Pose Bowl: Detection Track

Develop algorithms for use on inspector spacecraft that take and process photos of other ships. In the Detection Track, solutions will identify the boundaries of generic spacecraft in photos. #science

$12,000 in prizes
4 days left
634 joined

Overview

Inspector spacecraft are designed to conduct independent, low-cost, in-space inspections of other ships and may deploy off a host spacecraft to examine its exterior for damage. Inspector spacecraft typically have limited computing resources, but complex computing demands. Minimally, the chaser (inspector) spacecraft must locate a target ship and maneuver around it while maintaining an understanding of spatial pose.

A successful proof of concept for a low-cost inspector spacecraft was demonstrated by NASA’s Seeker. For this proof of concept, Seeker's object detection algorithm was trained on a specific type of spacecraft. A more useful version of this software would be generalized so that it could detect any type of spacecraft. It is also essential that future versions are able to determine the relative pose of the chaser spacecraft camera across a sequence of images.

Task

In this challenge, solvers will help NASA develop algorithms that could be run on inspector spacecraft. There are two tracks, with different associated prizes. In the Detection Track (that's this one), solvers develop object detection solutions that identify a bounding box around a spacecraft in an image. In the Pose Estimation Track, solvers develop solutions that identify the relative position and orientation (pose) of the chaser spacecraft camera across sequences of images.

Prizes and Timeline

Competition End Date:

May 14, 2024, 11:59 p.m. UTC

Award Prize Amount
1st $5,000
2nd $3,000
3rd $2,000
Real Hardware Speed Bonus Prize $2,000
Total $12,000

Real Hardware Speed Bonus Prize

The most useful algorithms for inspector spacecraft will be both accurate and fast. A bonus prize of $2,000 will be awarded to the prize-winning object detection solution that runs fastest on the actual hardware that the R5 spacecraft, which is demonstrating inspection technologies, uses (UP-CHT01-A20-0464-A11), to encourage solvers to experiment with methods that make their solutions run faster. The top three solutions from the private leaderboard will be run on a UP-CHT01, and the solution that generates inferences about a representative test set fastest will win this bonus prize.


How to compete

  1. Click the "Compete!" button in the sidebar to enroll in the competition.
  2. Get familiar with the problem through the Problem Description page.
  3. Download the training ground truth data by following instructions on the Data download page.
  4. Create and train your own model.
  5. Bundle your trained model and prediction code for evaluation in our cloud runtime. See the Code submission format page for more detail.
  6. Click “Submissions” in the sidebar, and then “Make new submission”.

The challenge rules are in place to promote fair competition and useful solutions. If you are ever unsure whether your solution meets the rules, ask the challenge organizers in the competition forum or send an email to info@drivendata.org.

Note on prize eligibility: Federal employees acting within the scope of their employment and federally-funded researchers acting within the scope of their funding are not eligible to win a prize in this challenge.


This challenge is in collaboration with the NASA Tournament Lab.

NTL Logo


Image courtesy of NASA.