I am currently doing my Master thesis project within Robot Perception Group: Deep Reinforcement Learning-based On-board Visual-inertial Autonomous landing of miniature UAVs.
Previously, I was working as a student assistant within the AirCap (Aerial outdoor motion capture) project. My duties included integrating sensors into the current distributed system, taking care of software and hardware repositories and assembling the drones. During this time, I also completed a 7-week Essay rotation - An Overview on Neuromorphic Event-Based Visual Perception for Autonomous Robots.
I have completed my 4-year Diploma in Electrical and Computer Engineering at the University of Belgrade, School of Electrical Engineering. Currently, I am studying M.Sc. in Neural Information Processing at the University of Tuebingen. My studies' curricular focus includes Machine Learning, Neural Data Analysis, Computational Vision and Rehabilitation Robotics.
IEEE Robotics and Automation Letters, Robotics and Automation Letters, 3(4):3193-3200, IEEE, October 2018, Also accepted and presented in the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (article)
Multi-camera tracking of humans and animals in outdoor environments is a relevant and challenging problem. Our approach to it involves a team of cooperating micro aerial vehicles (MAVs) with on-board cameras only. DNNs often fail at objects with small scale or far away from the camera, which are typical characteristics of a scenario with aerial robots. Thus, the core problem addressed in this paper is how to achieve on-board, online, continuous and accurate vision-based detections using DNNs for visual person tracking through MAVs. Our solution leverages cooperation among multiple MAVs and active selection of most informative regions of image. We demonstrate the efficiency of our approach through simulations with up to 16 robots and real robot experiments involving two aerial robots tracking a person, while maintaining an active perception-driven formation. ROS-based source code is provided for the benefit of the community.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems