Robust Localization in 3D Prior Maps for Autonomous Driving

Abstract

In order to navigate autonomously, many self-driving vehicles require precise localization within an a priori known map that is annotated with exact lane locations, traffic signs, and additional metadata that govern the rules of the road. This approach transforms the extremely difficult and unpredictable task of online perception into a more structured localization problem--where exact localization in these maps provides the autonomous agent a wealth of knowledge for safe navigation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 2016
Accession Number
AD1100454

Entities

People

  • Ryan Wolcott

Organizations

  • University of Michigan

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Autonomous Navigation
  • Autonomous Vehicles
  • Bayesian Networks
  • Computational Science
  • Computer Programs
  • Computer Science
  • Computer Vision
  • Computers
  • Detectors
  • Global Positioning Systems
  • Graphics Processing Unit
  • Image Processing
  • Inertial Navigation
  • Inertial Navigation Systems
  • Information Science
  • Kalman Filters
  • Machine Learning
  • Mobile Phones
  • Navigation
  • Neural Networks
  • Probabilistic Models
  • Random Variables
  • Reliability
  • Simultaneous Localization And Mapping
  • Three Dimensional
  • Unmanned Vehicles

Readers

  • Calculus or Mathematical Analysis
  • Computer Vision.
  • Distributed Systems and Data Platform Development