int main(){ cout << "program started" << endl; std::ofstream resfile; resfile.open ("results_biegler_10_1.txt"); // Test with different number of elements for(int N=1; N<=10; ++N){ // Degree of interpolating polynomial int K = 2; // Legrandre roots vector<double> tau_root(K+1); tau_root[0] = 0.; tau_root[1] = 0.211325; tau_root[2] = 0.788675; // Radau roots (K=3) /* tau_root[0] = 0; tau_root[1] = 0.155051; tau_root[2] = 0.644949; tau_root[3] = 1;*/ // Time SX t("t"); // Differential equation SX z("z"); SXFunction F(z,z*z - 2*z + 1); F.setOption("name","dz/dt"); F.init(); cout << F << endl; double z0 = -3; // Analytic solution SXFunction z_analytic(t, (4*t-3)/(3*t+1)); z_analytic.setOption("name","analytic solution"); z_analytic.init(); cout << z_analytic << endl; // Collocation point SX tau("tau"); // Step size double h = 1.0/N; // Lagrange polynomials vector<SXFunction> l(K+1); for(int j=0; j<=K; ++j){ SX L = 1; for(int k=0; k<=K; ++k) if(k != j) L *= (tau-tau_root[k])/(tau_root[j]-tau_root[k]); l[j] = SXFunction(tau,L); stringstream ss; ss << "l(" << j << ")"; l[j].setOption("name",ss.str()); l[j].init(); cout << l[j] << endl; } // Get the coefficients of the continuity equation vector<double> D(K+1); for(int j=0; j<=K; ++j){ l[j].setInput(1.0); l[j].evaluate(); l[j].getOutput(D[j]); } cout << "D = " << D << endl; // Get the coefficients of the collocation equation vector<vector<double> > C(K+1); for(int j=0; j<=K; ++j){ C[j].resize(K+1); for(int k=0; k<=K; ++k){ l[j].setInput(tau_root[k]); l[j].setFwdSeed(1.0); l[j].evaluate(1,0); l[j].getFwdSens(C[j][k]); } } cout << "C = " << C << endl; // Collocated states SX Z = ssym("Z",N,K+1); // State at final time // SX ZF("ZF"); // All variables SX x; x << vec(trans(Z)); // x << vec(ZF); cout << "x = " << x << endl; // Construct the "NLP" SX g; for(int i=0; i<N; ++i){ for(int k=1; k<=K; ++k){ // Add collocation equations to NLP SX rhs = 0; for(int j=0; j<=K; ++j) rhs += Z(i,j)*C[j][k]; g << (h*F.eval(SX(Z(i,k))) - rhs); } // Add continuity equation to NLP SX rhs = 0; for(int j=0; j<=K; ++j) rhs += D[j]*Z(i,j); if(i<N-1) g << (SX(Z(i+1,0)) - rhs); /* else g << (ZF - rhs);*/ } cout << "g = " << g << endl; SXFunction gfcn(x,g); // Dummy objective function SXFunction obj(x, Z(0,0)*Z(0,0)); // ---- // SOLVE THE NLP // ---- // Allocate an NLP solver IpoptSolver solver(obj,gfcn); // Set options solver.setOption("tol",1e-10); solver.setOption("hessian_approximation","limited-memory"); // pass_nonlinear_variables // initialize the solver solver.init(); // Initial condition vector<double> xinit(x.numel(),0); solver.setInput(xinit,"x0"); // Bounds on x vector<double> lbx(x.numel(),-100); vector<double> ubx(x.numel(), 100); lbx[0] = ubx[0] = z0; solver.setInput(lbx,"lbx"); solver.setInput(ubx,"ubx"); // Bounds on the constraints vector<double> lubg(g.numel(),0); solver.setInput(lubg,"lbg"); solver.setInput(lubg,"ubg"); // Solve the problem solver.solve(); // Print the time points vector<double> t_opt(N*(K+1)+1); for(int i=0; i<N; ++i) for(int j=0; j<=K; ++j) t_opt[j + (K+1)*i] = h*(i + tau_root[j]); t_opt.back() = 1; cout << "time points: " << t_opt << endl; resfile << t_opt << endl; // Print the optimal cost cout << "optimal cost: " << solver.output(NLP_SOLVER_F) << endl; // Print the optimal solution vector<double> xopt(x.numel()); solver.getOutput(xopt,"x"); cout << "optimal solution: " << xopt << endl; resfile << xopt << endl; } resfile.close(); return 0; }
void LiftedSQPInternal::init(){ // Call the init method of the base class NlpSolverInternal::init(); // Number of lifted variables nv = getOption("num_lifted"); if(verbose_){ cout << "Initializing SQP method with " << nx_ << " variables and " << ng_ << " constraints." << endl; cout << "Lifting " << nv << " variables." << endl; if(gauss_newton_){ cout << "Gauss-Newton objective with " << F_.input().numel() << " terms." << endl; } } // Read options max_iter_ = getOption("max_iter"); max_iter_ls_ = getOption("max_iter_ls"); toldx_ = getOption("toldx"); tolgl_ = getOption("tolgl"); sigma_ = getOption("sigma"); rho_ = getOption("rho"); mu_safety_ = getOption("mu_safety"); eta_ = getOption("eta"); tau_ = getOption("tau"); // Assume SXFunction for now SXFunction ffcn = shared_cast<SXFunction>(F_); casadi_assert(!ffcn.isNull()); SXFunction gfcn = shared_cast<SXFunction>(G_); casadi_assert(!gfcn.isNull()); // Extract the free variables and split into independent and dependent variables SX x = ffcn.inputExpr(0); int nx = x.size(); nu = nx-nv; SX u = x[Slice(0,nu)]; SX v = x[Slice(nu,nu+nv)]; // Extract the constraint equations and split into constraints and definitions of dependent variables SX f1 = ffcn.outputExpr(0); int nf1 = f1.numel(); SX g = gfcn.outputExpr(0); int nf2 = g.numel()-nv; SX v_eq = g(Slice(0,nv)); SX f2 = g(Slice(nv,nv+nf2)); // Definition of v SX v_def = v_eq + v; // Objective function SX f; // Multipliers SX lam_x, lam_g, lam_f2; if(gauss_newton_){ // Least square objective f = inner_prod(f1,f1)/2; } else { // Scalar objective function f = f1; // Lagrange multipliers for the simple bounds on u SX lam_u = ssym("lam_u",nu); // Lagrange multipliers for the simple bounds on v SX lam_v = ssym("lam_v",nv); // Lagrange multipliers for the simple bounds on x lam_x = vertcat(lam_u,lam_v); // Lagrange multipliers corresponding to the definition of the dependent variables SX lam_v_eq = ssym("lam_v_eq",nv); // Lagrange multipliers for the nonlinear constraints that aren't eliminated lam_f2 = ssym("lam_f2",nf2); if(verbose_){ cout << "Allocated intermediate variables." << endl; } // Lagrange multipliers for constraints lam_g = vertcat(lam_v_eq,lam_f2); // Lagrangian function SX lag = f + inner_prod(lam_x,x); if(!f2.empty()) lag += inner_prod(lam_f2,f2); if(!v.empty()) lag += inner_prod(lam_v_eq,v_def); // Gradient of the Lagrangian SX lgrad = casadi::gradient(lag,x); if(!v.empty()) lgrad -= vertcat(SX::zeros(nu),lam_v_eq); // Put here to ensure that lgrad is of the form "h_extended -v_extended" makeDense(lgrad); if(verbose_){ cout << "Generated the gradient of the Lagrangian." << endl; } // Condensed gradient of the Lagrangian f1 = lgrad[Slice(0,nu)]; nf1 = nu; // Gradient of h SX v_eq_grad = lgrad[Slice(nu,nu+nv)]; // Reverse lam_v_eq and v_eq_grad SX v_eq_grad_reversed = v_eq_grad; copy(v_eq_grad.rbegin(),v_eq_grad.rend(),v_eq_grad_reversed.begin()); SX lam_v_eq_reversed = lam_v_eq; copy(lam_v_eq.rbegin(),lam_v_eq.rend(),lam_v_eq_reversed.begin()); // Augment h and lam_v_eq v_eq.append(v_eq_grad_reversed); v.append(lam_v_eq_reversed); } // Residual function G SXVector G_in(G_NUM_IN); G_in[G_X] = x; G_in[G_LAM_X] = lam_x; G_in[G_LAM_G] = lam_g; SXVector G_out(G_NUM_OUT); G_out[G_D] = v_eq; G_out[G_G] = g; G_out[G_F] = f; rfcn_ = SXFunction(G_in,G_out); rfcn_.setOption("number_of_fwd_dir",0); rfcn_.setOption("number_of_adj_dir",0); rfcn_.setOption("live_variables",true); rfcn_.init(); if(verbose_){ cout << "Generated residual function ( " << shared_cast<SXFunction>(rfcn_).getAlgorithmSize() << " nodes)." << endl; } // Difference vector d SX d = ssym("d",nv); if(!gauss_newton_){ vector<SX> dg = ssym("dg",nv).data(); reverse(dg.begin(),dg.end()); d.append(dg); } // Substitute out the v from the h SX d_def = (v_eq + v)-d; SXVector ex(3); ex[0] = f1; ex[1] = f2; ex[2] = f; substituteInPlace(v, d_def, ex, false); SX f1_z = ex[0]; SX f2_z = ex[1]; SX f_z = ex[2]; // Modified function Z enum ZIn{Z_U,Z_D,Z_LAM_X,Z_LAM_F2,Z_NUM_IN}; SXVector zfcn_in(Z_NUM_IN); zfcn_in[Z_U] = u; zfcn_in[Z_D] = d; zfcn_in[Z_LAM_X] = lam_x; zfcn_in[Z_LAM_F2] = lam_f2; enum ZOut{Z_D_DEF,Z_F12,Z_NUM_OUT}; SXVector zfcn_out(Z_NUM_OUT); zfcn_out[Z_D_DEF] = d_def; zfcn_out[Z_F12] = vertcat(f1_z,f2_z); SXFunction zfcn(zfcn_in,zfcn_out); zfcn.init(); if(verbose_){ cout << "Generated reconstruction function ( " << zfcn.getAlgorithmSize() << " nodes)." << endl; } // Matrix A and B in lifted Newton SX B = zfcn.jac(Z_U,Z_F12); SX B1 = B(Slice(0,nf1),Slice(0,B.size2())); SX B2 = B(Slice(nf1,B.size1()),Slice(0,B.size2())); if(verbose_){ cout << "Formed B1 (dimension " << B1.size1() << "-by-" << B1.size2() << ", "<< B1.size() << " nonzeros) " << "and B2 (dimension " << B2.size1() << "-by-" << B2.size2() << ", "<< B2.size() << " nonzeros)." << endl; } // Step in u SX du = ssym("du",nu); SX dlam_f2 = ssym("dlam_f2",lam_f2.sparsity()); SX b1 = f1_z; SX b2 = f2_z; SX e; if(nv > 0){ // Directional derivative of Z vector<vector<SX> > Z_fwdSeed(2,zfcn_in); vector<vector<SX> > Z_fwdSens(2,zfcn_out); vector<vector<SX> > Z_adjSeed; vector<vector<SX> > Z_adjSens; Z_fwdSeed[0][Z_U].setZero(); Z_fwdSeed[0][Z_D] = -d; Z_fwdSeed[0][Z_LAM_X].setZero(); Z_fwdSeed[0][Z_LAM_F2].setZero(); Z_fwdSeed[1][Z_U] = du; Z_fwdSeed[1][Z_D] = -d; Z_fwdSeed[1][Z_LAM_X].setZero(); Z_fwdSeed[1][Z_LAM_F2] = dlam_f2; zfcn.eval(zfcn_in,zfcn_out,Z_fwdSeed,Z_fwdSens,Z_adjSeed,Z_adjSens); b1 += Z_fwdSens[0][Z_F12](Slice(0,nf1)); b2 += Z_fwdSens[0][Z_F12](Slice(nf1,B.size1())); e = Z_fwdSens[1][Z_D_DEF]; } if(verbose_){ cout << "Formed b1 (dimension " << b1.size1() << "-by-" << b1.size2() << ", "<< b1.size() << " nonzeros) " << "and b2 (dimension " << b2.size1() << "-by-" << b2.size2() << ", "<< b2.size() << " nonzeros)." << endl; } // Generate Gauss-Newton Hessian if(gauss_newton_){ b1 = mul(trans(B1),b1); B1 = mul(trans(B1),B1); if(verbose_){ cout << "Gauss Newton Hessian (dimension " << B1.size1() << "-by-" << B1.size2() << ", "<< B1.size() << " nonzeros)." << endl; } } // Make sure b1 and b2 are dense vectors makeDense(b1); makeDense(b2); // Quadratic approximation SXVector lfcn_in(LIN_NUM_IN); lfcn_in[LIN_X] = x; lfcn_in[LIN_D] = d; lfcn_in[LIN_LAM_X] = lam_x; lfcn_in[LIN_LAM_G] = lam_g; SXVector lfcn_out(LIN_NUM_OUT); lfcn_out[LIN_F1] = b1; lfcn_out[LIN_J1] = B1; lfcn_out[LIN_F2] = b2; lfcn_out[LIN_J2] = B2; lfcn_ = SXFunction(lfcn_in,lfcn_out); // lfcn_.setOption("verbose",true); lfcn_.setOption("number_of_fwd_dir",0); lfcn_.setOption("number_of_adj_dir",0); lfcn_.setOption("live_variables",true); lfcn_.init(); if(verbose_){ cout << "Generated linearization function ( " << shared_cast<SXFunction>(lfcn_).getAlgorithmSize() << " nodes)." << endl; } // Step expansion SXVector efcn_in(EXP_NUM_IN); copy(lfcn_in.begin(),lfcn_in.end(),efcn_in.begin()); efcn_in[EXP_DU] = du; efcn_in[EXP_DLAM_F2] = dlam_f2; efcn_ = SXFunction(efcn_in,e); efcn_.setOption("number_of_fwd_dir",0); efcn_.setOption("number_of_adj_dir",0); efcn_.setOption("live_variables",true); efcn_.init(); if(verbose_){ cout << "Generated step expansion function ( " << shared_cast<SXFunction>(efcn_).getAlgorithmSize() << " nodes)." << endl; } // Current guess for the primal solution DMatrix &x_k = output(NLP_SOLVER_X); // Current guess for the dual solution DMatrix &lam_x_k = output(NLP_SOLVER_LAM_X); DMatrix &lam_g_k = output(NLP_SOLVER_LAM_G); // Allocate a QP solver QpSolverCreator qp_solver_creator = getOption("qp_solver"); qp_solver_ = qp_solver_creator(B1.sparsity(),B2.sparsity()); // Set options if provided if(hasSetOption("qp_solver_options")){ Dictionary qp_solver_options = getOption("qp_solver_options"); qp_solver_.setOption(qp_solver_options); } // Initialize the QP solver qp_solver_.init(); if(verbose_){ cout << "Allocated QP solver." << endl; } // Residual d_k_ = DMatrix(d.sparsity(),0); // Primal step dx_k_ = DMatrix(x_k.sparsity()); // Dual step dlam_x_k_ = DMatrix(lam_x_k.sparsity()); dlam_g_k_ = DMatrix(lam_g_k.sparsity()); }