This lab works on phones, but writing code is much easier on a laptop.
Perception · Perception Foundations · P1-L2 · Beginner
A robot stands still and measures the distance to a wall. The log of readings looks nothing like a straight line: far-off points, stretches where the number never changes, gaps, and a whole log that is calm but wrong.
You will name each fault, write the checks that flag the untrustworthy readings, and produce one corrected distance together with a statement of how sure you are.
You have passed every stage. Now connect it back to the theory and move on:
Plain Python with math (and slamkit for small matrix helpers: matmul, transpose, solve, inverse, identity). Images, point clouds and detections arrive as lists inside the dictionary D; an image is a list of rows, each row a list of pixels. There is no NumPy or OpenCV: you write the algorithm yourself, which is the point of the lab. Print with print().
Stage 1 trains recognition: different faults have different shapes and need different remedies. Stage 2 asks you to write detectors and is graded on both missed faults and false alarms. Stage 3 combines rejection, bias calibration and an honest uncertainty. The simulator keeps the true distance and the fault positions private.
Educational simplification: a simulated range sensor pointed at a fixed wall, with Gaussian noise of 3 cm and a small number of injected faults of four kinds. Real sensors produce more complicated failures that depend on surface, angle, temperature and time. All data in this lab are simulated.
Get notified when new robotics labs are released. One email per new lab, nothing else.