This lab works on phones, but writing code is much easier on a laptop.
Localization & SLAM · SLAM Foundations · M1-L3 · Beginner
The lidar works. The robot knows where it is. And yet the walls on the map are doubled, smeared, and rotated away from where they should be.
Nothing is wrong with the data: a point has been put in the wrong frame. You will fix the chain, learn to read frame bugs from their symptoms, and publish the transform that keeps odometry smooth while localization corrects it.
You have passed every stage. Now connect it back to the theory and move on:
Plain Python with math and, for matrices, slamkit (matmul, transpose, solve, inverse, identity). The data arrive as the dictionary D. There is no NumPy, random, json or copy in the browser runtime. Your code runs locally and never leaves this page.
Stage 1 builds the chain lidar → base → map and is graded by how close your points land to the real walls on paths you never see. Stage 2 trains the diagnostic habit: test a transform at several poses and recognise which bug leaves which signature. Stage 3 is the map → odom transform of the ROS convention, graded against a later odometry pose so that a lucky answer cannot pass.
Educational simplification: planar SE(2) poses and a 2D lidar rigidly mounted on the base. Real systems add 3D rotation (SE(3)), time-varying transforms and extrinsic calibration (Module 2).
Get notified when new robotics labs are released. One email per new lab, nothing else.