Quadrotor Project

  • Summary
    • This project addresses the problem of autonomous quadrotor navigation within indoor spaces. In particular, we focus on the case where a visual map of the area, represented as a graph of linked images, is constructed offline (from visual and inertial data collected beforehand) and used to determine visual paths for the quadrotor to follow. Moreover, during the actual navigation, the quadrotor employs both the 3pt+1 and the 1pt+1 RANSAC (or 5pt and 2pt RANSAC when IMU information is not available) to efficiently determine its desired motion towards the next reference image, for both cases of sufficient and insufficient baseline (e.g., rotations in place). Lastly, we introduce an adaptive optical-flow algorithm that can accurately estimate the quadrotor's horizontal velocity under adverse conditions (e.g., when flying over dark, textureless floors) by progressively using information from more parts of the images. The speed and robustness of our algorithms are evaluated experimentally on a commercial quadrotor navigating in the presence of dynamic obstacles (i.e., people walking), along lengthy corridors, and through tight corners, as well as across building floors via poorly-lit staircases.
  • Videos

  • High-speed autonomous quadrotor navigation through two floors in Walter Library using Parrot's Bebop
  • Autonomous quadrotor navigation using gyro assited rotations on Walter Library basement
  • Autonomous quadrotor navigation using vison-only rotations on Walter Library basement
  • Autonomous quadrotor navigation using DJI F450 and Project Tango cell phone
  • Preliminary Tests:
  • Visual Servoing accuracy test in VICON (motion capture system) room using DJI F450
  • Waypoint navigation and controller test using DJI F330
  • Relevant Publications
  • C2. T. Do, L.C. Carrillo-Arce, Zhengqi Li, and S.I. Roumeliotis, "High-speed Autonomous Quadrotor Navigation through Image Paths," In Proc. International Conference on Robotics and Automation (ICRA), Stockholm, Sweden, May 16-21, 2016 [Submitted].
  • C1. T. Do, L.C. Carrillo-Arce, and S.I. Roumeliotis, "Autonomous Flights through Image-defined Paths," In Proc. International Symposium of Robotics Research (ISRR), Sestri Levante, Italy, Sep. 12-15, 2015 (pdf).