Surface reconstruction from cross-sectional contours has become increasingly important in medical image applications. In this paper, a method of reconstructing the surface of an object based on the descriptions of cro...
详细信息
To improve the performance of autonomous vehicles operating in a factory environment, it is important to develop an intelligent planning system to avoic. vehicle collisions as well as to design a good path network whi...
详细信息
The objective of this paper is to present a 3D object recognition system with emphasis on an optimum placement strategy for a mobile 3D range sensor. The theoretical aspects leading to the development of the 3D sensor...
详细信息
A tutorial introduction to the subject of multisensor integration and fusion is presented. The role of multisensor integration and fusion in the operation of intelligentsystems is defined in terms of the unique type ...
详细信息
A tutorial introduction to the subject of multisensor integration and fusion is presented. The role of multisensor integration and fusion in the operation of intelligentsystems is defined in terms of the unique type of information multiple sensors can provide. Multisensor integration is discussed in terms of basic integration functions and multisensor fusion in terms of the different levels at which fusion can take place. Numerical examples are given to illustrate a variety of different fusion methods. Speculations concerning possible research future directions and a guide to survey and review papers in the area of multisensor integration and fusion are presented.< >
Presents a 3D object recognition system with emphasis on an optimum placement strategy for a mobile 3D range sensor. The theoretical aspects leading to the development of the 3D sensor placement paradigm are presented...
详细信息
Presents a 3D object recognition system with emphasis on an optimum placement strategy for a mobile 3D range sensor. The theoretical aspects leading to the development of the 3D sensor placement paradigm are presented and described. The authors use a triangulation type laser of range finder in which a CCD based imaging device is utilized to view a plane of laser light bounced from a sweeping mirror. The sensor characteristics are described and modeled. A set of criteria for use in constraining the possible sensor site location for future scans is presented. These constraint conditions are essential to drive the actual sensor placement algorithm for 3D object recognition.< >
The objective of this study is to develop a method for mobile robot motion planning in the presence of moving obstacles. The concept of traversability vectors is used to analyze the spatial relationship between the ro...
详细信息
The objective of this study is to develop a method for mobile robot motion planning in the presence of moving obstacles. The concept of traversability vectors is used to analyze the spatial relationship between the robot and moving obstacles. Given a predefined path, the occupancy of the path by moving obstacles can be detected and registered on the constraint map. Obstacles on this map represent time constraints on the robot motion along the path. A search algorithm is then developed to coordinate the robot motion. Simulation results for this approach are discussed.< >
An intelligent robotic system for multi-sensor based tracking and interception of moving objects which travel at unknown velocities is presented. The capability for multi-sensor assisted object tracking has been achie...
详细信息
ISBN:
(纸本)9780819400383
An intelligent robotic system for multi-sensor based tracking and interception of moving objects which travel at unknown velocities is presented. The capability for multi-sensor assisted object tracking has been achieved through the development of techniques to track in multiple dimensions for both the static and dynamic cases. These methods are realized via the fusion of the best attributes of visual and acoustic sensing into an effective configuration that is ideal for real time tracking purposes. The kinematic information for a moving object is extracted via end effector mounted vision and ultrasonic sensors. A hybrid position/force servo-controlled gripper developed at NCSU has been used for the system implementation. One parallel actuation gripper finger houses a fiber optics based Eye-in-Hand vision sensor, while the other accommodates an ultrasonic range sensor. The primary intent of this work is to develop approaches for performing the tasks of: generalized visual/ultrasonic tracking of known rectangular entities;3-D tracking of arbitrary pseudo-planar objects that can change orientation about the optical axis;and a real time paradigm for the tracking of motion in 3-D with variable orientation about the optical axis. This discussion includes both a description of the underlying principles and the initial experimental results.
The problem of automatically generating the possible 3-D sensor locations for observing a scene is defined, and an approach to its solution is presented. The approach taken assumes that the sensor characteristics are ...
详细信息
The problem of automatically generating the possible 3-D sensor locations for observing a scene is defined, and an approach to its solution is presented. The approach taken assumes that the sensor characteristics are well understood and that objects expected in the scene are known and modeled. Then, given a set of constraints, a set of actions is specified directing a robot arm to position itself in such a manner that an attached 3-D sensor located in the robot gripper yields the maximum information content with minimum effort with respect to the constraints. Techniques that yield solutions for placement of a triangulation-type 3-D laser range finder are presented.< >
A structure for sensory information organization and robot task planning is introduced, and HMP, a hierarchical multiprocessor computer architecture, is developed to support the real-time execution of the defined info...
详细信息
A structure for sensory information organization and robot task planning is introduced, and HMP, a hierarchical multiprocessor computer architecture, is developed to support the real-time execution of the defined information structure. Queuing network analysis indicates that this hierarchical multiprocessor computer architecture, at least for the sets of loads defined, performs better than currently proposed systems based on single buses. All classes of data, except for large video data that have longer interarrival times, are transferred within 10 milliseconds, and most data are transferred at rates that are very close to their theoretical maximum speed. The gates, used for partitioning the buses, have also been successful; data transfers among processors inside the segment isolated by the gate have been speeded up while the transfer between clusters has either stayed the same or has been reduced slightly, compared to a system without gates.< >
暂无评论