Autonomous Object Tracking

July 2017

IEEE Robotics and Automation Letters
Justin Thomas, Jake Welde, Giuseppe Loianno, Kostas Daniilidis, and Vijay Kumar

In this work, we enable a small quadrotor to autonomously track a moving target and plan trajectories that allow the robot to converge on the target. Our approach respects the dynamic, sensor, and actuator constraints of the vehicle, in particular ensuring that the target does not leave the field of view of the camera, which is rigidly attached to the robot and therefore affected by the coupled dynamics of the system. One of the major contributions of this work is that all sensing and computation is done onboard the 250 g vehicle, with no outside assistance from motion capture systems or external processors.

We were featured in National Geographic’s Breakthrough in an episode called “Game of Drones”!


J. Thomas, J. Welde, G. Loianno, K. Daniilidis and V. Kumar, “Autonomous Flight for Detection, Localization, and Tracking of Moving Targets With a Small Quadrotor,” in IEEE Robotics and Automation Letters, vol. 2, no. 3, pp. 1762-1769, July 2017, doi: 10.1109/LRA.2017.2702198.


© 2017 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.