Ego-motion estimation is vital for drones when flying in GPS-denied environments. Vision-based methods struggle when flight speed increases and close-by objects lead to difficult visual conditions with considerable motion blur and large occlusions. To tackle this, vision is typically complemented by state estimation filters that combine a drone model with inertial measurements. However, these drone models are currently learned in a supervised manner with ground-truth data from external motion capture systems, limiting scalability to different environments and drones. In this work, we propose a self-supervised learning scheme to train a neural-network-based drone model using only onboard monocular video and flight controller data (IMU and motor feedback). We achieve this by first training a self-supervised relative pose estimation model, which then serves as a teacher for the drone model. To allow this to work at high speed close to obstacles, we propose an improved occlusion handling method for training self-supervised pose estimation models. Due to this method, the root mean squared error of resulting odometry estimates is reduced by an average of 15%. Moreover, the student neural drone model can be successfully obtained from the onboard data. It even becomes more accurate at higher speeds compared to its teacher, the self-supervised vision-based model. We demonstrate the value of the neural drone model by integrating it into a traditional filter-based VIO system (ROVIO), resulting in superior odometry accuracy on aggressive 3D racing trajectories near obstacles. Self-supervised learning of ego-motion estimation represents a significant step toward bridging the gap between flying in controlled, expensive lab environments and real-world drone applications. The fusion of vision and drone models will enable higher-speed flight and improve state estimation, on any drone in any environment.

Developing robust drone detection systems is often constrained by the limited availability of large-scale annotated training data and the high costs associated with real-world data collection. However, leveraging synthetic data generated via game engine-based simulations provides a promising and cost-effective solution to overcome this issue. Therefore, we present SynDroneVision, a synthetic dataset specifically designed for RGB-based drone detection in surveillance applications. Featuring diverse backgrounds, lighting conditions, and drone models, SynDroneVision offers a comprehensive training foundation for deep learning algorithms. To evaluate the dataset's effectiveness, we perform a comparative analysis across a selection of recent YOLO detection models. Our findings demonstrate that SynDroneVision is a valuable resource for real-world data enrichment, achieving notable enhancements in model performance and robustness, while significantly reducing the time and costs of real-world data acquisition. SynDroneVision will be publicly released upon paper acceptance.

Explosions in Armenia, broadcast on YouTube in 2020, revealed this new shape of war to the world. There, in a blue-tinted video, a radar dish spins underneath cyan crosshairs until it erupts into a cloud of smoke. The action repeats twice: a crosshair targets a vehicle mounted with a spinning dish sensor, its earthen barriers no defense against aerial attack, leaving an empty crater behind. The clip, released on YouTube on September 27, 2020, was one of many the Azerbaijan military published during the Second Nagorno-Karabakh War, which it launched against neighboring Armenia that same day. The video was recorded by the TB2.

Last November, at Fort Campbell, Tennessee, half a mile from the Kentucky border, a single human directed a swarm of 130 robots. The exercise was part of DARPA's OFFensive Swarm-Enabled Tactics (OFFSET) program. If the experiment can be replicated outside the controlled settings of a test environment, it suggests that managing swarms in war could be as easy as point and click for operators in the field. "The operator of our swarm really was interacting with things as a collective, not as individuals," says Shane Clark, of Raytheon BBN, who was the company's main lead for OFFSET. "We had done the work to establish the sort of baseline levels of autonomy to really support those many-to-one interactions in a natural way."