OpenUAV Project

From The OpenUAV Project
(Redirected from Main Page)
Jump to: navigation, search


NSF CPS-VO student UAV challenge 2018 summary video.

Announcing the 2019 CPS-VO UAV challenge: Imagine your friend’s quadrotor experienced a flyaway incident into a lightly wooded terrain. Sunset is approaching and a storm is expected later. Looking for this lost drone needs a solution that could be repurposed to solve many other problems, such as searching for a strategic location to deploy a mosquito trap.

The goal of this challenge is to use a quadrotor aircraft with downward facing camera, and possibly other sensors, to scan an area for a lost aircraft (light mock model), and recover it safely back to base. Teams will be provided with powerful simulation tools on the CPS-VO, as well as support with hardware decisions.

More information for this upcoming competition is available at competition site on the NSF CPS-VO.

UAV Testbed for the CPS and Robotics Community: We are developing a cloud-enabled testbed for UAV education and research. Supported by the NSF CPS Virtual Organization’s Active Resources initiative, the testbed includes standardized UAV hardware and an end-to-end simulation stack built upon open source technologies. The testbed facilitated a pilot student UAV challenge held at the TIMPA airfield in Arizona on October 3-4, 2016, where four student teams from Vanderbilt University, University of Arizona, UCLA, and UPenn demonstrated with varying degrees of autonomy, the deployment and retrieval of a mosquito trap. This task was motivated by Microsoft Research’s Project Premonition, which also funded the hardware for the participating teams. Watch short videos below that summarize the event.

NSF CPS-VO student UAV challenge 2016 summary video. Penn AiR (winning team) participation summary video.
OpenUAV simulation environment with six UAVs. Example of TensorFlow object detection (default object classes), and OpenCV general contours.


"Daytona Beach Students Dominate NSF's Autonomous Aerial Vehicles Competition" , The Embry-Riddle Newsroom, June 7, 2018.

"Engineering students in second place in international drone competition" , Halmstad University News, June 7, 2018.

What you may expect to learn

  • ROS - thorough understanding of sensing and control
  • MAVLink and MAVROS - comprehensive knowledge of UAV commanding standards.
  • Gazebo - learn how to modify UAV models
  • OpenAI Gym - familiarize yourself with state of the art in deep reinforcement learning.
  • Multi-UAV control - experiment with mission planning and autonomous control of multiple UAVs with full PX4 stack onboard, and avoid crashes and endurance limits of real UAVs! (till you are ready to fly outdoors).

Software Resources

Hardware Resources


  • Matt Schmittle, Anna Lukina, Lukas Vacek, Jnaneshwar Das, Christopher P. Buskirk, Stephen Rees, Janos Sztipanovits, Radu Grosu and Vijay Kumar, "OpenUAV: A UAV Testbed for the CPS and Robotics Community," 2018 International Conference on Cyber-Physical systems (ICCPS), accepted.
  • Lukas Vacek, Edward Atter, Pedro Rizo, Brian Nam, Ryan Kortvelesy, Delaney Kaufman, Jnaneshwar Das, Vijay Kumar, "sUAS for deployment and recovery of an environmental sensor probe," 2017 International Conference on Unmanned Aircraft Systems (ICUAS), Miami, FL, USA, 2017, pp. 1022-1029. (PDF)
  • Daniel Orol, Jnaneshwar Das, Lukas Vacek, Isabella Orr, Mathews Paret, Camillo. J. Taylor, Vijay Kumar, "An aerial phytobiopsy system: Design, evaluation, and lessons learned," 2017 International Conference on Unmanned Aircraft Systems (ICUAS), Miami, FL, USA, 2017, pp. 188-195. (PDF)


  • Ph.D. students
    • Kate Tolstaya
  • Masters students
    • Sandeep Dcunha
    • Arjun Kumar
    • Abhijeet Singh
  • High-school students
    • Bharath Nagarajan


back to top of page

Website maintained by Jnaneshwar Das, University of Pennsylvania, email: djnan [at]