Imitation of Manipulation Skills Using Multiple Geometries

• URL: http://arxiv.org/abs/2203.01171v1
• Date: Wed, 2 Mar 2022 15:19:33 GMT
• Title: Imitation of Manipulation Skills Using Multiple Geometries
• Authors: Boyang Ti, Yongsheng Gao, Jie Zhao and Sylvain Calinon
• Abstract summary: We propose a learning approach to extract the optimal representation from a dictionary of coordinate systems to represent an observed movement. We apply our approach to grasping and box opening tasks in simulation and on a 7-axis Franka Emika robot.
• Score: 20.21868546298435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Daily manipulation tasks are characterized by regular characteristics associated with the task structure, which can be described by multiple geometric primitives related to actions and object shapes. Such geometric descriptors can not be expressed only in Cartesian coordinate systems. In this paper, we propose a learning approach to extract the optimal representation from a dictionary of coordinate systems to represent an observed movement. This is achieved by using an extension of Gaussian distributions on Riemannian manifolds, which is used to analyse a set of user demonstrations statistically, by considering multiple geometries as candidate representations of the task. We formulate the reproduction problem as a general optimal control problem based on an iterative linear quadratic regulator (iLQR), where the Gaussian distribution in the extracted coordinate systems are used to define the cost function. We apply our approach to grasping and box opening tasks in simulation and on a 7-axis Franka Emika robot. The results show that the robot can exploit several geometries to execute the manipulation task and generalize it to new situations, by maintaining the invariant features of the skill in the coordinate system(s) of interest.

Related papers

• Symmetry Discovery for Different Data Types [52.2614860099811]
  Equivariant neural networks incorporate symmetries into their architecture, achieving higher generalization performance. We propose LieSD, a method for discovering symmetries via trained neural networks which approximate the input-output mappings of the tasks. We validate the performance of LieSD on tasks with symmetries such as the two-body problem, the moment of inertia matrix prediction, and top quark tagging.
  arXiv  Detail & Related papers  (2024-10-13T13:39:39Z)
• Polynomial Chaos Expansions on Principal Geodesic Grassmannian Submanifolds for Surrogate Modeling and Uncertainty Quantification [0.41709348827585524]
  We introduce a manifold learning-based surrogate modeling framework for uncertainty in high-dimensional systems. We employ Principal Geodesic Analysis on the Grassmann manifold of the response to identify a set of disjoint principal geodesic submanifolds. Polynomial chaos expansion is then used to construct a mapping between the random input parameters and the projection of the response.
  arXiv  Detail & Related papers  (2024-01-30T02:13:02Z)
• Variational Barycentric Coordinates [18.752506994498845]
  We propose a variational technique to optimize for generalized barycentric coordinates. We directly parameterize the continuous function that maps any coordinate in a polytope's interior to its barycentric coordinates using a neural field.
  arXiv  Detail & Related papers  (2023-10-05T19:45:06Z)
• Assembly Planning from Observations under Physical Constraints [65.83676649042623]
  The proposed algorithm uses a simple combination of physical stability constraints, convex optimization and Monte Carlo tree search to plan assemblies. It is efficient and, most importantly, robust to the errors in object detection and pose estimation unavoidable in any real robotic system.
  arXiv  Detail & Related papers  (2022-04-20T16:51:07Z)
• Group invariant machine learning by fundamental domain projections [0.5156484100374058]
  We approach the well-studied problem of supervised group invariant and equivariant machine learning from the point of view of geometric topology. We propose a novel approach using a pre-processing step, which involves projecting the input data into a geometric space. This new data can then be the input for an arbitrary machine learning model.
  arXiv  Detail & Related papers  (2022-02-04T14:45:57Z)
• Geometry-aware Bayesian Optimization in Robotics using Riemannian Mat\'ern Kernels [64.62221198500467]
  We show how to implement geometry-aware kernels for Bayesian optimization. This technique can be used for control parameter tuning, parametric policy adaptation, and structure design in robotics.
  arXiv  Detail & Related papers  (2021-11-02T09:47:22Z)
• Visual SLAM with Graph-Cut Optimized Multi-Plane Reconstruction [11.215334675788952]
  This paper presents a semantic planar SLAM system that improves pose estimation and mapping using cues from an instance planar segmentation network. While the mainstream approaches are using RGB-D sensors, employing a monocular camera with such a system still faces challenges such as robust data association and precise geometric model fitting.
  arXiv  Detail & Related papers  (2021-08-09T18:16:08Z)
• Manifold learning-based polynomial chaos expansions for high-dimensional surrogate models [0.0]
  We introduce a manifold learning-based method for uncertainty quantification (UQ) in describing systems. The proposed method is able to achieve highly accurate approximations which ultimately lead to the significant acceleration of UQ tasks.
  arXiv  Detail & Related papers  (2021-07-21T00:24:15Z)
• Primal-Dual Mesh Convolutional Neural Networks [62.165239866312334]
  We propose a primal-dual framework drawn from the graph-neural-network literature to triangle meshes. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them. We provide theoretical insights of our approach using tools from the mesh-simplification literature.
  arXiv  Detail & Related papers  (2020-10-23T14:49:02Z)
• Object-Centric Multi-View Aggregation [86.94544275235454]
  We present an approach for aggregating a sparse set of views of an object in order to compute a semi-implicit 3D representation in the form of a volumetric feature grid. Key to our approach is an object-centric canonical 3D coordinate system into which views can be lifted, without explicit camera pose estimation. We show that computing a symmetry-aware mapping from pixels to the canonical coordinate system allows us to better propagate information to unseen regions.
  arXiv  Detail & Related papers  (2020-07-20T17:38:31Z)
• Stochastic Flows and Geometric Optimization on the Orthogonal Group [52.50121190744979]
  We present a new class of geometrically-driven optimization algorithms on the orthogonal group $O(d)$. We show that our methods can be applied in various fields of machine learning including deep, convolutional and recurrent neural networks, reinforcement learning, flows and metric learning.
  arXiv  Detail & Related papers  (2020-03-30T15:37:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.