← Back to NASA Technology Projects

Robonaut 2 Tool Localization

Completed

Description

Robonaut 2 (R2) is constrained to an older and less capable set of vision sensors due to its space heritage and radiation environment. Many of the algorithms that have been developed have significantly reduced effectiveness when partnered with the quality of vision data used. The R2 team is looking to find vision algorithms that will be effective with noisy stereo vision data for localizing a specific point on a variety of tools. The R2 team has approximately 100 sets of stereo imagery to use for the stereo vision data which will be provided to the vendor. Additionally, ground truth data will also be provided. This data will be fed back to the control system to allow the robot to create a plan for grasping the object, enabling the robot to complete its tasks.
This challenge is seeking vision algorithms for NASA's Robonaut 2 (R2) that will be effective with noisy stereo vision data for localizing a specific point on a variety of tools. Robonaut 2 (R2) is constrained to an older and less capable set of vision sensors due to its space heritage and radiation environment. Many of the algorithms that have been developed have significantly reduced effectiveness when partnered with the quality of vision data used. The R2 team is looking to find vision algorithms that will be effective with noisy stereo vision data for localizing a specific point on a variety of tools. The R2 team has approximately 100 sets of stereo imagery to use for the stereo vision data which will be provided to the vendor. Additionally, ground truth data will also be provided. This data will be fed back to the control system to allow the robot to create a plan for grasping the object, enabling the robot to complete its tasks.

Benefits

In our close out package you will find all of this content: https://docs.google.com/presentation/d/1HmE2_dTWgtZZXYNM9-pd85vLbhbvc_EJ9_V-UKSNmuU/edit#slide=id.ge52f96c47_0_15
Significantly Advanced Towards a Solution
Planned for future implementation
Algorithm

Details

Technology areaRobotic Systems > Sensing and Perception > Object, Event, and Activity Recognition
ProgramPrizes, Challenges, and Crowdsourcing (PCC)
Lead organizationJohnson Space Center, Houston, TX
Start date2015-08-07
End date2016-12-06

Project contacts

Listed on TechPort itself — the most direct way to ask about this specific project.

How to get involved

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.