[franckgaga]

The current formulation (direct=false) of the MovingHorizonEstimator never needs the measured disturbances of the next time step $\mathbf{d}(k+1)$. All the required $\mathbf{d}$ values for computing the predictions are explicitly available in the mhe.D0 window.

Before this PR, the SingleShooting case was ignoring the most recent measurement and was using the approximation $\mathbf{d}(k) \approx \mathbf{d}(k-1)$. Now the latest $\mathbf{d}$ is used, as it should be.

Also, the coverage of the SingleShooting case with NonLinModel is slightly improved.

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 97.25%. Comparing base (9ac8953) to head (9ccd5fc).
⚠️ Report is 13 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #502   +/-   ##
=======================================
  Coverage   97.25%   97.25%           
=======================================
  Files          28       28           
  Lines        7093     7095    +2     
=======================================
+ Hits         6898     6900    +2     
  Misses        195      195           

Flag	Coverage Δ
unittests	97.25% <100.00%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.