Vision-based Agile Autonomous Navigation of UAVs

Full Day Workshop at IROS 2017

September 28, Vancouver Convention Center Room 109-110, Vancouver, Canada


  • 12/13/2017 An initial set of slides is now available
  • 09/19/2017 The workshop will be in room 109-110
  • 09/16/2017 A tentative program is now available and the final digest is available too
  • 07/14/2017 The submission deadline has been updated to August 15
  • 06/09/2017 The paper submission is available and we have listed at the bottom an impressive set of experts in the program committee that will support the review process
  • 04/22/2017 The program committee has been announced and we will have an impressive set of invited speakers both from academia and industry
  • 04/18/2017 The website is available


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


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 indoor and outdoor environments requires micro helicopters to fly at low altitudes, where GPS signals are often shadowed or absent.. In addition, during the previous mentioned tasks, agile motions are still not possible, compromising the execution of critical missions. These should be typically accomplished in a fast and agile manner and within a limited amount of time. Thus, several perception and control challenges have still to be addressed and solved. Unmanned Aerial Vehicles (UAVs) should be able to fly autonomously with agility in extreme navigation conditions guaranteeing robust high rate state estimation for closed loop control.


This workshop will focus on the systems' challenges for small-scale agile autonomous navigation of aerial vehicles, where the size, weight and payload constraints only allow lightweight sensors like cameras. The operating conditions of agile navigation require that the aerial vehicles should exhibit during flight, despite their underactuation, smooth motions at high speeds concurrently tolerating large and sudden changes in accelerations and angular rotations (>800 deg/s), while avoiding collisions with obstacles. Perception, mechanics, state estimation, environment reconstruction, obstacle avoidance, planning algorithms and computation are required to support during navigation these operating conditions over long ranges and short times and 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, agile 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:
  • Agile autonomous navigation of UAVs
  • 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 14 August 15: Deadline of full-length papers
  • August 22: Notification of acceptance
  • September 28: Workshop at IROS 2017 Vancouver Convention Center, Vancouver, Canada


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

    Session 1
    • 08:40 - 08:50 Welcome & Introduction
    • 08:50 - 09:10 Talk 1 – J.C. Lede, DARPA, “Field Experimentation in the DARPA Fast Lightweight Autonomy Program”, slides
    • 09:10 - 09:30 Talk 2 – Vijay Kumar, University of Pennsylvania, "Challenges for fast Navigation", slides
    • 09:30 - 10:00 Talk 3 - Andrew Browning, SSCI, “Visual-acoustic-reactive autonomy for mission centric UAVs”, Hector Hescobar, SSCI, “R-ADVANCE: 20m/s autonomous flight through a door using monocular obstacle avoidance”, slides
    • 10:00 - 10:30 Coffee Break
    Session 2
    • 10:30 - 10:50 Talk 4 - Nicholas Roy, MIT, “Learning to Fly Aggressively”
    • 10:50 - 11:00 Talk 5 - Lakmal Seneviratne, Khalifa University, “MBZIRC Challenges Related to Vision-based Autonomous Navigation of UAVs”
    • 11:00 - 11:20 Talk 6 - Shaojie Shen, HKUST, “Minimalist Visual Perception for Consumer Drones”
    • 11:20 - 11:40 Talk 7 - Giuseppe Loianno, University of Pennsylvania, “Flying Robots: Agile Autonomous Navigation, Transportation and Physical Interaction”, slides
    • 11:30 - 11:50 Talk 8 - Davide Scaramuzza, University of Zurich, “Event Vision and Learning for Agile Flight”, slides
    • 11:50 - 12:10 Talk 9 - Sanjiv Singh, CMU, “Hierarchical Alternative Paths for High-Speed Aerial Collision Avoidance in Complex Environments”
    • 12:10 - 12:30 Talk 10 - Feresteh Sadeghi, University of Washington, “CAD2RL : Real Single-Image Flight without a Single Real Image”
    • 12:30 - 12:50 Talk 11 - David Shim, KAUST, “Deep-learning assisted Indoor Navigation for Agile Drones”, slides
    • 12:50 - 14:10 Lunch Break
    Session 3
    • 14:10 - 14:20 Talk 12 - Contributed paper 1, Eric Heiden, Karol Hausman, Gaurav S. Sukhatme, Ali-akbar Agha-mohammadi, “High-speed Safe Trajectory Planning in Confidence-rich Maps” Ali-akbar Agha-mohammadi, Eric Heiden, Karol Hausman, Gaurav S. Sukhatme, “Confidence-aware Occupancy Grids”
    • 14:20 - 14:30 Talk 13 - Contributed paper 2, Jianing Chen, Stephen J. Carey and Piotr Dudek, “Feature Extraction using a Portable Vision”
    • 14:30 - 14:50 Talk 14 - Ashish Kapoor, Microsoft, “Enabling Autonomous Flight with AirSim”
    • 14:50 - 15:05 Talk 15 - Max Ruffo, Terabee, “Challenging the point-cloud conundrum”, slides
    • 15:05 - 15:20 Talk 16 - Zhiyuan Li, DJI, “Sable, strong & smart flying robots, extensible development platform”
    • 15:20 - 15:35 Talk 17 - Matt Turpin, Qualcomm, “Developing with Snapdragon Flight”, slides
    • 15:35 - 16:00 Demos Session
    • 16:00 - 16:30 Coffee Break and Demos Session
    Session 4
    • 16:30 - 16:50 Talk 18 - Walterio Mayol-Cuevas, Piotr Dudek, Tom Richardson, Stephen Carey, Colin Greatwood, Jianing Chen, Laurie Bose, Universitiy of Manchester and University of Bristol, “Towards Integrated Perception and Control for UAVs with Pixel Processor Arrays”, slides
    • 16:50 - 17:10 Talk 19 - Sebastian Scherer, CMU, “Scene Understanding, Exploration Planning and Obstacle Avoidance for Autonomous Scouting with Micro Aerial Vehicles”
    • 17:10 - 17:30 Talk 20 - Zachary Taylor, Juan Nieto, and Roland Siegwart, ETH Zurich, “Overcoming the challenges facing lightweight UAVs in unstructured environments”
    • 17:30 - 17:40 Talk 21 - Martin Saska, CTU, “Aspects of vision-based navigation and agile control in tasks of MBZIRC competition”
    • 17:40 - 18:00 Panel Discussion and Closing Remarks


Giuseppe Loianno
University of Pennsylvania

Davide Scaramuzza
University of Zurich

Vijay Kumar
University of Pennsylvania

Program Committee

  • Dr. Shaojie Shen, HKUST
  • Dr. Gary McGrath, Qualcomm Research
  • Dr. Sebastian Scherer, CMU
  • Dr. Friedrich Fraundorfer, TU Graz
  • Dr. Debadeepta Dey, Microsoft
  • Dr. Juan Nieto, ETH Zurich
  • Dr. Nathan Michael, CMU
  • Dr. Martin Saska, CTU