm have on “smart assistant” and “smart home” technology? (Amazon Echo, Google Home…)
• Who could most benefit from having a robot helper at home?
  • What kinds of questions might a robot helper need to ask in those scenarios?
• What other applications could this type of algorithm be used for?
• This algorithm allows robots to replicate certain human social traits. How might this impact the adoption and perception of the proposed robot assistants?

Relating This Story to the CSP Curriculum Framework

Global Impact Learning Objectives:

• LO 7.1.1 Explain how computing innovations affect communication, interaction, and cognition.

Global Impact Essential Knowledge:

• EK 7.1.1J Sensor networks facilitate new ways of interacting with the environment and with physical systems.
• EK 7.1.1L Computing contributes to many assistive technologies that enhance human capabilities.

Other CSP Big Ideas:

• Idea 4 Algorithms

Banner Image: “ Network Visualization – Violet – Offset Crop“, derivative work by ICSI. New license: CC BY-SA 4.0. Based on “Social Network Analysis Visualization” by Martin Grandjean. Original license: CC BY-SA 3.0.