Vision-based High Speed Autonomous Navigation of UAVs

Full Day Workshop at IROS 2016

October 14, Daejeon Convention Center Room 111, Daejeon, South Korea

Updates

  • 12/05/2016 The workshop was a success with over 200 people attending, slides have started to be uploaded for each talk.
  • 12/04/2016 The final digest is now available.
  • 09/22/2016 A tentative program is now available and the final digest is available too.
  • 09/01/2016 The final decisions have been sent, the final program will be posted soon on the website.
  • 08/26/2016 The submitted papers are still under reviews. The final results will be available by August 31.
  • 08/17/2016 Last minutes submission will be possible till Friday 19 August!
  • 08/15/2016 Last few days to submit your works! We will have a high profile set of speakers and 5 companies attending the workshop!
  • 07/09/2016 Three companies will be part of the workshop! More updates will follow soon!
  • 07/08/2016 A special issue of Journal of Field Robotics has been organized! All the workshop contributors are invited to submit their works!
  • 05/15/2016 The website is available

Overview

The workshop will feature peer-reviewed paper presentations and live demos.

Motivation

Autonomous micro helicopters are starting to play a major role in tasks like search and rescue, environment monitoring, security surveillance, transportation and inspection. However, for such operations, two main challenges arise. The use GPS based navigation is not sufficient. Fully autonomous operation in cities or other dense environments requires micro helicopters to fly at low altitudes, where GPS signals are often shadowed or indoors and generally. In addition, the previous listed tasks are executed at low speed, compromising the execution of critical missions, which have to be typically accomplished in a limited amount of time. Thus, a number of perception and control challenges have still to be solved.

Goal

This workshop will focus on the systems' challenges for small-scale and high speed navigation of aerial vehicles, where the size, weight and payload constraints only allow light-weight sensors like cameras, and the operating conditions of high speeds (20 m/s) require perception, state estimation, environment reconstruction, obstacle avoidance and planning algorithms over longer ranges and shorter time scales. This workshop will focus not only on the scientific foundations, but also the algorithmic and software design challenges, which arise in the settings of small-scale, high speed navigation in three-dimensional environments. The workshop will feature, in addition to contributed and invited talks, real-time demos provided both from academia and industry actively working in this field.

Topics of Interest

Topics of interest to this workshop include, but are not necessarily limited to:
  • High-speed visual control and state estimation of aerial vehicles
  • Long term and range perception for UAVs without GPS
  • Sensor fusion for autonomous navigation in unstructured environment
  • System software and hardware architectures
  • Mapping and Obstacle avoidance
  • Perception in challenging and dynamic environments
  • Modeling and benchmarking of performances for three-dimensional navigation
  • Dynamic visual servo control of aerial vehicles
  • Cooperative estimation and control with multiple aerial vehicles
  • Resource constrained navigation
  • Field robotics
  • Search and rescue robotics

We encourage the submission of papers describing work in progress, preliminary results, novel concepts, and industry experiences. Contributions are expected from researchers working in different fields related to autonomous aerial vehicles.

Call for papers

All submitted papers will be reviewed by at least two international experts (see Program Committee Member list below) on the basis of technical quality, relevance, significance, and clarity. We accept extended abstracts (2-4 pages), experiences' reports (2-4 pages), or full research papers (up to 6 pages). We also encourage submission of live demos and working systems (up to 2 pages). All accepted papers will appear on the workshop website. We are currently exploring the possibility of a journal special issue for the best contributions at the workshop.

Important Dates

  • June 8: Call for submission opens
  • July 25 August 15: Deadline of full-length papers
  • August 25 August 31: Notification of acceptance
  • October 14: Workshop at IROS 2016 Daejeon Convention Center, Daejeon, South Korea

Program

The program includes invited talks, contributed papers and real-time demos. The final schedule might slightly change.

    Session 1
    Session 2
    • 10:30 - 10:40 Talk 7 - Lakmal Seneviratne, Khalifa University, “MBZIRC challenges related to autonomous navigation of UAVs: A status update”
    • 10:40 - 10:50 Talk 8 - David Shim, KAIST, “Looking back at the Indoor Drone Competition in IROS 2016”
    • 10:50 - 11:10 Talk 9 - David Shim, KAIST, “Vision-enabled drones: collision avoidance and aerial manipulations”, slides
    • 11:10 - 11:30 Talk 10 - Shaojie Shen, HKUST, “Autonomous Aerial Navigation using Monocular Visual-Inertial Fusion”
    • 11:30 - 11:50 Talk 11 - Giuseppe Loianno, University of Pennsylvania, “Vision-based Fast Localization and Environment Interaction with MAVs”, slides
    • 11:50 - 12:10 Talk 12 - Davide Scaramuzza, University of Zurich, Davide Scaramuzza, University of Zurich, “Agile Flight of Vision-controlled Micro Flying Robots”,slides
    • 12:10 - 12:45 Demos Session
    • 12:45 - 14:00 Lunch Break
    Session 3
    • 14:00 - 14:20 Talk 13 - Max Ruffo, Terabee, “Simplifying the world of high-speed 2D & 3D sensing for robotics and drones”, slides
    • 14:20 - 14:40 Talk 14 - Zhenfei Yang, DJI, “DJI Phantom 4 and Vision-based Technologies”
    • 14:40 - 15:00 Talk 15 - Debadeepta Dey, Microsoft, “Vision, Learning and Control for UAV Flight in Dense Clutter”, slides
    • 15:00 - 15:20 Talk 16 - Andrew Browning, SSCI, “R-ADVANCE: Rapid Adaptive PreDiction for Vision-based Autonomous Navigation and Evasion”
    • 15:20 - 15:30 Demos Session
    • 15:30 - 16:00 Coffee Break and Demos Session
    Session 4
    • 16:00 - 16:20 Talk 17 - Kartik Mohta and Vijay Kumar, University of Pennsylvania, "FLA DARPA Team Falcon: A status update"
    • 16:20 - 16:40 Talk 18 - Michael Burri and Roland Siegwart, ETH Zurich, “Robust State Estimation and Replanning for Fast UAV Navigation”, slides
    • 16:40 - 17:00 Talk 19 - Gregory Kahn and Sergey Levine, UC Berkeley, “Learning Control Policies for Partially Observable Safety-Critical Systems applied to High-Speed Flight”, slides
    • 17:00 - 17:20 Talk 20 - Kumar Shaurya Shankar and Nathan Michael, CMU, “Mutual Information for Robust Visual Odometry”
    • 17:20 - 18:15 Panel Discussion and Closing Remarks

Organizers

Giuseppe Loianno
loiannog@seas.upenn.edu
University of Pennsylvania

Davide Scaramuzza
sdavide@ifi.uzh.ch
University of Zurich

Vijay Kumar
kumar@seas.upenn.edu
University of Pennsylvania

Program Committee

  • Dr. Shaojie Shen, HKUST
  • Dr. Gary McGrath, Qualcomm Research
  • Dr. Sebastian Scherer, CMU
  • Mr. Justin Thomas, University of Pennsylvania
  • Dr. Friedrich Fraundorfer, TU Graz
  • Dr. Juan Nieto, ETH Zurich
  • Mr. Michael Watterson, University of Pennsylvania
  • Dr. Nathan Michael, CMU
  • Dr. Zachary Taylor, ETH Zurich
  • Dr. Martin Saska, CTU