Challenges in Vision-based Drones Navigation

Program

9:00	Welcome
	Session 1: Competition Challenges and New Research Directions Part 1
9:10	Talk 1 Tung Dang and Kostas Alexis, University of Nevada Reno, “Field-hardened Subterranean Robotic Autonomy”
9:40	Talk 2 Lakmal Seneviratne, Khalifa University, “MBZIRC 2020 Challenges Related to Vision-Based Drone autonomy”
10:00	3 Best papers presentations from contributed papers 10 minutes each
10:30	Pitch from other papers 2 minutes each
10:45-11:15	Coffee Break and paper poster presentation from other papers
	Session 2: New Research Directions Part 2
11:15	Talk 4 Shaojie Shen, HKUST, “Teach-Repeat-Replan: A Complete and Robust System for Autonomous Drone Racing”
11:45	Talk 5 Giuseppe Loianno, New York University, “Resilient Agile Aerial Navigation”
12:15	Talk 6 Davide Scaramuzza, University of Zurich, “Event Cameras”
12:45	VIO competition best result
13:00	Lunch
	Session 3: Industry Perspective
14:00	Talk 7 Tarek Taha, Krypto Labs, “Deployment of Vision-based Localization in Multi-UAV Exploratory Missions – DroneXChallenge 2020”
14:30	Talk 8 Ashish Kapoor, Microsoft, “Self-Supervised Representation Learning for Safe Drone Flights”
15:00	Talk 9 Max Ruffo, Terabee, “AI and industrial safety, a gap to fill”
15:30	Introduction to Autonomous Racing Drone Competition by Hyungpil Moon 5 minutes. 5 minutes, Pitch from 3 best teams
15:45-16:15	Coffee break and poster presentation by the drone racing teams
	Session 4: Industry Perspective and New Research Directions Part 3
16:15	Talk 10 Samuel Wang, DJI, “Building Aerial Solutions with DJI”
16:45	Talk 11 Anibal Ollero, University of Seville, “Present and future of perception systems for aerial robotic manipulators”
17:15	Talk 12 Ji Zhang, CMU, “A Lightweight Aerial Autonomy System with Limited Sensing”
17:45	Panel Discussion and Best Paper Award
18:00	Closing remarks

The complete workshop digest is available here.

List of accepted papers, in bold best paper candidates

Y. Lee, J. Kang and D. Lee, Seoul National University, “Tight fusion of GPS-VIO for Indoor-Outdoor Transitional Flight of UAV”
X. Wan, G. Zhao, P. Li and Y. Sun, Chinese Academy of Sciences, “Phase Correlation based Geo-referencing for Planetary UAV Optical Navigation”
David, W. Mostowski, M. Aramrattna, Y. Fan, M. Varshosaz, P. Karlsson, M. Roden, A. Bogga, J. Carlsen, E. Johansson and E. Andersson, Halmstad University, “Design and Development of a Hexacopter for the Search and Rescue of a Lost Drone”
R. Bonatti, W. Wang, C. Ho, A. Ahuja, M. Gschwindt, E. Camci, E. Kayacan, S. Choudhury and S. Scherer, CMU “Autonomous Aerial Filming In Unstructured Environments With Learned Artistic Decision-Making”
F. Chow, B. B. Kocer, J. Henawy and G. G. L. Seet, Nanyang Technological University, “Towards Underground Localization: Lidar Inertial Odometry Enabled Aerial Robot Navigation”
R. Muzaffar, A. Hardt-Stremayr, Samira Hayat, A. Vogell and E. Yanmaz, Alpen-Adria University, “Autonomous Drone Navigator for 3D Reconstruction of Forests”
M. Müller, M. Schuster, I. von Bargen, W. Stürzl, P. Lutz, M. Maier, S. Stoneman, T. Tomic, F. Steidle, A. Wedler and R. Triebel, DLR, “Challenges of Vision-Based Navigation for Flying Robots on Extraterrestrial Bodies”
J. Pan, C. Liu and S. Shen, HKUST, “A Complete and Robust Aerial Robot System for Automated Inspection”
V. Radhakrishnan and T. Taha, Algorythma, “Experimental Evaluation of State Estimation During Missions with Indoor and Outdoor Transitions”

News

The workshop will feature a 500 USD best paper award sponsored by Krypto Labs in Abu Dhabi, UAE and a 1000 USD VIO competition sponsored by Huawei. We are happy to announce that Krypto Labs, Huawei, and DJI will be the sponsors of the workshop.

This workshop is endorsed by the IEEE RAS TC on Aerial Robotics and Unmanned Aerial Vehicles and supported by the DCIST Distributed and Collaborative Intelligent Systems and Technology Collaborative Research Alliance (CRA).

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 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. On the other hand, multiple MAVs have been endowed with manipulation and transportation capabilities. Although the complexity of such systems increases with the number of agents, MAVs can perform tasks in a collaborative manner and exchange information between each other to make better decisions and optimize tasks.

Goal

This workshop will focus on the next research challenges in the area of vision-based navigation for single and multiple collaborative vision-based drones. In these areas, there are still several open research and scientific challenges related to the best and efficient environment representations for navigation and toward unified solutions for manipulation, transportation, locomotion, human-robot interaction, and heterogeneity in unstructured environments. How can drones autonomy change the human mobility? How can these machines interact with humans during a task predicting his future behavior and provide situational awareness relaxing communication constraints? How do we co-design perception and action loops for fast navigation of small-scale aerial platforms to obtain racing and super vehicles machines? What role should machine learning play for autonomy? What are and how do we solve the perception challenges in aerial swarms?

Topics of interest to this workshop include, but are not necessarily limited to: