Patent•
Object Pickup Strategies for a Robotic Device
14 Mar 2014-
TL;DR: In this article, a robotic manipulator may identify characteristics of a physical object within a physical environment and then determine potential grasp points on the physical object corresponding to points at which a gripper attached to the robotic manipulators is operable to grip the object.
Abstract: Example embodiments may relate to methods and systems for selecting a grasp point on an object. In particular, a robotic manipulator may identify characteristics of a physical object within a physical environment. Based on the identified characteristics, the robotic manipulator may determine potential grasp points on the physical object corresponding to points at which a gripper attached to the robotic manipulator is operable to grip the physical object. Subsequently, the robotic manipulator may determine a motion path for the gripper to follow in order to move the physical object to a drop-off location for the physical object and then select a grasp point, from the potential grasp points, based on the determined motion path. After selecting the grasp point, the robotic manipulator may grip the physical object at the selected grasp point with the gripper and move the physical object through the determined motion path to the drop-off location.
Citations
More filters
Patent•
08 Feb 2017
TL;DR: In this paper, a grasp acquisition system for acquiring the object using the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination bins, and a motion planning system for determining a changing portion of a trajectory path of the end-effector from an object to a base location proximate to the input location, where the unchanging portion of the trajectory path is chosen to provide a path from the base location to the destination bin location that is consistent with paths taken by other objects.
Abstract: A processing system is disclosed for providing processing of homogenous and non-homogenous objects in both structured and cluttered environments. The processing system includes a programmable motion device including an end effector, a perception system for recognizing any of the identity, location, and orientation of an object presented in a plurality of objects at an input location, a grasp acquisition system for acquiring the object using the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination bins, and a motion planning system for determining a changing portion of a trajectory path of the end effector from the object to a base location proximate to the input location, and determining an unchanging portion of a trajectory path of the end effector from the base location to a destination bin location proximate to a destination bin, wherein the unchanging portion of the trajectory path is chosen to provide a path from the base location to the destination bin location that is consistent with paths taken by other objects.
55 citations
Patent•
10 Feb 2016TL;DR: In this article, a selective sorting method is described to identify and sort material objects of different natures, sizes and shapes having the form of a pile, and a device able to implement the method is also described.
Abstract: A selective sorting method is described to identify and sort material objects of different natures, sizes and shapes having the form of a pile. The method is characterized in that the attribution of the nature of the object to be sorted includes in capturing at least one two-dimensional image wherein the object appears, using at least one sensor for electromagnetic radiation and in diffusing at least one of the two-dimensional images on a display screen that can be observed by an operator, the operator attributing a nature to the object viewed. A device able to implement the method is also described.
25 citations
Patent•
23 Apr 2015
TL;DR: In this article, a method for automatically gripping, via a polyarticulated system secured to a viewing system, is described, which involves at least the steps of capturing an image of the receiving area via the viewing system and processing the information resulting from the 3D image and identifying all the specific areas that the objects to be grabbed can include, and which are compatible with the one or more gripping members.
Abstract: The invention relates to a method for automatically gripping, via a polyarticulated system (3) secured to a viewing system (9), an object (2) located in an area (4) capable of receiving at least one object (2), said polyarticulated system (3) comprising at least one gripping member (5) capable of grabbing an object (2) by a specific area of said object (2) According to the invention, the method comprises at least the steps of: capturing an image of the receiving area (4) via the viewing system (9); processing the information resulting from the 3D image and identifying all the specific areas that the objects (2) to be grabbed can include, and which are compatible with the one or more gripping members (5); locating the position and direction of the one or more compatible specific areas identified; selecting one of the located compatible specific areas and automatically defining, for the corresponding gripping member (5), a path for taking the corresponding object (2) by the selected compatible specific area; grabbing the corresponding object (2) according to the defined path
22 citations
Patent•
01 Feb 2016
TL;DR: In this paper, a robotic system for maintaining product inventory and dispensing products upon request from a customer or other user is presented, where product items are stored in an inventory storage unit (ISU), one item per bin.
Abstract: The present application is directed to a robotic system for maintaining product inventory and dispensing products upon request from a customer or other user. Product items are stored in an inventory storage unit (ISU), one item per bin. Controller logic allows items to be stored in, and retrieved from, arbitrarily-assigned storage locations. The bins hang on rails within drawers. Upon a request from a consumer (or other user) in a fulfillment operation, the robot retrieves a bin holding the first item from the ISU. Upon a request from an operator (or other user) in a replenishment operation, the robot transfers an empty bin to an operator station (such as a replenishing unit). The controller logic allows the fulfillment operations to be prioritized over the replenishment operations, in addition to the implementation of other prioritizations.
20 citations
Patent•
24 Jun 2015TL;DR: In this paper, a non-rigid transformation for articulated bodies is discussed, in which the target positions for matching a kinematic model of an articulated body are selected and a virtual end-effector for the model is generated.
Abstract: Techniques related to non-rigid transformations for articulated bodies are discussed. Such techniques may include repeatedly selecting target positions for matching a kinematic model of an articulated body, generating virtual end-effectors for the kinematic model and corresponding to the target positions, generating an inverse kinematics problem including a Jacobian matrix, and determining a change in kinematic model parameters based on the inverse kinematics problem until a convergence is attained.
17 citations
References
More filters
01 Aug 1987
TL;DR: In this paper, a divide-and-conquer approach is used to generate inter-slice connectivity, and then a case table is created to define triangle topology using linear interpolation.
Abstract: We present a new algorithm, called marching cubes, that creates triangle models of constant density surfaces from 3D medical data. Using a divide-and-conquer approach to generate inter-slice connectivity, we create a case table that defines triangle topology. The algorithm processes the 3D medical data in scan-line order and calculates triangle vertices using linear interpolation. We find the gradient of the original data, normalize it, and use it as a basis for shading the models. The detail in images produced from the generated surface models is the result of maintaining the inter-slice connectivity, surface data, and gradient information present in the original 3D data. Results from computed tomography (CT), magnetic resonance (MR), and single-photon emission computed tomography (SPECT) illustrate the quality and functionality of marching cubes. We also discuss improvements that decrease processing time and add solid modeling capabilities.
13,231 citations
Book•
01 Jan 1986
TL;DR: This chapter discusses Jacobians: Velocities and Static Forces, Robot Programming Languages and Systems, and Manipulator Dynamics, which focuses on the role of Jacobians in the control of Manipulators.
Abstract: 1. Introduction. 2. Spatial Descriptions and Transformations. 3. Manipulator Kinematics. 4. Inverse Manipulator Kinematics. 5. Jacobians: Velocities and Static Forces. 6. Manipulator Dynamics. 7. Trajectory Generation. 8. Manipulator Mechanism Design. 9. Linear Control of Manipulators. 10. Nonlinear Control of Manipulators. 11. Force Control of Manipulators. 12. Robot Programming Languages and Systems. 13. Off-Line Programming Systems.
5,992 citations
26 Oct 2011
TL;DR: A system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware, which fuse all of the depth data streamed from a Kinect sensor into a single global implicit surface model of the observed scene in real- time.
Abstract: We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware. We fuse all of the depth data streamed from a Kinect sensor into a single global implicit surface model of the observed scene in real-time. The current sensor pose is simultaneously obtained by tracking the live depth frame relative to the global model using a coarse-to-fine iterative closest point (ICP) algorithm, which uses all of the observed depth data available. We demonstrate the advantages of tracking against the growing full surface model compared with frame-to-frame tracking, obtaining tracking and mapping results in constant time within room sized scenes with limited drift and high accuracy. We also show both qualitative and quantitative results relating to various aspects of our tracking and mapping system. Modelling of natural scenes, in real-time with only commodity sensor and GPU hardware, promises an exciting step forward in augmented reality (AR), in particular, it allows dense surfaces to be reconstructed in real-time, with a level of detail and robustness beyond any solution yet presented using passive computer vision.
4,184 citations
01 Aug 1996
TL;DR: This paper presents a volumetric method for integrating range images that is able to integrate a large number of range images yielding seamless, high-detail models of up to 2.6 million triangles.
Abstract: A number of techniques have been developed for reconstructing surfaces by integrating groups of aligned range images. A desirable set of properties for such algorithms includes: incremental updating, representation of directional uncertainty, the ability to fill gaps in the reconstruction, and robustness in the presence of outliers. Prior algorithms possess subsets of these properties. In this paper, we present a volumetric method for integrating range images that possesses all of these properties. Our volumetric representation consists of a cumulative weighted signed distance function. Working with one range image at a time, we first scan-convert it to a distance function, then combine this with the data already acquired using a simple additive scheme. To achieve space efficiency, we employ a run-length encoding of the volume. To achieve time efficiency, we resample the range image to align with the voxel grid and traverse the range and voxel scanlines synchronously. We generate the final manifold by extracting an isosurface from the volumetric grid. We show that under certain assumptions, this isosurface is optimal in the least squares sense. To fill gaps in the model, we tessellate over the boundaries between regions seen to be empty and regions never observed. Using this method, we are able to integrate a large number of range images (as many as 70) yielding seamless, high-detail models of up to 2.6 million triangles.
3,282 citations
24 Apr 2000
TL;DR: A simple and efficient randomized algorithm is presented for solving single-query path planning problems in high-dimensional configuration spaces by incrementally building two rapidly-exploring random trees rooted at the start and the goal configurations.
Abstract: A simple and efficient randomized algorithm is presented for solving single-query path planning problems in high-dimensional configuration spaces. The method works by incrementally building two rapidly-exploring random trees (RRTs) rooted at the start and the goal configurations. The trees each explore space around them and also advance towards each other through, the use of a simple greedy heuristic. Although originally designed to plan motions for a human arm (modeled as a 7-DOF kinematic chain) for the automatic graphic animation of collision-free grasping and manipulation tasks, the algorithm has been successfully applied to a variety of path planning problems. Computed examples include generating collision-free motions for rigid objects in 2D and 3D, and collision-free manipulation motions for a 6-DOF PUMA arm in a 3D workspace. Some basic theoretical analysis is also presented.
3,102 citations