September 27, 2016 Crowdsourcing News: NASA Teams Up with Topcoder to Try to Improve Vision Algorithms for Robonaut 2
We love NASA! Growing up, watching shows like Star Trek the Next Generation was a ton of fun, helping us to stretch our imaginations and dare I say, to boldly go!!! However, beyond watching a TV program set in the 24th century, growing up and following the advances being made in real life by NASA were truly inspiring.
Whether it was the Space Shuttle program, the launching and fixing of Hubble, the landing of multiple rovers on the Red Planet, or satellite missions to Jupiter, Saturn, Pluto and beyond, NASA has continued to inspire us throughout the decades.
At Topcoder, we’ve been an innovation partner with NASA for several years now working on projects to better help identify asteroids, creating an iPad application for improved nutrition tracking of astronauts, and creating sophisticated algorithms to attempt to improve the energy harvesting abilities of the International Space Station!
With that we’re extremely excited to introduce another amazing challenge in our Topcoder Marketplace!
Robonaut 2 Round 2 – Vision Algorithm Improvement Data Science Challenge
Robonaut 2 Vision Challenge Round 2 is a follow-on problem where we look to create vision algorithms for determining the 3D representation of different tools that will be effective with noisy, stereo vision data.
Robonaut 2 (“R2”), a humanoid robot that operates both on Earth and on the International Space Station, uses tools to do its work. For example, it manages inventory using an RFID reader and fastens bolts with a drill. In order to use a tool, R2 relies on an algorithm to determine a 3D representation of the tool. The algorithm works with the robot’s control system and allows R2 to create a plan for grasping objects and completing its tasks.
There exist several algorithms that could be used to determine a 3D representation of the tool. However, the robot employs an older, less capable set of vision sensors, due to its space heritage and having been exposed to high levels of environmental radiation over time.
Many existing algorithms assume that the vision data being used is of relatively high resolution, detail, and quality, and such algorithms are not effective when used with the grade of vision data available to R2. As a result, the R2 team needs you to create vision algorithms for determining the 3D representation of different tools that will be effective with noisy, stereo vision data.
Prizes Available and a Trip to TCO16 in Washington D.C.
The best 5 performers in this 14-day contest according to system test results will receive the following prizes:
- place: $4,000
- place: $2,750
- place: $1,750
- place: $1,000
- Place: $500
The winner of this challenge will win an all-expenses paid trip to the 2016 Topcoder Open Finals in Washington D.C. November 18-21, 2016. Topcoder will coordinate and pay for the travel details as well as assist with a visa appointment (if needed). At the TCO16 finals, the winner will assist Topcoder in reporting on the TCO16 Marathon Competition finals on the Topcoder blog.
Registering for Robonaut 2 Round 2 on Topcoder
We’ve made this easy for you. If you are seeing this post before the challenge launch on September 30th, just go here and fill out this very simple form. That’s it! As long as you are a Topcoder member who is eligible to compete, we will handle the rest and you will be alerted about any major updates and when the ‘starting gun’ goes off for this unique crowdsourcing data science challenge!
We wish all those who will be competing – good luck! We will keep striving to provide you, our Topcoder community with the opportunity to work on amazing problems such as this one from our partners at NASA! Have fun with this important data science challenge and here’s to helping NASA improve the sight algorithms for their famous humanoid robot!