A Testbed for Autonomous Reflexive Grasping

Abstract

This work describes the development of a testbed which combines a subsumption architecture approach with neural network processing of tactile information in a reflexive behavior feasibility study. An overview of the tactile sensor, the neural network processor, and subsumption architecture is provided along with a plan for integrating these components into a single system. By incorporating local (reflexive) processing capabilities within a robot gripper, an additional layer of control is attained without an increased computing burden being placed on the system controller.... Neural network processor, Subsumption architecture.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1993
Accession Number
ADA264557

Entities

People

  • David A. Kemme
  • John R. Mcdonnell

Organizations

  • Naval Command, Control and Ocean Surveillance Center

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Abstracts
  • Cerebral Cortex
  • Classification
  • Computers
  • Control
  • Control Systems
  • Data Acquisition
  • Elastomers
  • Engineering
  • Materials
  • Mechanical Engineering
  • Neural Networks
  • Ocean Surveillance
  • Pattern Recognition
  • Prosthetics
  • Surveillance
  • Universities

Fields of Study

  • Computer science

Readers

  • Database Systems and Applications
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks
  • Autonomy