Motion Planning of a Mobile Robotic Manipulator for Grasping Tasks in Complex Environments
Date Issued
2009
Date
2009
Author(s)
Wang, Wei-Jen
Abstract
The main objective of this thesis is to develop an autonomous navigation systemor a mobile manipulator for grasping tasks, which can operate in a complexnvironment. A high-dimensional planning algorithm for a robot to grasp oranipulate an object is developed. First, we generate a set of feasible grasps for aiven object. We consider a grasp’s stability (force-closure) and local environmentlearance to form a scoring function to generate feasible grasps that are the goals inrasp planning.ext, in order solve the planning problems that have different dimensions in theonfiguration space and the goal space, we propose a BiRRT-GCS (Bi-directionalRT with Goal Configuration Search) algorithm, which can make the robot moveoward the object and use its arm to reach the goal without using inverse kinematics in known environment. Moreover, the algorithm is more than five times faster than theiSpace algorithm in complex scenes. We also propose a Multi-Goal BiRRT-GCSlanner to increase the probability of success of a grasping task. The simulationesults and the real world experiment show that our algorithms can efficiently find arajectory of the robot to accomplish grasping tasks.
Subjects
Grasp Planning
Grasp Stability
High-Dimensional Motion Planning
Mobile Manipulator
Robotics
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-98-R96522810-1.pdf
Size
23.53 KB
Format
Adobe PDF
Checksum
(MD5):a1ba64dbdd37c96716842fae25a2f686