Pushbroom Stereo for High-Speed Navigation in Cluttered Environments

Abstract

We present a novel stereo vision algorithm that is capable of obstacle detection on a mobile-CPU processor at 120 frames per second. Our system performs a subset of standard block-matching stereo processing, searching only for obstacles at a single depth. By using an onboard IMU and state-estimator we can recover the position of obstacles at all other depths, building and updating a full depth-map at framerate. Here, we describe both the algorithm and our implementation on a high-speed, small UAV, flying at over 20 MPH (9 m/s) close to obstacles. The system requires no external sensing or computation and is, to the best of our knowledge, the first high-framerate stereo detection system running onboard a small UAV.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2014
Accession Number
ADA608257

Entities

People

  • Andrew J. Barry
  • Russ Tedrake

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Sensors
  • Space

DTIC Thesaurus Topics

  • Aircrafts
  • Algorithms
  • Collision Avoidance
  • Computations
  • Computer Science
  • Computer Stereo Vision
  • Computer Vision
  • Control Systems
  • Detection
  • Environment
  • Estimators
  • Field Programmable Gate Arrays
  • Inertial Navigation Systems
  • Measurement
  • Navigation
  • Standards
  • Unmanned Aerial Vehicles

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Robotics and Automation.