Prove
LiveProof-of-Work · Oct–Nov: every verified proof counts. 28 days leftAll outcomes
Skills

Robotics 4: Perception

6 weeks · 2 milestones

See the world: vision, depth and knowing where you are. Stage 4 of the Varsity Curriculum: Robotics. A simulation-only route counts at every step; free resources only.

Part of: Robotics · Proves for: Engineers, UG

Milestone map

Milestone map

2 milestones

Make a robot see and localise

3–5 weeks (about 8 hrs/week, est)

Build a perception pipeline for a simulated robot: detect objects in camera images, estimate depth or position, and localise the robot on a map (SLAM or a known map), with accuracy measured against the simulator's ground truth. Keep it in one public repo and commit as you go. No hardware needed: this milestone is done in simulation.

Proof required

Link the public repo with the pipeline, the evaluation against ground truth (detection accuracy and localisation error), and a screen recording.

What gets checked

  • Accuracy is measured against ground truth, not eyeballed.
  • Localisation error is reported over a whole route.
  • Failure cases (bad light, clutter) are shown.

Common mistakes

  • One big upload with no commit history.
  • Results the repo cannot reproduce.

Powstik Guide

A public repo with a perception pipeline for a simulated robot: detect objects in camera images, estimate depth or position, and localise the robot on a map (SLAM or a known map), with accuracy measured against the simulator's ground truth.

Steps

  1. Make a public repo.
  2. Set up the simulator from its free docs.
  3. Build the smallest version that works, then measure it.
  4. Write a README: what it is, how to launch it, what the numbers show.
  5. Ask someone who knows robotics to check it.

Template

README
Stage 4: Perception
What is here:
How to launch it:
Results:
Limits:

What gets sent back

  • No measurements.
  • Code that does not work from the README.
  • Copied code with no history.

Resources

Foundationstart here

What a verifier looks for

  • Accuracy is measured against ground truth, not eyeballed.
  • Localisation error is reported over a whole route.
  • Failure cases (bad light, clutter) are shown.
  • Open the repo: does the code produce what the recording shows?

You'll sign in first, then come straight back here.

Test it on a scene someone else sets

1 week (about 4 hrs, est)

Show your perception working on a scene someone else arranges, on a real camera or in simulation. Do it in person or on a live video call. Simulation-only route: if you have no hardware, a live run in the simulator counts.

Proof required

Name the person who watched and add the recording or your notes of what happened, including anything that failed.

What gets checked

  • The other person sets the scene.
  • Results are reported for that scene.
  • Mistakes are shown, not cut.

Common mistakes

  • A pre-recorded run passed off as live.
  • Cutting the failures.

Powstik Guide

A live demo to one person who knows robotics, with notes or a recording.

Steps

  1. Agree the test with the person first.
  2. Let them choose the conditions.
  3. Show it live and record what happened.
  4. Write down what failed and why.

Template

Demo notes
Who watched:
What they asked for:
What happened:
What failed:

What gets sent back

  • The person did not see it live.
  • No notes or recording.

Resources

What a verifier looks for

  • The other person sets the scene.
  • Results are reported for that scene.
  • Mistakes are shown, not cut.
  • Did you watch it happen live?

You'll sign in first, then come straight back here.