skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: 3-D world modeling for an autonomous robot

Abstract

This paper presents a methodology for a concise representation of the 3-D world model for a mobile robot, using range data. The process starts with the segmentation of the scene into ''objects'' that are given a unique label, based on principles of range continuity. Then the external surface of each object is partitioned into homogeneous surface patches. Contours of surface patches in 3-D space are identified by estimating the normal and curvature associated with each pixel. The resulting surface patches are then classified as planar, convex or concave. Since the world model uses a volumetric representation for the 3-D environment, planar surfaces are represented by thin volumetric polyhedra. Spherical and cylindrical surfaces are extracted and represented by appropriate volumetric primitives. All other surfaces are represented using the boolean union of spherical volumes (as described in a separate paper by the same authors). The result is a general, concise representation of the external 3-D world, which allows for efficient and robust 3-D object recognition. 20 refs., 14 figs.

Authors:
; ;
Publication Date:
Research Org.:
Oak Ridge National Lab., TN (USA)
OSTI Identifier:
6094443
Report Number(s):
CONF-871163-1
ON: DE87013878
DOE Contract Number:
AC05-84OR21400
Resource Type:
Conference
Resource Relation:
Conference: SPIE Cambridge symposium on intelligent robots and computer vision, Cambridge, MA, USA, 1 Nov 1987; Other Information: Portions of this document are illegible in microfiche products
Country of Publication:
United States
Language:
English
Subject:
42 ENGINEERING; ROBOTS; PATTERN RECOGNITION; CYLINDERS; NAVIGATION; SPHERES; 420200* - Engineering- Facilities, Equipment, & Techniques

Citation Formats

Goldstein, M., Pin, F.G., and Weisbin, C.R. 3-D world modeling for an autonomous robot. United States: N. p., 1987. Web.
Goldstein, M., Pin, F.G., & Weisbin, C.R. 3-D world modeling for an autonomous robot. United States.
Goldstein, M., Pin, F.G., and Weisbin, C.R. Sat . "3-D world modeling for an autonomous robot". United States. doi:.
@article{osti_6094443,
title = {3-D world modeling for an autonomous robot},
author = {Goldstein, M. and Pin, F.G. and Weisbin, C.R.},
abstractNote = {This paper presents a methodology for a concise representation of the 3-D world model for a mobile robot, using range data. The process starts with the segmentation of the scene into ''objects'' that are given a unique label, based on principles of range continuity. Then the external surface of each object is partitioned into homogeneous surface patches. Contours of surface patches in 3-D space are identified by estimating the normal and curvature associated with each pixel. The resulting surface patches are then classified as planar, convex or concave. Since the world model uses a volumetric representation for the 3-D environment, planar surfaces are represented by thin volumetric polyhedra. Spherical and cylindrical surfaces are extracted and represented by appropriate volumetric primitives. All other surfaces are represented using the boolean union of spherical volumes (as described in a separate paper by the same authors). The result is a general, concise representation of the external 3-D world, which allows for efficient and robust 3-D object recognition. 20 refs., 14 figs.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sat Aug 01 00:00:00 EDT 1987},
month = {Sat Aug 01 00:00:00 EDT 1987}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • In applications of robotics to surveillance and mapping at nuclear facilities, the scene to be described is fundamentally three-dimensional. Usually, only partial information concerning the 3-D environment is known a-priori. Using an autonomous robot, this information may be updated using range data to provide an accurate model of the environment. Range data quantify the distances from the sensor focal plane to the object surface. In other words, the 3-D coordinates of discrete points on the object surface are known. The approach proposed herein for 3-D world modeling is based on the Combinatorial Geometry (C.G.) Method which is widely used inmore » Monte Carlo particle transport calculations. First, each measured point on the object surface is surrounded by a small solid sphere with a radius determined by the range to that point. Then, the 3-D shapes of the visible surfaces are obtained by taking the (Boolean) union of all the spheres. The result is a concise and unambiguous representation of the object's boundary surfaces. The distances from discrete points on the robot's boundary surface to various objects are calculated effectively using the C.G. type of representation. This feature is particularly useful for navigation purposes. The efficiency of the proposed approach is illustrated by a simulation of a spherical robot navigating in a 3-D room with several static obstacles.« less
  • This paper describes a 3-D world modeling technique using range data. Range data quantify the distances from the sensor focal plane to the object surface, i.e., the 3-D coordinates of discrete points on the object surface are known. The approach proposed herein for 3-D world modeling is based on the Combinatorial Geometry (CG) Method which is widely used in Monte Carlo particle transport calculations. First, each measured point on the object surface is surrounded by a small sphere with a radius determined by the range to that point. Then, the 3-D shapes of the visible surfaces are obtained by takingmore » the (Boolean) union of all the spheres. The result is an unambiguous representation of the object's boundary surfaces. The ''pre-learned'' partial knowledge of the environment can be also represented using the CG Method with a relatively small amount of data. Using the CG type of representation, distances in desired directions to boundary surfaces of various objects are efficiently calculated. This feature is particularly useful for continuously verifying the world model against the data provided by a range finder, and for integrating range data from successive locations of the robot during motion. The efficiency of the proposed approach is illustrated by simulations of a spherical robot in a 3-D room in the presence of moving obstacles and inadequate prelearned partial knowledge of the environment.« less
  • A 2-D and 3-D path planning algorithm for robot navigation and manipulation is developed in this paper. This method is of particular interest for robotic systems which require both 2-D navigation to reach the work site and 3-D path planning for on-site manipulation and inspection. This study extends the approach of 2-D path planning to 3-D with minimum effort. The quadtree and octree structures are used for 2-D and 3-D workspace representation, respectively. Quadtrees and octrees are generated from brightness image of the workspace obtained using a camera mounted on a robot. Path generation is based on the A* algorithm.more » The spatial length and the clearance space available for the robot are used as constraints in the path generation. The results of this approach are illustrated through an experimental system setup on a robotic workstation. 12 refs., 11 figs.« less
  • This paper reports on the status and future directions in the research, development and experimental validation of intelligent control techniques for autonomous mobile robots using the HERMIES-III robot at the Center for Engineering Systems Advanced research (CESAR) at Oak Ridge National Laboratory (ORNL). HERMIES-III is the fourth robot in a series of increasingly more sophisticated and capable experimental test beds developed at CESAR. HERMIES-III is comprised of a battery powered, onmi-directional wheeled platform with a seven degree-of-freedom manipulator arm, video cameras, sonar range sensors, laser imaging scanner and a dual computer system containing up to 128 NCUBE nodes in hypercubemore » configuration. All electronics, sensors, computers, and communication equipment required for autonomous operation of HERMIES-III are located on board along with sufficient battery power for three to four hours of operation. The paper first provides a more detailed description of the HERMIES-III characteristics, focussing on the new areas of research and demonstration now possible at CESAR with this new test-bed. The initial experimental program is then described with emphasis placed on autonomous performance of human-scale tasks (e.g., valve manipulation, use of tools), integration of a dexterous manipulator and platform motion in geometrically complex environments, and effective use of multiple cooperating robots (HERMIES-IIB and HERMIES- III). The paper concludes with a discussion of the integration problems and safety considerations necessarily arising from the set-up of an experimental program involving human-scale, multi-autonomous mobile robots performance. 10 refs., 3 figs.« less
  • A sensory-interactive robot requires real-time responses to its queries about the world. These responses must contain three-dimensional information about the objects to be manipulated in the world. The domain, however, allows the use of special camera and lighting configurations, models of the objects to be sensed, and knowledge of the geometry of the workspace. The paper presents the design of a hierarchical, multi-processor, sensory system that is tailored to the robot vision domain. The system interacts with a hierarchical control system that drives the robot in accomplishing its task. Together, the systems allow real-time, sensory-interactive performance, taking advantage of themore » constraints allowed by the domain. 3 references.« less