Winning Spacesuit Assessment Concept

Congratulations to Linh Vu, MEIT human factors design engineer at NASA JSC, and team for winning the NASA@Work Crowdsourcing Contender Challenge, an agency-wide solicitation for ideas that would greatly benefit from crowdsourcing. The challenge serves as a catalyst to generate revolutionary ideas for NASA with funding provided to support public crowdsourcing projects.

The winning proposal, titled “Machine-learning Approach for Accurate Assessment of Spacesuit Movement from Conventional Video,” proposes to create a system to quantify suit kinematic patterns in current/future missions and analog training events. A spacesuit has unique movement patterns that can be observed during spacewalks or Extravehicular Activities (EVA), and mobility assessments are needed to discern and mitigate suit injury risk. It is very difficult to measure spacesuit motion in uncontrolled environments such as training facilities, so there is a need to quantify spacesuit motion from readily available and conventional photographs or video. Ultimately, this information will help optimize the suit, hardware and task designs.

Through NASA@Work, this team will collaborate with the greater community-at-large and leverage the accumulated knowledge in deep/machine learning to perform spacesuit pose extraction in a variety of mission and analog environments.

Linh’s team submittal was one of roughly 50 submissions that entered the NASA@Work Crowdsourcing Contender Challenge.

^{Photo caption: Spacesuit recognition and posture prediction from an image. Images courtesy of NASA / Linh Vu.}