added manual-ai-ded.md

docs/make.jl

@@ -128,7 +128,12 @@ Draft = false
 ```
 =#
 makedocs(;
-    draft=false,
+    draft=true, # if draft is true, then the julia code from .md is not executed # debug
+    # to disable the draft mode in a specific markdown file, use the following:
+    # ```@meta
+    # Draft = false
+    # ```
+    #draft=false,
     #warnonly=[:cross_references, :autodocs_block],
     sitename="OptimalControl.jl",
     format=Documenter.HTML(;
@@ -150,6 +155,7 @@ makedocs(;
         ],
         "Manual" => [
             "Define a problem" => "manual-abstract.md",
+            "Use AI" => "manual-ai-ded.md",
             "Problem characteristics" => "manual-model.md",
             "Set an initial guess" => "manual-initial-guess.md",
             "Solve a problem" => "manual-solve.md",

docs/src/manual-ai-ded.md

@@ -0,0 +1,85 @@
+# [Use AI](@id manual-ai-ded)
+
+Using now common models from AI, it is an elementary task to have such an agent learn the syntax of OptimalControl.jl DSL, then use the agent to translate standard math into this DSL. Here is a typical prompt, pointing to the [DSL syntax](@ref manual-abstract-syntax):
+
+```
+learn the syntax of optimalcontrol.jl dsl described at the link below to translate math into this dsl (julia language):
+https://control-toolbox.org/OptimalControl.jl/stable/manual-abstract.html
+```
+
+Now, here is an extract of, *e.g.*, [claude.ai](https://claude.ai) answer (Sonnet 4 model) to the request below:
+
+```
+translate the problem below into this DSL: minimise the final time tf under the constraint q''(t) = u(t) with -1 <= u(t) <= 1, q(0) = 1, q'(0) = -2, q(tf) = 3, q'(tf) = 1, and q'(t) <= 1
+```
+
+```julia
+@def begin
+    tf ∈ R, variable
+    t ∈ [0, tf], time
+    x = (q, v) ∈ R², state
+    u ∈ R, control
+
+    # Variable constraint
+    tf ≥ 0
+
+    # Control constraint
+    -1 ≤ u(t) ≤ 1
+
+    # Initial conditions
+    q(0) == 1
+    v(0) == -2
+
+    # Final conditions  
+    q(tf) == 3
+    v(tf) == 1
+
+    # Path constraint
+    v(t) ≤ 1
+
+    # Dynamics (q'' = u becomes first-order system)
+    ẋ(t) == [v(t), u(t)]
+
+    # Objective: minimize final time
+    tf → min
+end
+```
+
+The answer is syntactically correct and can be updated, for instance according to the new request below:
+
+```
+use a form compatible with examodels
+```
+
+```julia
+@def begin
+    tf ∈ R, variable
+    t ∈ [0, tf], time
+    x = (q, v) ∈ R², state
+    u ∈ R, control
+
+    # Variable constraint
+    tf ≥ 0
+
+    # Control constraint
+    -1 ≤ u(t) ≤ 1
+
+    # Initial conditions
+    q(0) == 1
+    v(0) == -2
+
+    # Final conditions  
+    q(tf) == 3
+    v(tf) == 1
+
+    # Path constraint
+    v(t) ≤ 1
+
+    # Dynamics (coordinate-wise for ExaModels)
+    ∂(q)(t) == v(t)
+    ∂(v)(t) == u(t)
+
+    # Objective: minimize final time
+    tf → min
+end
+```

docs/src/manual-solve-gpu.md

@@ -39,20 +39,21 @@ Computation on GPU is currently only tested with CUDA, and the associated backen
 sol = solve(ocp, :exa, :madnlp; exa_backend=CUDABackend())
 ```
 
-```
-▫ This is OptimalControl version v1.1.0 running with: direct, exa, madnlp.
 
-▫ The optimal control problem is solved with CTDirect version v0.16.0.
+```julia
+▫ This is OptimalControl version v1.1.2 running with: direct, exa, madnlp.
+
+▫ The optimal control problem is solved with CTDirect version v0.17.2.
 
-   ┌─ The NLP is modelled with ExaModels and solved with MadNLP.
+   ┌─ The NLP is modelled with ExaModels and solved with MadNLPMumps.
    │
    ├─ Number of time steps⋅: 250
-   └─ Discretisation scheme: trapeze
+   └─ Discretisation scheme: midpoint
 
-▫ This is MadNLP version v0.8.7, running with cuDSS v0.4.0
+▫ This is MadNLP version v0.8.12, running with cuDSS v0.6.0
 
-Number of nonzeros in constraint Jacobian............:     2506
-Number of nonzeros in Lagrangian Hessian.............:     2006
+Number of nonzeros in constraint Jacobian............:     2256
+Number of nonzeros in Lagrangian Hessian.............:     1251
 
 Total number of variables............................:      754
                      variables with only lower bounds:        0
@@ -64,21 +65,30 @@ Total number of inequality constraints...............:      251
    inequality constraints with lower and upper bounds:      251
         inequality constraints with only upper bounds:        0
 
-iter    objective    inf_pr   inf_du lg(mu)  ||d||  lg(rg) alpha_du alpha_pr  ls
-   0  1.0200000e+00 1.10e+00 1.00e+00  -1.0 0.00e+00    -  0.00e+00 0.00e+00   0
-  ...
-  26  9.8902986e+00 2.22e-16 7.11e-15  -9.0 1.32e-04    -  1.00e+00 1.00e+00h  1
+iter    objective    inf_pr   inf_du inf_compl lg(mu)  ||d||  lg(rg) alpha_du alpha_pr  ls
+   0  1.0200000e+00 1.10e+00 1.00e+00 1.01e+01  -1.0 0.00e+00    -  0.00e+00 0.00e+00   0
+   1  1.0199978e+00 1.10e+00 1.45e+00 8.73e-02  -1.0 1.97e+02    -  5.05e-03 4.00e-07h  1
+   ...
+  27  9.8891249e+00 2.22e-16 7.11e-15 1.60e-09  -9.0 2.36e-04    -  1.00e+00 1.00e+00h  1
 
-Number of Iterations....: 26
+Number of Iterations....: 27
 
                                    (scaled)                 (unscaled)
-Objective...............:   9.8902986337530514e+00    9.8902986337530514e+00
+Objective...............:   9.8891248915014458e+00    9.8891248915014458e+00
 Dual infeasibility......:   7.1054273576010019e-15    7.1054273576010019e-15
 Constraint violation....:   2.2204460492503131e-16    2.2204460492503131e-16
-Complementarity.........:   4.8363494304578671e-09    4.8363494304578671e-09
-Overall NLP error.......:   4.8363494304578671e-09    4.8363494304578671e-09
-
-...
+Complementarity.........:   1.5999963912421547e-09    1.5999963912421547e-09
+Overall NLP error.......:   1.5999963912421547e-09    1.5999963912421547e-09
+
+Number of objective function evaluations             = 28
+Number of objective gradient evaluations             = 28
+Number of constraint evaluations                     = 28
+Number of constraint Jacobian evaluations            = 28
+Number of Lagrangian Hessian evaluations             = 27
+Total wall-clock secs in solver (w/o fun. eval./lin. alg.)  =  0.126
+Total wall-clock secs in linear solver                      =  0.103
+Total wall-clock secs in NLP function evaluations           =  0.022
+Total wall-clock secs                                       =  0.251
 
 EXIT: Optimal Solution Found (tol = 1.0e-08).
 ```