Skip to content

Fit parameters from a log

Draft

This guide is scaffolded. The outline below marks what it should cover.

Fit minimizes windowed prediction error against logged controls + measurements to recover physical parameters.

To cover

  • Marking a Parameter promotable with a manifold= (thruster gains, Mass.mass, mount transforms).
  • Assembling Windows from a log (x0, u, z, dt).
  • Adding a Prior for MAP regularization.
  • Running Fit(world, parameters={...}), reading FitResult.converged and the recovered values.
  • Fitting the noise model instead with NoiseFit (innovation-NLL σ) — and why σ can't be L2-fit.
  • Pitfalls: whiten sensors before fitting; OP_OUTPUT must snapshot.

Source material