Probability for Robotics · Expectation, Variance and Covariance · M4-L1 · Intermediate
Robot Uncertainty Visualizer
Bench log · Rover in the teaching lab
14:40. The localisation filter publishes a 2 × 2 matrix of numbers with every pose. Nobody on the team can read it, and the planner keeps a fixed one-metre safety margin because nobody trusts it either. A pole detector sometimes matches the wrong pole.
You will turn the matrix into something you can see: compute it from samples, draw its ellipse, follow it through the conversion from range and bearing to world coordinates, and use it as a gate that accepts plausible detections and rejects the rest.
Your task
Lab complete: post-mortem
You have passed every stage. Now connect it back to the theory and move on:
Output
What Python can I use?
Plain Python with math and the course library robotprob (for example from robotprob import Rng, mean, gaussian_pdf). NumPy is not available in the browser. Your code runs in a background worker: an endless loop is stopped after a few seconds and the page stays usable. It runs in your browser and is never sent anywhere.