Session: CIE-05-01CIE Graduate Student Poster Symposium

Paper Number: 74864

Start Time: August 18, 10:00 AM

74864 - A Grasp-Planning Framework for Sheet Metal Multi-Type Grippers Using an Evolutionary Approach 

The objective of this research is to develop a framework for automating the grasp synthesis of multi-type grippers that are used in the automotive industry to position, manipulate, and immobilize sheet metal parts during manufacturing operations. Automation of steps in the design of grippers is essential to the timely introduction of new vehicles to the market since the production can not start prior to designing, testing, and building the grippers for the parts. By automating the grasp synthesis step in the design of a robotic gripper, this research aims to alleviate this problem by cutting a significant part of the design of such grippers. A combination of Siemens NX and Microsoft Excel is used to generate the option grasp space and search for optimal grasps using a variation of the genetic algorithm. The resulting end-usable tool will be used in human-subject studies to validate the benefits of the proposed approach.

The main motivation of this work is to reduce the design time of grippers by giving the designer tools to accelerate the process of grasp synthesis. The impact, however, is bigger than cutting the time to produce grippers. Most importantly, it hastens the production of the main workpieces, as the grippers are necessary prior to production. The secondary motivation of this research is to develop a tool to aid the designer in systematically find good solutions. This is accomplished by incorporating the expert knowledge of designers into the algorithm in the form of fitness functions. As the search space for these grasp points is significantly large and involves multiple objective functions, a variation of the genetic algorithm is well suited for this purpose.

Presenting Author: Jicmat Ali Florida Institute of Technology

Authors:

Jicmat Ali Florida Institute of Technology