Robonaut Challenge

NASA?s Robonaut needs improved computer vision in order to increase its autonomy and ability to perform useful tasks.To improve Robonaut?s vision, competitors were given a set of imagery from Robonaut here on earth, on the ISS, and in the simulator. The camera system is slightly different for each system and has different lighting conditions as well. The resulting algorithm was required to work for every application. Strong performance on the real imagery was identified as that which will translate best to software that works on the ISS. For each test case competitors were given two images ? a ?left eye? image and a ?right eye? image ? and a string array containing the names of the buttons/switches/LEDs to be located on the taskboard. Competitors were then asked to define the button/switch?s state and (x,y) location in pixels relative to the upper left corner of the image chosen (?left eye? or ?right eye?). Competitors were judged on: Accuracy · What is the false alarm rate vs. detection · How far from actual position is the computed position Time · How long does it take to determine the state of the LEDs
Robonaut 2 is the first humanoid robot in space and was sent to the International Space Station (ISS) with the intention of taking over tasks too dangerous or too mundane for astronauts. There's a problem though: Robonaut 2 needs to learn how to interact with the types of input devices the astronauts use on the ISS. The challenge for the TopCoder community was to write an algorithm to control Robonaut and teach him how to interact with the taskboard. Specifically, competitors were asked to teach Robonaut how to recognize the state and location of several buttons and switches on the taskboard. This was important to advance Robonaut 2's "seeing" capability and potentially accelerate his effectiveness in supporting efforts on the ISS. NASA's Robonaut needs improved computer vision in order to increase its autonomy and ability to perform useful tasks.To improve Robonaut's vision, competitors were given a set of imagery from Robonaut here on earth, on the ISS, and in the simulator. The camera system is slightly different for each system and has different lighting conditions as well. The resulting algorithm was required to work for every application. Strong performance on the real imagery was identified as that which will translate best to software that works on the ISS. For each test case competitors were given two images ? a "left eye" image and a "right eye" image ? and a string array containing the names of the buttons/switches/LEDs to be located on the taskboard. Competitors were then asked to define the button/switch's state and (x,y) location in pixels relative to the upper left corner of the image chosen ("left eye" or "right eye"). Competitors were judged on: Accuracy · What is the false alarm rate vs. detection · How far from actual position is the computed position Time · How long does it take to determine the state of the LEDs

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.