Optimal control on special Euclidean group via natural gradient algorithm
نویسندگان
چکیده
منابع مشابه
Natural gradient via optimal transport I
We study a natural Wasserstein gradient flow on manifolds of probability distributions with discrete sample spaces. We derive the Riemannian structure for the probability simplex from the dynamical formulation of the Wasserstein distance on a weighted graph. We pull back the geometric structure to the parameter space of any given probability model, which allows us to define a natural gradient f...
متن کاملRiemannian Means on Special Euclidean Group and Unipotent Matrices Group
Among the noncompact matrix Lie groups, the special Euclidean group and the unipotent matrix group play important roles in both theoretic and applied studies. The Riemannian means of a finite set of the given points on the two matrix groups are investigated, respectively. Based on the left invariant metric on the matrix Lie groups, the geodesic between any two points is gotten. And the sum of t...
متن کاملMinimum-Energy Pose Filtering on the Special Euclidean Group
Obtaining a robust estimate for the pose ( attitude and position) of a rigid body moving in three dimensional space using noisy vectorial measurements is a challenging problem. The underlying geometry of pose space, the special Euclidean group SE(3), makes this problem highly nonlinear and sensitive to measurement noise. According to a recent survey [9], most attitude estimation applications in...
متن کاملConjugate gradient algorithm for optimal control problems with parameters
The basic conjugate gradient method for unconstrained optimal control problems was proposed by Lasdon et al. in [1]. The penalty function approach to the solution of inequality constrained optimal control problems has been considered in [2] and the clipping-off technique that solves optimal control problems with magnitude constraint on the control inputs is described in [3, 4]. The proposed alg...
متن کاملTopmoumoute Online Natural Gradient Algorithm
Natural gradient is a gradient descent technique which uses the inverse of the covariance matrix of the gradient. Using the centrallimit theorem, we prove that it yields the direction that minimizes the probability of overfitting. However, its prohibitive computational cost makes it impractical for online training. Here, we present a new online version of the natural gradient which we coin TONG...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Science China Information Sciences
سال: 2016
ISSN: 1674-733X,1869-1919
DOI: 10.1007/s11432-015-0096-3