10 Hardest Things to Teach a Robot


1
Feel Emotions
Along with his emotive abilities, Nao clearly knows how to chill. © Gerd Roth/dpa/Corbis

"The best and most beautiful things in the world cannot be seen or even touched. They must be felt with the heart." If this observation by Helen Keller is true, then robots would be destined to miss out on the best and beautiful. After all, they're great at sensing the world around them, but they can't turn that sensory data into specific emotions. They can't see a loved one's smile and feel joy, or record a shadowy stranger's grimace and tremble with fear.

This, more than anything on our list, could be the thing that separates man from machine. How can you teach a robot to fall in love? How can you program frustration, disgust, amazement or pity? Is it even worth trying?

Some scientists think so. They believe that future robots will integrate both cognitive emotion systems, and that, as a result, they'll be able to function better, learn faster and interact more effectively with humans. Believe it or not, prototypes already exist that express a limited range of human emotion. Nao, a robot developed by a European research team, has the affective qualities of a 1-year-old child. It can show happiness, anger, fear and pride, all by combining postures with gestures. These display actions, derived from studies of chimpanzees and human infants, are programmed into Nao, but the robot decides which emotion to display based on its interaction with nearby people and objects. In the coming years, robots like Nao will likely work in a variety of settings -- hospitals, homes and schools -- in which they will be able to lend a helping hand and a sympathetic ear.

Author's Note: 10 Hardest Things to Teach Robots

The Robot from "Lost in Space" (the 1960s TV series, not the horrible 1998 movie) roamed my imagination as I wrote this article. It was difficult to write about humans interacting with machines and not hear The Robot's iconic warning -- "Danger, Will Robinson, danger!" -- echoing in my thoughts.

Related Articles

Sources

  • Ackerman, Evan. "Cornell Teaching Robots to Use Their Imaginations When Organizing Your Stuff." IEEE Spectrum. June 21, 2012. (Nov. 4, 2013)http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/cornell-teaching-robots-to-use-their-imaginations-when-organizing-your-stuff
  • Ackerman, Evan. "Georgia Tech Robots Learn Deceptive Behaviors from Squirrels." IEEE Spectrum. Dec. 3, 2012. (Nov. 4, 2013)http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/robots-learn-deceptive-behaviors-from-squirrels
  • Ackerman, Evan. "Why Teaching a Robot to Fetch a Cup of Coffee Matters." IEEE Spectrum. May 9, 2013. (Nov. 4, 2013)http://spectrum.ieee.org/automaton/robotics/robotics-software/pr2-robot-fetches-cup-of-coffee
  • Anderson, Michael and Susan Leigh Anderson. "Robot, Be Good." Scientific American. October 2010.
  • Batalin, Maxim A., Gaurav S. Sukhatme and Myron Hattig. "Mobile Robot Navigation using a Sensor Network." IEEE International Conference on Robotics and Automation. April 26, 2004. (Nov. 4, 2013)http://robotics.usc.edu/publications/media/uploads/pubs/367.pdf
  • Bonabeau, Eric and Guy Th√©raulaz. "Swarm Smarts." Scientific American Reports. Special Edition on Robotics. 2008.
  • Breazeal, Cynthia and Rodney Brooks. "Robot Emotion: A Functional Perspective." Personal Robotics Group. 2005. (Nov. 4, 2013)http://robotic.media.mit.edu/pdfs/other/Breazeal-Brooks-03.pdf
  • Carroll, Chris. "Teaching Robots to Anticipate Human Actions." National Geographic News. May 31, 2013. (Nov. 4, 2013)http://news.nationalgeographic.com/news/2013/05/130531-personal-robot-beer-microsoft-kinect-saxena-science/
  • Dillow, Clay. "Enhancing Robots' Senses of Touch By Giving them Human-Like Fingerprints." Popular Science. Sept. 21, 2011. (Nov. 4, 2013)http://www.popsci.com/technology/article/2011-09/enhancing-robots-senses-touch-giving-them-human-fingerprints
  • Durrant-Whyte, Hugh and Tim Bailey. "Simultaneous Localisation and Mapping (SLAM): Part I The Essential Algorithms." Robotics and Automation Magazine. 2006. (Nov. 4, 2013)http://www-personal.acfr.usyd.edu.au/tbailey/papers/slamtute1.pdf
  • Englert, Peter, Alexandros Paraschos, Jan Peters and Marc Peter Deisenroth. "Model-based Imitation Learning by Proabilistic Trajectory Matching." Proceedings of the IEEE International Conference on Robotics and Automation. 2013. (Nov. 4, 2013)http://www.is.tuebingen.mpg.de/fileadmin/user_upload/files/publications/2013/Englert_ICRA_2013.pdf
  • Griffin, Catherine. "MIT Scientists Create M-Cube Self-Assembling Robots: Real World Transformers." Science World Report. Oct. 4, 2013. (Nov. 4, 2013)http://www.scienceworldreport.com/articles/9948/20131004/mit-scientists-create-m-cube-self-assembling-robots-real-world.htm
  • Halverson, Nic. "Electronic Skin Gives Robots a Sense of Touch." Discovery News. July 1, 2011. (Nov. 4, 2013)http://news.discovery.com/tech/robotics/electronic-skin-gives-robots-sense-touch-110701.htm
  • Handwerk, Brian. "Robot Revolution? Scientists Teach Robots to Learn." National Geographic News. July 18, 2013. (Nov. 4, 2013)http://news.nationalgeographic.com/news/2013/07/130719-robot-lfd-pr2-artificial-intelligence-crowdsourcing-robotics-machine-learning/
  • Hardesty, Larry. "Teaching robots lateral thinking." MIT News. Feb. 25, 2013. (Nov. 4, 2013)http://web.mit.edu/newsoffice/2013/teaching-robots-lateral-thinking-0225.html
  • Hartshorne, Joshua K. "Where Are the Talking Robots?" Scientific American Mind. March/April 2011.
  • Hicks, Jennifer. "Teaching Robots To Deceive." Forbes. Dec. 30, 2012. (Nov. 4, 2013)http://www.forbes.com/sites/jenniferhicks/2012/12/30/teaching-robots-to-deceive/
  • Jha, Alok. "First robot able to develop and show emotions is unveiled." The Guardian. Aug. 8, 2010. (Nov. 4, 2013)http://www.theguardian.com/technology/2010/aug/09/nao-robot-develop-display-emotions
  • Jones, Joshua, research scientist, Georgia Institute of Technology. E-mail correspondence. Nov. 11, 2013. http://www.cc.gatech.edu/~jj187/
  • Korn, Jon. "A 'Bot Bestiary: The Robotic Tradition In Science Fiction." LitReactor. July 13, 2012. (Nov. 4, 2013)http://litreactor.com/columns/a-bot-bestiary-the-robotic-tradition-in-science-fiction
  • Markoff, John. "Researchers Put Sense of Touch in Reach for Robots." The New York Times. April 28, 2013. (Nov. 4, 2013)http://www.nytimes.com/2013/04/28/science/researchers-put-sense-of-touch-in-reach-for-robots.html?_r=0
  • OpenSLAM.org. "What is SLAM?" (Nov. 4, 2013)http://www.openslam.org/
  • Ratlif, Nathan D., J. Andrew Bagnell and Siddhartha Srinivasa. "Imitation Learning for Locomotion and Manipulation." Robotics Institute, Carnegie Mellon University. December 2007. (Nov. 4, 2013)http://www.ri.cmu.edu/pub_files/pub4/ratliff_nathan_2007_4/ratliff_nathan_2007_4.pdf
  • Rieland, Randy. "Robots Get the Human Touch." Smithsonian Magazine. Nov. 10, 2011. (Nov. 4, 2013)http://blogs.smithsonianmag.com/ideas/2011/11/robots-get-the-human-touch/
  • Schultz, Colin. "This New Robot Has a Sense of Touch." Smithsonian Magazine. April 29, 2013. (Nov. 4, 2013)http://blogs.smithsonianmag.com/smartnews/2013/04/this-new-robot-has-a-sense-of-touch/
  • Sipper, Moshe and James A. Reggia. "Go Forth and Replicate." Scientific American Reports. Special Edition on Robotics. 2008.
  • Steele, Bill. "Researchers build a robot that can reproduce." Cornell Chronicle. May 25, 2005. (Nov. 4, 2013)http://www.news.cornell.edu/stories/2005/05/researchers-build-robot-can-reproduce
  • Summet, Jay. E-mail correspondence. Nov. 22, 2013. http://www.summet.com/
  • Tofel, Kevin C. "MIT: We are one step closer to self-replicating objects." Gigaom. April 3, 2012. (Nov. 4, 2013)http://gigaom.com/2012/04/03/mit-were-one-step-closer-to-self-replicating-objects/
  • Wadsworth, Derek. "Adaptive Robotics." Idaho National Laboratory. (Nov. 4, 2013)https://inlportal.inl.gov/portal/server.pt/community/robotics_and_intelligence_systems/455

UP NEXT

50 Years After '2001: A Space Odyssey,' How Close Are We to HAL 9000?

50 Years After '2001: A Space Odyssey,' How Close Are We to HAL 9000?

'2001: A Space Odyssey' premiered 50 years ago and predicted a lot right. HowStuffWorks wanted to know just how close we are now to the abilities of HAL 9000.


More to Explore