We have posted the entire workshop event on youtube https://www.youtube.com/playlist?list=PLOZv2PvzIPCCFGBl-feqTVk8Dyp7fORQY
The event was extremely successful with over 190 daily participants.

Due to multiple requests, the workshop will be held on November 2 and November 3 from 10 am to 2 pm New York time EST.
We will use the zoom platform https://nyu.zoom.us/j/93410908538

Program Day 1 November 2

Time	Talk
10:00	Welcome, video
10:10	Talk 1 Anibal Ollero, University of Seville, Perception and control of bioinspired aerial robots, video slides
10:30	Talk 2 Sung Kim, NASA/JPL, Agile and Resilient Robotic Autonomy in Extreme Environments, video slides
10:50	Talk 3 Sertac Karaman, MIT, On Challenges and Opportunities in Agile Robotics: From Computing Hardware to Simulation and Testing, video slides
11:10	Panel Discussion 1, video
11:30	Winner FPV competition
11:50	Contributed Papers 1 to 3 below
12:20	Talk 4 Giuseppe Loianno, NYU, Agile Flight with Minimalistic Perception, video slides
12:40	Talk 5 Nikolai Smolyanskiy, NVIDIA, Towards Modular Deep Learning Based Navigation Stack for Autonomous Driving, video slides
13:00	Talk 6 Mac Schwager, Stanford University, Competing Safely with Humans: from Drone Racing to Autonomous Freeway Driving, video slides
13:20-13:40	Panel discussion 2, video
14:00	Conclusion

Program Day 2 November 3

Time	Talk
10:00	Welcome
10:10	Talk 7 Angela Schoellig and Melissa Greff, U Toronto, Using Data-driven Models to Achieve Reliable Outdoor Visual Navigation, video slides
10:30	Talk 8 Guido De Croon, TU Delft, Spiking neural networks for agile autonomous flight of tiny drones, video slides
10:50	Talk 9 Shaojie Shen, HKUST, Efficient Autonomous Exploration of Unknown Environments using Aerial Robots, video
11:10	Panel discussion 3, video
11:30	Contributed Papers 4 to 7
12:10	Talk 10  Aleksandra Faust, Google, Toward autonomous robots through evolution, reinforcement, and self-supervision, video slides
12:30	Talk 11 Davide Scaramuzza, University of Zurich, Learning to Fly, video slides
12:50	Talk 12 Ashish Kapoor, Microsoft, Adversarial Considerations in Learning and Control for Safe Autonomous Flight, video
13:10-13:30	Panel discussion 4, video
13:30-13:50	Winner of the best paper award, video

List of accepted papers

1. I. Bozcan and E. Kayacan, Aarhus University, “Contextual Anomaly Detection for Low Altitude Aerial Surveillance”, video
2. Y.-J. R. Chu, T. H. Wei, J.-B. Huang, Y.-H. Chen and I-C. Wu, National Chiao-Tung University, “Sim-To-Real Transfer for Autonomous Miniature Car Racing”, video
3. T.Weiss, V. Suresh Babu and M. Behl, University of Virginia, “DeepRacing AI: Agile Trajectory Synthesis for Autonomous Racing”, video
4. K. Esterle, L. Gressenbuch and A. Knoll, Fortiss GmbH Research Institute, “Modeling and Testing Multi-Agent Traffic Rules within Interactive Behavior Planning”, video
5. P. Hart and A. Knoll, Fortiss GmbH Research Institute, “Counterfactual Policy Evaluation for Decision-Making in Autonomous Driving”, video
6. G. Barros and E. Colombini, Institute of Computing Unicamp Campinas, “Using Soft Actor-Critic for Low-Level UAV Control”, video
7. A. Spitzer and N. Michael, CMU, “Rotational Error Metrics for Quadrotor Control”, video

Motivation

Remotely-piloted aerial and ground vehicles/cars navigating at high speed in complex racing courses have inspired many researchers to design autonomy algorithms with the goal to create the so called super-vehicles, i.e. autonomous vehicles with the ability to execute agile and racing maneuvers with superior performances compared to human controlled vehicles. Navigation solutions designed for super-vehicles can help to address autonomy problems for autonomous cars. Concurrently, a tremendous progress has been made in the area of autonomous cars and this can inspire solutions as well for racing drones and small ground vehicles. Fully autonomous operations in cities or dense indoor and outdoor environments require autonomous vehicles to navigate and react in a fast and agile manner, where GPS signals are often shadowed or absent.

Goal

This workshop will bring together heterogeneous communities working on aerial robots, mobile ground vehicles, and autonomous cars to discuss the next research challenges in the area of agile navigation of autonomous robots and vehicles to achieve super-human maneuvering and racing capabilities in dynamic and challenging environments. In these areas, there are still several open research and scientific questions related to the best and efficient environment representations for navigation and toward unified solutions for perception, control, and planning. How can autonomous vehicles 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? What is the role and the benefits provided by the new 5G mmWave communication technology in the perception-action loop of robots? How do we co-design perception and action loops for fast navigation of aerial and ground platforms to obtain racing and super vehicles machines in dynamic environments? What role should machine learning play for autonomy? How can the algorithms scale and be used on autonomous cars and vice-versa?

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

• Visionary ideas for autonomy of ground and aerial vehicles
• Learning for control
• Agile autonomous navigation, transportation and manipulation with ground and aerial vehicles
• Agile visual control and state estimation
• SLAM
• Sensor fusion
• Motion planning
• Obstacle avoidance
• Modeling and benchmarking of performances for three-dimensional navigation
• Cooperative estimation and control with multiple robots
• Search and rescue robotics

Organizers

Giuseppe Loianno New York University	Davide Scaramuzza University of Zurich	Sertac Karaman MIT

This workshop is endorsed by the IEEE RAS TC on Aerial Robotics and Unmanned Aerial Vehicles, IEEE Technical Committee on Computer and Robot Vision, and the IEEE Technical Committee on Algorithms for Planning and Control of Robot Motion and supported by the DCIST Distributed and Collaborative Intelligent Systems and Technology Collaborative Research Alliance (CRA).