def test_simple_sampling_problem(self):
'''Sample from a twodimensional Gaussian distribution N(0, I)
'''
options = ab.SamplerMetropolisHastingsOptions()
options.transitionKernelSigma = 0.1
sampler = ab.SamplerMetropolisHastings(options)
negLogDensity = ab.OptimizationProblem()
# Add a scalar design variables.
point = ab.Point2d(np.array([0, 0]))
point.setBlockIndex(0)
point.setActive(True)
negLogDensity.addDesignVariable(point)
# Add the error term.
grad = np.array([-1., -1.])
err = ab.TestNonSquaredError(point, grad)
err._p = 0.0
# set mean
negLogDensity.addScalarNonSquaredErrorTerm(err)
# Now let's sample.
sampler.setNegativeLogDensity(negLogDensity)
sampler.checkNegativeLogDensitySetup()
sampler.run(10000)
def test_construction(self):
splineOrder = 4;
spline = createUniformKnotOldBSpline(splineOrder, 6, 3)
sdv = aslam_splines.EuclideanBSplineDesignVariable(spline)
tMin = spline.t_min();
tMax = spline.t_max();
sqrtW = numpy.matrix(numpy.random.random((3, 3)))
W = sqrtW.T * sqrtW;
for derivativeOrder in range(0, splineOrder - 1):
p = aslam_backend.OptimizationProblem()
for i in range(0, sdv.numDesignVariables()) : p.addDesignVariable(sdv.designVariable(i))
aslam_splines.addQuadraticIntegralEuclideanExpressionErrorTermsToProblem(p, tMin, tMax, 100, lambda time : sdv.toEuclideanExpression(time, derivativeOrder), sqrtW)
E = 0;
for i in range(0, p.numErrorTerms()):
E += p.errorTerm(i).evaluateError()
evalQF = lambda t: (numpy.matrix(spline.evalD(t, derivativeOrder)) * W * numpy.matrix(spline.evalD(t, derivativeOrder)).T)[0, 0];
Epy = integrate.quad(evalQF, tMin, tMax)[0]
self.assertAlmostEqual(E, Epy, 3);
def registration(self, target, w=0.0,
objective_type='pt2pt',
maxiter=50, tol=0.001,
feature_fn=lambda x: x):
q = None
ftarget = feature_fn(target)
# build the problem
self.problem = aopt.OptimizationProblem()
T_init = np.array([[-0.99813747, -0.05730897, -0.02091093, 0.03399231],
[0.05726434, -0.99835533, 0.00272772, 0.31433327],
[-0.02103286, 0.00152519, 0.99977762, 0.22997991],
[0., 0., 0., 1.]])
self.T_b_l_Dv = aopt.TransformationDv(sm.Transformation(), rotationActive=True, translationActive=True)
for i in range(0, self.T_b_l_Dv.numDesignVariables()):
self.problem.addDesignVariable(self.T_b_l_Dv.getDesignVariable(i))
for _ in range(maxiter):
T_b_l = self.T_b_l_Dv.toExpression().toTransformationMatrix()
print("Inital laser to body transformation: T_b_l ")
print(T_b_l)
T_l_b = np.linalg.inv(T_b_l)
numPoints = self._source.shape[0]
source = np.hstack([self._source, np.ones((numPoints, 1), dtype=self._source.dtype)])
t_source = np.array([np.dot(T_l_b, np.dot(self._sensor_tfs[i], np.dot(T_b_l, source[i]))) for i in xrange(numPoints)])
t_source = t_source[:, :3]
util.showPointCloud([t_source, target])
fsource = feature_fn(t_source)
estep_res = self.expectation_step(fsource, ftarget, target, objective_type)
res = self.maximization_step(self._source, target, estep_res, w=w,
objective_type=objective_type)
if not q is None and abs(res.q - q) < tol:
break
q = res.q
return res.transformation
def test_simple_optimization(self):
options = ab.OptimizerOptionsRprop()
options.maxIterations = 500
options.numThreads = 1
options.convergenceGradientNorm = 1e-6
options.method = ab.RpropMethod.RPROP_PLUS
optimizer = ab.OptimizerRprop(options)
problem = ab.OptimizationProblem()
D = 2
E = 3
# Add some design variables.
p2ds = []
for d in range(0, D):
point = ab.Point2d(np.array([d, d]))
p2ds.append(point)
problem.addDesignVariable(point)
point.setBlockIndex(d)
point.setActive(True)
# Add some error terms.
errors = []
for e in range(0, E):
for d in range(0, D):
grad = np.array([d + 1, e + 1])
err = ab.TestNonSquaredError(p2ds[d], grad)
err._p = 1.0
errors.append(err)
problem.addScalarNonSquaredErrorTerm(err)
# Now let's optimize.
optimizer.setProblem(problem)
optimizer.checkProblemSetup()
optimizer.optimize()
self.assertLessEqual(optimizer.status.gradientNorm, 1e-3)
# Create random odometry
true_u_k = np.random.random(K);
u_k = true_u_k + sigma_u * np.random.randn(K)
# Integrate the odometry
x_k = np.cumsum(u_k)
true_x_k = np.cumsum(true_u_k)
# Create the noisy measurments
y_k = np.zeros(K)
for k in range(0,K):
y_k[k] = 1.0 / (true_w - true_x_k[k]) + sigma_n * np.random.randn()
# Now we can build an optimization problem.
problem = aslam.OptimizationProblem()
# Create a design variable for the wall position
dv_w = abt.ScalarDesignVariable(true_w + np.random.randn())
# Setting this active means we estimate it.
dv_w.setActive(True)
# Add it to the optimization problem.
problem.addDesignVariable(dv_w)
# Now we add the initial state.
dv_x_km1 = abt.ScalarDesignVariable(x_k[0])
# Setting this active means we estimate it.
dv_x_km1.setActive(True)
# Add it to the optimization problem.
problem.addDesignVariable(dv_x_km1)
def findOrientationPriorCameraToImu(self, imu):
print
print "Estimating imu-camera rotation prior"
# build the problem
problem = aopt.OptimizationProblem()
# Add the rotation as design variable
q_i_c_Dv = aopt.RotationQuaternionDv(self.T_extrinsic.q())
q_i_c_Dv.setActive(True)
problem.addDesignVariable(q_i_c_Dv)
# Add the gyro bias as design variable
gyroBiasDv = aopt.EuclideanPointDv(np.zeros(3))
gyroBiasDv.setActive(True)
problem.addDesignVariable(gyroBiasDv)
#initialize a pose spline using the camera poses
poseSpline = self.initPoseSplineFromCamera(timeOffsetPadding=0.0)
for im in imu.imuData:
tk = im.stamp.toSec()
if tk > poseSpline.t_min() and tk < poseSpline.t_max():
#DV expressions
R_i_c = q_i_c_Dv.toExpression()
bias = gyroBiasDv.toExpression()
#get the vision predicted omega and measured omega (IMU)
omega_predicted = R_i_c * aopt.EuclideanExpression(
np.matrix(
poseSpline.angularVelocityBodyFrame(tk)).transpose())
omega_measured = im.omega
#error term
gerr = ket.GyroscopeError(omega_measured, im.omegaInvR,
omega_predicted, bias)
problem.addErrorTerm(gerr)
#define the optimization
options = aopt.Optimizer2Options()
options.verbose = False
options.linearSolver = aopt.BlockCholeskyLinearSystemSolver()
options.nThreads = 2
options.convergenceDeltaX = 1e-4
options.convergenceDeltaJ = 1
options.maxIterations = 50
#run the optimization
optimizer = aopt.Optimizer2(options)
optimizer.setProblem(problem)
#get the prior
try:
optimizer.optimize()
except:
sm.logFatal("Failed to obtain orientation prior!")
sys.exit(-1)
#overwrite the external rotation prior (keep the external translation prior)
R_i_c = q_i_c_Dv.toRotationMatrix().transpose()
self.T_extrinsic = sm.Transformation(
sm.rt2Transform(R_i_c, self.T_extrinsic.t()))
#set the gyro bias prior (if we have more than 1 cameras use recursive average)
b_gyro = bias.toEuclidean()
imu.GyroBiasPriorCount += 1
imu.GyroBiasPrior = (
imu.GyroBiasPriorCount - 1.0
) / imu.GyroBiasPriorCount * imu.GyroBiasPrior + 1.0 / imu.GyroBiasPriorCount * b_gyro
#print result
print " Orientation prior camera-imu found as: (T_i_c)"
print R_i_c
print " Gyro bias prior found as: (b_gyro)"
print b_gyro
import fcl_python as fcl
import sm
# Setup
plotCircles = False
sm.setLoggingLevel(sm.LoggingLevel.Debug)
scene = putil.populateScene(2, 7.0)
fig = pl.figure()
ax = fig.add_subplot(111)
ax.grid('on')
putil.plotScene(scene, ax, plotCircles=plotCircles)
# Aslam optimizer optimization problem
problem = opt.OptimizationProblem()
for id, optAgent in scene.optAgents.iteritems():
optAgent.trajectory.addDesignVariables(problem)
print "Added {0} design varibales of agent {1}".format(len(optAgent.trajectory.getDesignVariables()), id)
featureContainer = planner.FeatureContainer()
featureContainer.push_back('singleton_integrated_acceleration', planner.OptAgentType.PEDESTRIAN, 1.0)
featureContainer.push_back('singleton_integrated_velocity', planner.OptAgentType.PEDESTRIAN, 1.0)
featureContainer.push_back('singleton_integrated_rotation_rate', planner.OptAgentType.PEDESTRIAN, 1.0)
featureContainer.push_back('pairwise_integrated_distance', planner.OptAgentType.PEDESTRIAN, 0.0)
featureContainer.addErrorTerms(scene, problem)
# Optimization options
options = opt.OptimizerRpropOptions()
def solveFullBatch(cameras, baseline_guesses, graph):
############################################
## solve the bundle adjustment
############################################
problem = aopt.OptimizationProblem()
#add camera dvs
for cam in cameras:
cam.setDvActiveStatus(True, True, False)
problem.addDesignVariable(cam.dv.distortionDesignVariable())
problem.addDesignVariable(cam.dv.projectionDesignVariable())
problem.addDesignVariable(cam.dv.shutterDesignVariable())
baseline_dvs = list()
for baseline_idx in range(0, len(cameras) - 1):
baseline_dv = aopt.TransformationDv(baseline_guesses[baseline_idx])
for i in range(0, baseline_dv.numDesignVariables()):
problem.addDesignVariable(baseline_dv.getDesignVariable(i))
baseline_dvs.append(baseline_dv)
#corner uncertainty
cornerUncertainty = 1.0
R = np.eye(2) * cornerUncertainty * cornerUncertainty
invR = np.linalg.inv(R)
#get the target
target = cameras[0].ctarget.detector.target()
#Add calibration target reprojection error terms for all camera in chain
target_pose_dvs = list()
#shuffle the views
reprojectionErrors = []
timestamps = graph.obs_db.getAllViewTimestamps()
for view_id, timestamp in enumerate(timestamps):
#get all observations for all cams at this time
obs_tuple = graph.obs_db.getAllObsAtTimestamp(timestamp)
#create a target pose dv for all target views (= T_cam0_w)
T0 = graph.getTargetPoseGuess(timestamp, cameras, baseline_guesses)
target_pose_dv = addPoseDesignVariable(problem, T0)
target_pose_dvs.append(target_pose_dv)
for cidx, obs in obs_tuple:
cam = cameras[cidx]
#calibration target coords to camera X coords
T_cam0_calib = target_pose_dv.toExpression().inverse()
#build pose chain (target->cam0->baselines->camN)
T_camN_calib = T_cam0_calib
for idx in range(0, cidx):
T_camN_calib = baseline_dvs[idx].toExpression() * T_camN_calib
## add error terms
for i in range(0, target.size()):
p_target = aopt.HomogeneousExpression(
sm.toHomogeneous(target.point(i)))
valid, y = obs.imagePoint(i)
if valid:
rerr = cameras[cidx].model.reprojectionError(
y, invR, T_camN_calib * p_target, cameras[cidx].dv)
problem.addErrorTerm(rerr)
reprojectionErrors.append(rerr)
sm.logDebug("solveFullBatch: added {0} camera error terms".format(
len(reprojectionErrors)))
############################################
## solve
############################################
options = aopt.Optimizer2Options()
options.verbose = True if sm.getLoggingLevel(
) == sm.LoggingLevel.Debug else False
options.nThreads = 4
options.convergenceDeltaX = 1e-3
options.convergenceDeltaJ = 1
options.maxIterations = 250
options.trustRegionPolicy = aopt.LevenbergMarquardtTrustRegionPolicy(10)
optimizer = aopt.Optimizer2(options)
optimizer.setProblem(problem)
#verbose output
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
sm.logDebug("Before optimization:")
e2 = np.array([e.evaluateError() for e in reprojectionErrors])
sm.logDebug(
" Reprojection error squarred (camL): mean {0}, median {1}, std: {2}"
.format(np.mean(e2), np.median(e2), np.std(e2)))
#run intrinsic calibration
try:
retval = optimizer.optimize()
if retval.linearSolverFailure:
sm.logError("calibrateIntrinsics: Optimization failed!")
success = not retval.linearSolverFailure
except:
sm.logError("calibrateIntrinsics: Optimization failed!")
success = False
baselines = list()
for baseline_dv in baseline_dvs:
baselines.append(sm.Transformation(baseline_dv.T()))
return success, baselines
def calibrateIntrinsics(cam_geometry,
obslist,
distortionActive=True,
intrinsicsActive=True):
#verbose output
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
d = cam_geometry.geometry.projection().distortion().getParameters(
).flatten()
p = cam_geometry.geometry.projection().getParameters().flatten()
sm.logDebug("calibrateIntrinsics: intrinsics guess: {0}".format(p))
sm.logDebug("calibrateIntrinsics: distortion guess: {0}".format(d))
############################################
## solve the bundle adjustment
############################################
problem = aopt.OptimizationProblem()
#add camera dvs
cam_geometry.setDvActiveStatus(intrinsicsActive, distortionActive, False)
problem.addDesignVariable(cam_geometry.dv.distortionDesignVariable())
problem.addDesignVariable(cam_geometry.dv.projectionDesignVariable())
problem.addDesignVariable(cam_geometry.dv.shutterDesignVariable())
#corner uncertainty
cornerUncertainty = 1.0
R = np.eye(2) * cornerUncertainty * cornerUncertainty
invR = np.linalg.inv(R)
#get the image and target points corresponding to the frame
target = cam_geometry.ctarget.detector.target()
#target pose dv for all target views (=T_camL_w)
reprojectionErrors = []
sm.logDebug(
"calibrateIntrinsics: adding camera error terms for {0} calibration targets"
.format(len(obslist)))
target_pose_dvs = list()
for obs in obslist:
success, T_t_c = cam_geometry.geometry.estimateTransformation(obs)
target_pose_dv = addPoseDesignVariable(problem, T_t_c)
target_pose_dvs.append(target_pose_dv)
T_cam_w = target_pose_dv.toExpression().inverse()
## add error terms
for i in range(0, target.size()):
p_target = aopt.HomogeneousExpression(
sm.toHomogeneous(target.point(i)))
valid, y = obs.imagePoint(i)
if valid:
rerr = cam_geometry.model.reprojectionError(
y, invR, T_cam_w * p_target, cam_geometry.dv)
problem.addErrorTerm(rerr)
reprojectionErrors.append(rerr)
sm.logDebug("calibrateIntrinsics: added {0} camera error terms".format(
len(reprojectionErrors)))
############################################
## solve
############################################
options = aopt.Optimizer2Options()
options.verbose = True if sm.getLoggingLevel(
) == sm.LoggingLevel.Debug else False
options.nThreads = 4
options.convergenceDeltaX = 1e-3
options.convergenceDeltaJ = 1
options.maxIterations = 200
options.trustRegionPolicy = aopt.LevenbergMarquardtTrustRegionPolicy(10)
optimizer = aopt.Optimizer2(options)
optimizer.setProblem(problem)
#verbose output
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
sm.logDebug("Before optimization:")
e2 = np.array([e.evaluateError() for e in reprojectionErrors])
sm.logDebug(
" Reprojection error squarred (camL): mean {0}, median {1}, std: {2}"
.format(np.mean(e2), np.median(e2), np.std(e2)))
#run intrinsic calibration
try:
retval = optimizer.optimize()
if retval.linearSolverFailure:
sm.logError("calibrateIntrinsics: Optimization failed!")
success = not retval.linearSolverFailure
except:
sm.logError("calibrateIntrinsics: Optimization failed!")
success = False
#verbose output
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
d = cam_geometry.geometry.projection().distortion().getParameters(
).flatten()
p = cam_geometry.geometry.projection().getParameters().flatten()
sm.logDebug(
"calibrateIntrinsics: guess for intrinsics cam: {0}".format(p))
sm.logDebug(
"calibrateIntrinsics: guess for distortion cam: {0}".format(d))
return success
def stereoCalibrate(camL_geometry,
camH_geometry,
obslist,
distortionActive=False,
baseline=None):
#####################################################
## find initial guess as median of all pnp solutions
#####################################################
if baseline is None:
r = []
t = []
for obsL, obsH in obslist:
#if we have observations for both camss
if obsL is not None and obsH is not None:
success, T_L = camL_geometry.geometry.estimateTransformation(
obsL)
success, T_H = camH_geometry.geometry.estimateTransformation(
obsH)
baseline = T_H.inverse() * T_L
t.append(baseline.t())
rv = sm.RotationVector()
r.append(rv.rotationMatrixToParameters(baseline.C()))
r_median = np.median(np.asmatrix(r), axis=0).flatten().T
R_median = rv.parametersToRotationMatrix(r_median)
t_median = np.median(np.asmatrix(t), axis=0).flatten().T
baseline_HL = sm.Transformation(sm.rt2Transform(R_median, t_median))
else:
baseline_HL = baseline
#verbose output
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
dL = camL_geometry.geometry.projection().distortion().getParameters(
).flatten()
pL = camL_geometry.geometry.projection().getParameters().flatten()
dH = camH_geometry.geometry.projection().distortion().getParameters(
).flatten()
pH = camH_geometry.geometry.projection().getParameters().flatten()
sm.logDebug("initial guess for stereo calib: {0}".format(
baseline_HL.T()))
sm.logDebug("initial guess for intrinsics camL: {0}".format(pL))
sm.logDebug("initial guess for intrinsics camH: {0}".format(pH))
sm.logDebug("initial guess for distortion camL: {0}".format(dL))
sm.logDebug("initial guess for distortion camH: {0}".format(dH))
############################################
## solve the bundle adjustment
############################################
problem = aopt.OptimizationProblem()
#baseline design variable
baseline_dv = addPoseDesignVariable(problem, baseline_HL)
#target pose dv for all target views (=T_camL_w)
target_pose_dvs = list()
for obsL, obsH in obslist:
if obsL is not None: #use camL if we have an obs for this one
success, T_t_cL = camL_geometry.geometry.estimateTransformation(
obsL)
else:
success, T_t_cH = camH_geometry.geometry.estimateTransformation(
obsH)
T_t_cL = T_t_cH * baseline_HL #apply baseline for the second camera
target_pose_dv = addPoseDesignVariable(problem, T_t_cL)
target_pose_dvs.append(target_pose_dv)
#add camera dvs
camL_geometry.setDvActiveStatus(True, distortionActive, False)
camH_geometry.setDvActiveStatus(True, distortionActive, False)
problem.addDesignVariable(camL_geometry.dv.distortionDesignVariable())
problem.addDesignVariable(camL_geometry.dv.projectionDesignVariable())
problem.addDesignVariable(camL_geometry.dv.shutterDesignVariable())
problem.addDesignVariable(camH_geometry.dv.distortionDesignVariable())
problem.addDesignVariable(camH_geometry.dv.projectionDesignVariable())
problem.addDesignVariable(camH_geometry.dv.shutterDesignVariable())
############################################
## add error terms
############################################
#corner uncertainty
# \todo pass in the detector uncertainty somehow.
cornerUncertainty = 1.0
R = np.eye(2) * cornerUncertainty * cornerUncertainty
invR = np.linalg.inv(R)
#Add reprojection error terms for both cameras
reprojectionErrors0 = []
reprojectionErrors1 = []
for cidx, cam in enumerate([camL_geometry, camH_geometry]):
sm.logDebug(
"stereoCalibration: adding camera error terms for {0} calibration targets"
.format(len(obslist)))
#get the image and target points corresponding to the frame
target = cam.ctarget.detector.target()
#add error terms for all observations
for view_id, obstuple in enumerate(obslist):
#add error terms if we have an observation for this cam
obs = obstuple[cidx]
if obs is not None:
T_cam_w = target_pose_dvs[view_id].toExpression().inverse()
#add the baseline for the second camera
if cidx != 0:
T_cam_w = baseline_dv.toExpression() * T_cam_w
for i in range(0, target.size()):
p_target = aopt.HomogeneousExpression(
sm.toHomogeneous(target.point(i)))
valid, y = obs.imagePoint(i)
if valid:
# Create an error term.
rerr = cam.model.reprojectionError(
y, invR, T_cam_w * p_target, cam.dv)
rerr.idx = i
problem.addErrorTerm(rerr)
if cidx == 0:
reprojectionErrors0.append(rerr)
else:
reprojectionErrors1.append(rerr)
sm.logDebug("stereoCalibrate: added {0} camera error terms".format(
len(reprojectionErrors0) + len(reprojectionErrors1)))
############################################
## solve
############################################
options = aopt.Optimizer2Options()
options.verbose = True if sm.getLoggingLevel(
) == sm.LoggingLevel.Debug else False
options.nThreads = 4
options.convergenceDeltaX = 1e-3
options.convergenceDeltaJ = 1
options.maxIterations = 200
options.trustRegionPolicy = aopt.LevenbergMarquardtTrustRegionPolicy(10)
optimizer = aopt.Optimizer2(options)
optimizer.setProblem(problem)
#verbose output
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
sm.logDebug("Before optimization:")
e2 = np.array([e.evaluateError() for e in reprojectionErrors0])
sm.logDebug(
" Reprojection error squarred (camL): mean {0}, median {1}, std: {2}"
.format(np.mean(e2), np.median(e2), np.std(e2)))
e2 = np.array([e.evaluateError() for e in reprojectionErrors1])
sm.logDebug(
" Reprojection error squarred (camH): mean {0}, median {1}, std: {2}"
.format(np.mean(e2), np.median(e2), np.std(e2)))
sm.logDebug("baseline={0}".format(
baseline_dv.toTransformationMatrix()))
try:
retval = optimizer.optimize()
if retval.linearSolverFailure:
sm.logError("stereoCalibrate: Optimization failed!")
success = not retval.linearSolverFailure
except:
sm.logError("stereoCalibrate: Optimization failed!")
success = False
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
sm.logDebug("After optimization:")
e2 = np.array([e.evaluateError() for e in reprojectionErrors0])
sm.logDebug(
" Reprojection error squarred (camL): mean {0}, median {1}, std: {2}"
.format(np.mean(e2), np.median(e2), np.std(e2)))
e2 = np.array([e.evaluateError() for e in reprojectionErrors1])
sm.logDebug(
" Reprojection error squarred (camH): mean {0}, median {1}, std: {2}"
.format(np.mean(e2), np.median(e2), np.std(e2)))
#verbose output
if sm.getLoggingLevel() == sm.LoggingLevel.Debug:
dL = camL_geometry.geometry.projection().distortion().getParameters(
).flatten()
pL = camL_geometry.geometry.projection().getParameters().flatten()
dH = camH_geometry.geometry.projection().distortion().getParameters(
).flatten()
pH = camH_geometry.geometry.projection().getParameters().flatten()
sm.logDebug("guess for intrinsics camL: {0}".format(pL))
sm.logDebug("guess for intrinsics camH: {0}".format(pH))
sm.logDebug("guess for distortion camL: {0}".format(dL))
sm.logDebug("guess for distortion camH: {0}".format(dH))
if success:
baseline_HL = sm.Transformation(baseline_dv.toTransformationMatrix())
return success, baseline_HL
else:
#return the initial guess if we fail
return success, baseline_HL
sm.seed(int(time.time()*1000000)) # required to add randomness to the sampling procedure
s = pputil.populateScene(2, spline_coeff_noise = 0.000)
scene = Sampling.ContinuousSceneWrapper(s)
usedFeatures = {
'singleton_integrated_acceleration': (True, pp.OptAgentType.PEDESTRIAN, 2.0),
# 'singleton_integrated_velocity': (True, pp.OptAgentType.PEDESTRIAN, 1.0),
'singleton_integrated_rotation_rate': (True, pp.OptAgentType.PEDESTRIAN, 1.0),
'pairwise_integrated_distance': (True, pp.OptAgentType.PEDESTRIAN, 10.0),
}
features = pp.FeatureContainerModifiable()
for fname,info in usedFeatures.iteritems():
features.push_back(fname, info[1], info[2])
negLogDensity = opt.OptimizationProblem()
for id,oa in scene.base.optAgents.iteritems():
oa.trajectory.addDesignVariables(negLogDensity)
for f in features.getContainer():
f.addErrorTerms(scene.base, negLogDensity)
# Bring the system to it's maximum likelihood state as an alternative to burn in
# nRpropIterations = 1000
# options = opt.OptimizerRpropOptions()
# options.convergenceGradientNorm
# options.verbose=False
# options.initialDelta=0.5
# options.maxIterations=1
# options.nThreads=2
