Tag
SpaceX is using a drone to clean the windows at Mission Control in Starbase, which is reminiscent of futuristic technology seen in movies.
A demonstration highlights how drone footage of crowded streets can be analyzed with just 10 lines of Python to detect and count hundreds of people, illustrating how accessible computer vision has become.
Saildrone conducted its first live-fire demonstration, launching JAGM missiles from its SD-3001 drone during RIMPAC, in collaboration with Lockheed Martin and the US Navy.
HoverAir's Versa drone has been halted in the US due to FCC drone bans, impacting its Indiegogo launch and shipping plans for backers.
This paper introduces the Travelling Thief Problem with Drone (TTP-D), which jointly optimizes ground routing, drone synchronization, and item selection using mixed-integer programming, metaheuristics, and attention-based deep reinforcement learning.
DJI showcases a slowed 60x lab test of the Mavic 4 Pro's hovering rotors, revealing steady tip vortices that demonstrate efficient airflow management for stability and control.
A test of the DJI Mavic 4 Pro's Return-to-Home (RTH) precision is showcased in a video, demonstrating how accurate the drone's RTH feature can be.
User comment on a drone rescue video, saying the rescue work was done very well.
Applies federated learning to object detection for drone fleets, enabling collaborative training without centralizing aerial imagery, achieving performance close to centralized training while preserving privacy and reducing bandwidth.
John Tse of I Build Stuff has created an autonomous flying umbrella that hovers above the user, using a depth camera and drone technology to follow and shield them from rain and sunlight without requiring manual holding.
This paper presents a two-stage learning pipeline that uses an attention-augmented gated recurrent network to estimate wind from onboard kinematics and then leverages that estimate in a reinforcement learning controller to improve quadrotor trajectory tracking under turbulent winds, reducing tracking error by 48% compared to a baseline.
A bird-inspired robot from EPFL can walk, hop over obstacles, and launch into flight without a runway, suggesting a future for drones that mimics wildlife.
Building a fault-tolerant RL octocopter from scratch, using MuJoCo simulation and PPO training with domain randomization to handle motor failures. The project aims to directly command motors via RL policy without PID loops, focusing on six failure classes.
China's National University of Defense Technology has developed a micro-drone the size of a mosquito, equipped with a camera, microphone, and sensors, designed for covert surveillance and espionage. The prototype currently has limited flight time but represents a significant advancement in miniaturized drone technology.
Gliderboy has developed a weather balloon that can glide back home after its mission, reinventing the humble weather balloon with autonomous return flight capability.
The US military used a drone boat (Corsair unmanned surface vessel) to rescue two downed Army helicopter pilots near the Strait of Hormuz, marking the first such rescue by a drone at sea.
A maker built a drone that uses a laser to track targets, leveraging Claude AI to assist in development or processing.
Nagoya startup AirKamuy launched a 120 km/h cardboard fixed-wing drone that assembles in five minutes and flies 80 minutes.