A Hybrid Approach for Fault Detection in Autonomous Physical Agents

Abstract

One of the challenges of fault detection in the domain of autonomous physical agents (or Robots) is the handling of unclassified data, meaning, most data sets are not recognized as normal or faulty. This fact makes it very challenging to use collected data as a training set such that learning algorithms would produce a successful fault detection model. Traditionally unsupervised algorithms try to address this challenge. In this paper we present a hybrid approach that combines unsupervised and supervised methods. An unsupervised approach is utilized for classifying a training set, and then by a standard supervised algorithm we build a fault detection model that is much more accurate than the original unsupervised approach. We show promising results on simulated and real world domains.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2014
Accession Number
ADA602188

Entities

People

  • Eliahu Khalastchi
  • Lior Rokach
  • Meir Kalech

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Autonomous Vehicles
  • Detection
  • Detectors
  • Information Systems
  • Learning
  • Multiagent Systems
  • Reliability
  • Robotics
  • Robots
  • Systems Engineering
  • Test Sets
  • Training
  • Unmanned Aerial Vehicles
  • Unmanned Vehicles
  • Vehicles

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Fault Tolerant Diagnosis of Black and White Balloon Isolation Tests Using ¥.

Technology Areas

  • AI & ML
  • Autonomy
  • Autonomy - Autonomous System Control