private static double[] obstacleFieldErrorGradient(IObstaclePositionProvider ops, GridCarModelState state, int time) { //C = sum((1/d(X) - 1/d(0))^2) //dC/dy_x =... //dC/dy_y =... double ksi = 0.1; double disterr = 0; double orxerr = 0; double oryerr = 0; List <ObstacleState> obstacles = ops.GetObstacleStates(0); foreach (ObstacleState obst in obstacles)//cel az origo, tehat az origohoz relativak az akadalyok, origo felfele nez { double d = ComMath.Normal(Math.Sqrt(obst.pp.position.X * obst.pp.position.X + obst.pp.position.Y * obst.pp.position.Y), GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, MAX_NEURON_VALUE); double a = ComMath.Normal(state.TargetDist, GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, MAX_NEURON_VALUE); double ang = Math.PI - (Math.Atan2(obst.pp.position.Y, obst.pp.position.X) + Math.PI) + state.TargetAngle - state.TargetFinishAngle; if (ang > Math.PI) { ang -= 2 * Math.PI; } if (ang < -Math.PI) { ang += 2 * Math.PI; } double AA = -2 * d * Math.Cos(ang); double BB = d * d; double obstdist = Math.Sqrt(a * a + BB + AA * a); double obstang = state.TargetAngle + Math.Sign(ang) * Math.Acos((a * a + obstdist * obstdist - d * d) / (2 * a * obstdist)); double r = ComMath.Normal(obst.radius + CarModel.SHAFT_LENGTH / 2, GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, MAX_NEURON_VALUE); double dist = obstdist - r; if (dist <= 0.0001) { dist = 0.0001; } double err = 1 / (2 * (dist * dist * dist)); disterr += -(AA + 2 * a) * err; double angerr = (-2 * a * d * Math.Sin(ang)) * err; orxerr += -Math.Sin(state.TargetAngle) * angerr; oryerr += Math.Cos(state.TargetAngle) * angerr; } if (obstacles.Count > 0) { disterr /= obstacles.Count; orxerr /= obstacles.Count; oryerr /= obstacles.Count; } return(new double[] { -ksi * disterr, -ksi * orxerr, -ksi * oryerr }); }
//private double obstacleFieldError(GridCarModelState state) //{ // double err = 0; // List<ObstacleState> obstacles = obstacleProvider.GetObstacleStates(1); // foreach (ObstacleState obst in obstacles) // { // double d = ComMath.Normal(state.TargetDist, GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, MIN_NEURON_VALUE, MAX_NEURON_VALUE); // double x = Math.Cos(state.TargetAngle - state.TargetFinishAngle) * d; // double y = Math.Sin(state.TargetAngle - state.TargetFinishAngle) * d; // double x0 = ComMath.Normal(obst.pp.position.X, CarModelState.MIN_POS_X, CarModelState.MAX_POS_X, MIN_NEURON_VALUE, MAX_NEURON_VALUE); // double y0 = ComMath.Normal(obst.pp.position.Y, CarModelState.MIN_POS_X, CarModelState.MAX_POS_X, MIN_NEURON_VALUE, MAX_NEURON_VALUE); // double dist = Math.Sqrt((x - x0) * (x - x0) + (y - y0) * (y - y0)); // err += Math.Pow(1 / dist - 1 / obst.radius, 2); // } // return err; //} private static PolarGrid obstaclePolarGrid(IObstaclePositionProvider ops, GridCarModelState state) { List <ObstacleState> obstacles = ops.GetObstacleStates(0); PolarGrid pg = new PolarGrid(); foreach (ObstacleState obst in obstacles) { GridObstacleState gos = GridObstacleState.FromObstacleState(obst, state); pg.AddObstacle(gos); } return(pg); }
public GridNeuralController(IGridModelSimulator model, IObstaclePositionProvider obstacle, ICarPositionProvider start, IFinishPositionProvider finish) { this.model = model; //controller = new MLPDll(new int[] { 40, 1 }, 5, true);//4 bemenet a state, 1 kimenet az input controllerOriginal = new MLPDll(new int[] { 40, 1 }, 5, false);//4 bemenet a state, 1 kimenet az input obstacleProvider = obstacle; carStateProvider = start; finishStateProvider = finish; trainingStopped = true; mu = 0.005; }
private static double[] obstacleFieldErrorGradient(IObstaclePositionProvider ops, GridCarModelState state, int time) { //C = sum((1/d(X) - 1/d(0))^2) //dC/dy_x =... //dC/dy_y =... double ksi = 0.1; double disterr = 0; double orxerr = 0; double oryerr = 0; List<ObstacleState> obstacles = ops.GetObstacleStates(0); foreach (ObstacleState obst in obstacles)//cel az origo, tehat az origohoz relativak az akadalyok, origo felfele nez { double d = ComMath.Normal(Math.Sqrt(obst.pp.position.X * obst.pp.position.X + obst.pp.position.Y * obst.pp.position.Y), GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, MAX_NEURON_VALUE); double a = ComMath.Normal(state.TargetDist , GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, MAX_NEURON_VALUE); double ang = Math.PI - (Math.Atan2(obst.pp.position.Y, obst.pp.position.X) + Math.PI) + state.TargetAngle - state.TargetFinishAngle; if (ang > Math.PI) ang -= 2 * Math.PI; if (ang < -Math.PI) ang += 2 * Math.PI; double AA = -2 * d * Math.Cos(ang); double BB = d * d; double obstdist = Math.Sqrt(a * a + BB + AA * a); double obstang = state.TargetAngle + Math.Sign(ang) * Math.Acos((a * a + obstdist * obstdist - d * d) / (2 * a * obstdist)); double r = ComMath.Normal(obst.radius + CarModel.SHAFT_LENGTH / 2, GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, MAX_NEURON_VALUE); double dist = obstdist - r; if (dist <= 0.0001) dist = 0.0001; double err = 1 / (2 * (dist * dist * dist)); disterr += -(AA + 2 * a) * err; double angerr = (-2 * a * d * Math.Sin(ang)) * err; orxerr += -Math.Sin(state.TargetAngle) * angerr; oryerr += Math.Cos(state.TargetAngle) * angerr; } if (obstacles.Count > 0) { disterr /= obstacles.Count; orxerr /= obstacles.Count; oryerr /= obstacles.Count; } return new double[] { -ksi * disterr, -ksi * orxerr, -ksi * oryerr }; }
public NeuralController(IModelSimulator model, IObstaclePositionProvider obstacle, ICarPositionProvider start, IFinishPositionProvider finish) { this.model = model; if (INPUT_TYPE == inputType.wheelAngle) { controller = new MLPDll(new int[] { 20, 1 }, 4);//4 bemenet a state, 1 kimenet az input } else if (INPUT_TYPE == inputType.wheelSpeed) { controller = new MLPDll(new int[] { 75, 2 }, 4);//4 bemenet a state, 2 kimenet az input } obstacleProvider = obstacle; carStateProvider = start; finishStateProvider = finish; trainingStopped = true; mu = 0.005; }
public void SetSimulation(bool b) { if (b) { carPositionProvider = simManager; finishPositionProvider = simManager; obstacleProvider = simManager; simulation = true; } else { carPositionProvider = cameraCarPos; finishPositionProvider = cameraCarPos; obstacleProvider = cameraCarPos; simulation = false; } }
private static double TrainOneEpoch(MLPDll controller, IGridModelSimulator model, ICarPositionProvider cps, IFinishPositionProvider fps, IObstaclePositionProvider ops, double mu, int maxSimCount, out double SumSimCount, out List<GridCarModelState> innerStates) { double sumSimCount = 0; double error = 0; innerStates = new List<GridCarModelState>(); List<double> deltaws = new List<double>(); MLPDll[] controllers = new MLPDll[maxSimCount]; IGridModelSimulator[] models = new IGridModelSimulator[maxSimCount]; GridCarModelState state = GridCarModelState.FromCarModelState(cps.GetCarState()); GridCarModelInput input = new GridCarModelInput(); //kimenet kiszamitasa int simCount = 0; List<double[]> singleErrors = new List<double[]>(); List<double[]> regularizationErrors = new List<double[]>(); GridCarModelState laststate; bool earlyStop; do { if (simCount == 0) controllers[simCount] = new MLPDll(controller);//lemasoljuk else controllers[simCount] = new MLPDll(controllers[simCount - 1]); models[simCount] = model.Clone();//a modellt is laststate = state; GridNeuralController.SimulateOneStep(controllers[simCount], models[simCount], state, out input, out state);//vegigszimulaljuk a simCount darab controlleren es modellen innerStates.Add(state); //kozbulso hibak kiszamitasa, itt csak az akadalyoktol valo tavolsag "hibajat" vesszuk figyelembe, irany nem szamit -> hibaja 0 regularizationErrors.Add(obstacleFieldErrorGradient(ops, state, simCount)); //minden pont celtol vett tavolsaga double disterror = ComMath.Normal(state.TargetDist, GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, 1); double orientationerror = disterror; if (orientationerror < 0.2) orientationerror = 0; double finishorientationerror = disterror; if (finishorientationerror > 0.05) finishorientationerror = 0; else finishorientationerror = 1; double finishX = Math.Cos(Math.PI - fps.GetFinishState(simCount).Angle); double finishY = Math.Sin(Math.PI - fps.GetFinishState(simCount).Angle); singleErrors.Add(new double[] { -disterror * MAX_NEURON_VALUE , orientationerror*ComMath.Normal(1 - state.TargetOrientation.X,GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE), orientationerror*ComMath.Normal(0 - state.TargetOrientation.Y,GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE), finishorientationerror*ComMath.Normal(finishX - state.TargetFinishOrientation.X,GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE), finishorientationerror*ComMath.Normal(finishY - state.TargetFinishOrientation.Y,GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE) } ); ++simCount; earlyStop = false; if (simCount > 3) { double[] err1 = singleErrors[simCount - 1]; double[] err2 = singleErrors[simCount - 2]; double[] err3 = singleErrors[simCount - 3]; double error1, error2, error3; error1 = error2 = error3 = 0; for (int i = 0; i < 1; i++)//err1.Length { error1 += err1[i] * err1[i]; error2 += err2[i] * err2[i]; error3 += err3[i] * err3[i]; } earlyStop = ((error1 > error2) && (error3 > error2)); if (earlyStop) { //utolso elemet toroljuk singleErrors.RemoveAt(singleErrors.Count - 1); regularizationErrors.RemoveAt(regularizationErrors.Count - 1); innerStates.RemoveAt(innerStates.Count - 1); --simCount; } } } while ((simCount < maxSimCount) && !earlyStop); double[] errors = singleErrors[singleErrors.Count - 1]; sumSimCount += simCount; //hibavisszaterjesztes for (int i = simCount - 1; i >= 0; --i) { double[] sensitibility; models[i].CalcErrorSensibility(errors, out sensitibility); double[] inputSensitibility; inputSensitibility = new double[1]; inputSensitibility[0] = sensitibility[5]; double[] sensitibility2; controllers[i].SetOutputError(inputSensitibility); controllers[i].Backpropagate(); controllers[i].CalculateDeltaWeights(); sensitibility2 = controllers[i].SensitibilityD(); errors[0] = (sensitibility[0] + sensitibility2[0] + 0.1 * singleErrors[i][0]); errors[1] = (sensitibility[1] + sensitibility2[1] + 0 * singleErrors[i][1]); errors[2] = (sensitibility[2] + sensitibility2[2] + 0 * singleErrors[i][2]); errors[3] = (sensitibility[3] + sensitibility2[3] + singleErrors[i][3]); errors[4] = (sensitibility[4] + sensitibility2[4] + singleErrors[i][4]); //regularizaciobol szarmazo hiba hozzaadasa errors[0] += regularizationErrors[i][0]; errors[1] += regularizationErrors[i][1]; errors[2] += regularizationErrors[i][2]; } controller.ClearDeltaWeights(); //sulymodositasok osszegzese for (int i2 = 0; i2 < simCount; ++i2) { controller.AddDeltaWeights(controllers[i2]); } float maxdw = controller.MaxDeltaWeight(); //if (maxdw < 50) maxdw = 50; controller.ChangeWeights(mu / maxdw); ////sulymodositasok osszegzese //for (int i2 = 0; i2 < simCount; ++i2) //simCount //{ // int count = 0; // for (int i = 1; i < controllers[i2]; ++i) // { // foreach (INeuron n in controllers[i2].mlp[i]) // { // foreach (NeuronInput ni in ((Neuron)n).inputs) // { // if (deltaws.Count <= count) deltaws.Add(ni.deltaw); // else deltaws[count] += ni.deltaw; // ++count; // } // } // } //} ////legnagyobb sulymodositas ertekenek meghatarozasa, majd ezzel normalas //double maxdw = 1; //foreach (double dw in deltaws) //{ // if (Math.Abs(dw) > maxdw) maxdw = Math.Abs(dw); //} //if (maxdw < 50) maxdw = 50; ////sulymodositasok ervenyre juttatasa a controllerben //int count2 = 0; //for (int i = 1; i < controller.mlp.Count; ++i) //{ // foreach (INeuron n in controller.mlp[i]) // { // foreach (NeuronInput ni in ((Neuron)n).inputs) // { // ni.w += mu * deltaws[count2] / maxdw; // ++count2; // } // } //} SumSimCount = sumSimCount; return error; }
//private double obstacleFieldError(GridCarModelState state) //{ // double err = 0; // List<ObstacleState> obstacles = obstacleProvider.GetObstacleStates(1); // foreach (ObstacleState obst in obstacles) // { // double d = ComMath.Normal(state.TargetDist, GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, MIN_NEURON_VALUE, MAX_NEURON_VALUE); // double x = Math.Cos(state.TargetAngle - state.TargetFinishAngle) * d; // double y = Math.Sin(state.TargetAngle - state.TargetFinishAngle) * d; // double x0 = ComMath.Normal(obst.pp.position.X, CarModelState.MIN_POS_X, CarModelState.MAX_POS_X, MIN_NEURON_VALUE, MAX_NEURON_VALUE); // double y0 = ComMath.Normal(obst.pp.position.Y, CarModelState.MIN_POS_X, CarModelState.MAX_POS_X, MIN_NEURON_VALUE, MAX_NEURON_VALUE); // double dist = Math.Sqrt((x - x0) * (x - x0) + (y - y0) * (y - y0)); // err += Math.Pow(1 / dist - 1 / obst.radius, 2); // } // return err; //} private static PolarGrid obstaclePolarGrid(IObstaclePositionProvider ops, GridCarModelState state) { List<ObstacleState> obstacles = ops.GetObstacleStates(0); PolarGrid pg = new PolarGrid(); foreach (ObstacleState obst in obstacles) { GridObstacleState gos = GridObstacleState.FromObstacleState(obst, state); pg.AddObstacle(gos); } return pg; }
private static double TrainOneEpoch(MLPDll controller, IGridModelSimulator model, ICarPositionProvider cps, IFinishPositionProvider fps, IObstaclePositionProvider ops, double mu, int maxSimCount, out double SumSimCount, out List <GridCarModelState> innerStates) { double sumSimCount = 0; double error = 0; innerStates = new List <GridCarModelState>(); List <double> deltaws = new List <double>(); MLPDll[] controllers = new MLPDll[maxSimCount]; IGridModelSimulator[] models = new IGridModelSimulator[maxSimCount]; GridCarModelState state = GridCarModelState.FromCarModelState(cps.GetCarState()); GridCarModelInput input = new GridCarModelInput(); //kimenet kiszamitasa int simCount = 0; List <double[]> singleErrors = new List <double[]>(); List <double[]> regularizationErrors = new List <double[]>(); GridCarModelState laststate; bool earlyStop; do { if (simCount == 0) { controllers[simCount] = new MLPDll(controller); //lemasoljuk } else { controllers[simCount] = new MLPDll(controllers[simCount - 1]); } models[simCount] = model.Clone();//a modellt is laststate = state; GridNeuralController.SimulateOneStep(controllers[simCount], models[simCount], state, out input, out state);//vegigszimulaljuk a simCount darab controlleren es modellen innerStates.Add(state); //kozbulso hibak kiszamitasa, itt csak az akadalyoktol valo tavolsag "hibajat" vesszuk figyelembe, irany nem szamit -> hibaja 0 regularizationErrors.Add(obstacleFieldErrorGradient(ops, state, simCount)); //minden pont celtol vett tavolsaga double disterror = ComMath.Normal(state.TargetDist, GridCarModelState.MIN_DIST, GridCarModelState.MAX_DIST, 0, 1); double orientationerror = disterror; if (orientationerror < 0.2) { orientationerror = 0; } double finishorientationerror = disterror; if (finishorientationerror > 0.05) { finishorientationerror = 0; } else { finishorientationerror = 1; } double finishX = Math.Cos(Math.PI - fps.GetFinishState(simCount).Angle); double finishY = Math.Sin(Math.PI - fps.GetFinishState(simCount).Angle); singleErrors.Add(new double[] { -disterror * MAX_NEURON_VALUE, orientationerror * ComMath.Normal(1 - state.TargetOrientation.X, GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE), orientationerror * ComMath.Normal(0 - state.TargetOrientation.Y, GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE), finishorientationerror * ComMath.Normal(finishX - state.TargetFinishOrientation.X, GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE), finishorientationerror * ComMath.Normal(finishY - state.TargetFinishOrientation.Y, GridCarModelState.MIN_OR_XY, GridCarModelState.MAX_OR_XY, MIN_NEURON_VALUE, MAX_NEURON_VALUE) } ); ++simCount; earlyStop = false; if (simCount > 3) { double[] err1 = singleErrors[simCount - 1]; double[] err2 = singleErrors[simCount - 2]; double[] err3 = singleErrors[simCount - 3]; double error1, error2, error3; error1 = error2 = error3 = 0; for (int i = 0; i < 1; i++)//err1.Length { error1 += err1[i] * err1[i]; error2 += err2[i] * err2[i]; error3 += err3[i] * err3[i]; } earlyStop = ((error1 > error2) && (error3 > error2)); if (earlyStop) { //utolso elemet toroljuk singleErrors.RemoveAt(singleErrors.Count - 1); regularizationErrors.RemoveAt(regularizationErrors.Count - 1); innerStates.RemoveAt(innerStates.Count - 1); --simCount; } } }while ((simCount < maxSimCount) && !earlyStop); double[] errors = singleErrors[singleErrors.Count - 1]; sumSimCount += simCount; //hibavisszaterjesztes for (int i = simCount - 1; i >= 0; --i) { double[] sensitibility; models[i].CalcErrorSensibility(errors, out sensitibility); double[] inputSensitibility; inputSensitibility = new double[1]; inputSensitibility[0] = sensitibility[5]; double[] sensitibility2; controllers[i].SetOutputError(inputSensitibility); controllers[i].Backpropagate(); controllers[i].CalculateDeltaWeights(); sensitibility2 = controllers[i].SensitibilityD(); errors[0] = (sensitibility[0] + sensitibility2[0] + 0.1 * singleErrors[i][0]); errors[1] = (sensitibility[1] + sensitibility2[1] + 0 * singleErrors[i][1]); errors[2] = (sensitibility[2] + sensitibility2[2] + 0 * singleErrors[i][2]); errors[3] = (sensitibility[3] + sensitibility2[3] + singleErrors[i][3]); errors[4] = (sensitibility[4] + sensitibility2[4] + singleErrors[i][4]); //regularizaciobol szarmazo hiba hozzaadasa errors[0] += regularizationErrors[i][0]; errors[1] += regularizationErrors[i][1]; errors[2] += regularizationErrors[i][2]; } controller.ClearDeltaWeights(); //sulymodositasok osszegzese for (int i2 = 0; i2 < simCount; ++i2) { controller.AddDeltaWeights(controllers[i2]); } float maxdw = controller.MaxDeltaWeight(); //if (maxdw < 50) maxdw = 50; controller.ChangeWeights(mu / maxdw); ////sulymodositasok osszegzese //for (int i2 = 0; i2 < simCount; ++i2) //simCount //{ // int count = 0; // for (int i = 1; i < controllers[i2]; ++i) // { // foreach (INeuron n in controllers[i2].mlp[i]) // { // foreach (NeuronInput ni in ((Neuron)n).inputs) // { // if (deltaws.Count <= count) deltaws.Add(ni.deltaw); // else deltaws[count] += ni.deltaw; // ++count; // } // } // } //} ////legnagyobb sulymodositas ertekenek meghatarozasa, majd ezzel normalas //double maxdw = 1; //foreach (double dw in deltaws) //{ // if (Math.Abs(dw) > maxdw) maxdw = Math.Abs(dw); //} //if (maxdw < 50) maxdw = 50; ////sulymodositasok ervenyre juttatasa a controllerben //int count2 = 0; //for (int i = 1; i < controller.mlp.Count; ++i) //{ // foreach (INeuron n in controller.mlp[i]) // { // foreach (NeuronInput ni in ((Neuron)n).inputs) // { // ni.w += mu * deltaws[count2] / maxdw; // ++count2; // } // } //} SumSimCount = sumSimCount; return(error); }