Robot Training Through Incremental Learning

Abstract

The real world is too complex and variable to directly program an autonomous ground robot's control system to respond to the inputs from its environmental sensors such as LIDAR and video. The need for learning incrementally, discarding prior data, is important because of the vast amount of data that can be generated by these sensors. This is crucial because the system needs to generate and update its internal models in real-time. There should be little difference between the training and execution phases; the system should be continually learning, or engaged in "life-long learning". This paper explores research into incremental learning systems such as nearest neighbor, Bayesian classifiers, and fuzzy c-means clustering.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 18, 2011
Accession Number
ADA542296

Entities

People

  • Gary Witus
  • Robert E. Karlsen
  • Shawn Hunt

Organizations

  • United States Army Tank Automotive Research, Development and Engineering Center

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence Software
  • Classification
  • Clustering
  • Data Sets
  • Detectors
  • Information Science
  • Machine Learning
  • Probability
  • Statistics
  • Supervised Machine Learning
  • Test Sets
  • Training
  • Unmanned Ground Vehicles
  • Unmanned Systems
  • Vehicles

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • STEM Education
  • Systems Analysis and Design

Technology Areas

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