Technology Tools
Technology Tools

Educators often take advantage of educational technologies as they make the shifts in instruction, teacher roles, and learning experiences that next gen learning requires. Technology should not lead the design of learning, but when educators use it to personalize and enrich learning, it has the potential to accelerate mastery of critical content and skills by all students.

Learn More

The XPRIZE Global Learning Challenge was designed to inspire teams to create motivating educational experiences to help students in developing countries learn the basic literacy and mathematics skills they need to lift themselves out of poverty. XPRIZE recently announced five finalists from the 200 teams in 40 countries around the world who submitted. One of these finalists was the RoboTutor Team led by Jack Mostow of Carnegie Mellon University.

The RoboTutor software is powered by advanced technologies, including speech and handwriting recognition as well as facial analysis and machine learning to enable cognitive tutors powered by artificial intelligence to adapt to individual students. Given the acute shortage of teachers in developing countries, RoboTutor has the potential to help an estimated 250 million children around the world who cannot read, write, or do fundamental arithmetic.

Number Sense and Fluency

RoboTutor includes fluency games developed by the Mathematics Fluency Data Collaborative (MFDC), a project led by Carnegie Learning in partnership with New York University, the University of North Carolina at Charlotte, Carnegie Mellon University, Playpower Labs and Pellisippi State Community College.

These games help students develop number sense, the set of skills and intuitions that allows people to make rapid judgments about quantity. Number sense is the basis for higher mathematical reasoning. It is not about rote memorization, but about developing perceptual skills that help decode numerical representations and estimation skills that underlie the ability to compare quantities.

In one game, the player controls a car that drives on a three-lane road. The challenge is to pass through signposts so that the number on your car is appropriately positioned relative to the numbers on the signs. Since 0.39 is less than 0.7, the car should move to the left lane. Players can go as fast as they are able, but they are penalized for being in the wrong lane.

While the original game was designed for adult students and focused on fractions, decimals and percents, the RoboTutor team was able to adapt it for the XPRIZE Challenge.

RoboTutor team leader Jack Mostow talks about the advantage of building on the already-successful games developed through Next Generation Learning Challenges:

RoboTutor benefits enormously from two games previously developed by other groups – an open source race car game from MFDC, and a bubble-popping game from Playpower Labs. When I realized how much work it takes to develop games that are both engaging and educationally effective, I decided to get maximum use out of these two games by generalizing them as much as possible.  For instance, besides porting the race car game to Android tablets, streamlining its user interface, eliminating text for non-readers, and replacing decimals with integers, we extended it to allow 1 or 3 signs (not just 2), audio or image stimuli (not just numbers), and words (not just numbers) as targets.  Consequently RoboTutor uses the race car game for literally dozens of different activities.  Even though we had to reimplement it, adapting its design (and reusing some of its audio and graphical assets) was much easier than developing a new game from scratch and iteratively testing and improving its design to make it usable, fun, and effective.

The next step? Field testing in Tanzania. If the RoboTutor Team is successful, a $10 million prize awaits.

If you are interested in trying the MFDC games, they are available at To find out how to support the RoboTutor Team, go to

Dr. Steven Ritter

Founder and Chief Scientist, Carnegie Learning

Dr. Steven Ritter has been developing and evaluating educational systems for over 20 years. He earned his Ph.D. in Cognitive Psychology at Carnegie Mellon University and was instrumental in the development and evaluation of Cognitive Tutors for mathematics. Through leadership of the research department, Dr. Ritter has led many improvements to the use of adaptive learning systems and math education in real-world settings. He is the author of numerous papers on the design, architecture and evaluation of Intelligent Tutoring Systems. He is lead author of an evaluation judged by the US Department of Education’s What Works Clearinghouse as fully meeting their standards and is lead author of a "Best Paper" at the International Conference on Educational Data Mining.