Visual tracking is one of the key components for robots
to accomplish a given task in a dynamic environment,
especially when independently moving objects are included.
This paper proposes an extension of Adaptive
Visual Servoing (hereafter, AVS) for unknown moving
object tracking. The method utilizes binocular stereo
vision, but does not need the knowledge of camera parameters.
Only one assumption is that the system
need stationary references in the both images by which
the system can predict the motion of unknown moving
objects. The basic ideas how we extended the AVS
method such that it can track unknown moving objects
are given and formalized into a new AVS system. The
experimental results with proposed control architecture
are shown and a discussion is given.
項目描述:
EMC is software that implements real-time control of equipment such as machine tools, robots, and coordinate measuring machines. It runs in real-time under Linux with the NMT rtlinux patch, and in nonrealtime under Solaris, and WindowsNT.
EMC 是一個設備的實時控制軟件，可以控制機器工具，機器人，協調式的測量機器。它可以實時在帶有NMT補丁的Linux下運行，可以在Solaris, 和WindowsNT下可非實時運行。
Sensing and planning are at the core of robot motion. Traditionally,
mobile robots have been used for performing various tasks
with a general-purpose processor on-board. This book grew out of
our research enquiry into alternate architectures for sensor-based
robot motion. It describes our research starting early 2002 with the
objectives of obtaining a time, space and energy-efficient solution
for processing sensor data for various robotic tasks.
New algorithms and architectures have been developed for
exploration and other aspects of robot motion. The research has
also resulted in design and fabrication of an FPGA-based mobile
robot equipped with ultrasonic sensors. Numerous experiments
with the FPGA-based mobile robot have also been performed and
they confirm the efficacy of the alternate architecture.
