This drone goes where GPS can't
Published on Jun 7, 2017
"Into the Woods: This Drone Goes Where No GPS Can"NVIDIA researchers developed a drone that navigates without GPS and instead relies on deep learning and computer vision. Here, it flies along a forest trail, avoiding obstacles and maintaining a steady position in the center of the trail.
by Jamie Beckett
June 9, 2017
Buzz of drones is more annoying than any other kind of vehicle
Published on Jul 19, 2017
Article "Buzz of drones is more annoying than any other kind of vehicle"A NASA study has discovered that people find the noise of drones more annoying than that of ground vehicles, even when the sounds are the same volume.
by Alasdair Wilkins
July 18, 2017
Drones getting smarter with AI | Intel
Published on Aug 29, 2017
Drone pilot Kara Murphy and Intel Moviduis’ Cormac Brick explain why artificial intelligence and computer vision technologies are making drones easier to fly, safer and more capable that ever.
About Intel:
Intel, the world leader in silicon innovation, develops technologies, products and initiatives to continually advance how people work and live. Founded in 1968 to build semiconductor memory products, Intel introduced the world's first microprocessor in 1971. This decade, our mission is to create and extend computing technology to connect and enrich the lives of every person on earth.
Hybrid, frame and event based VIO for robust, autonomous navigation of quadrotors
Published on Sep 19, 2017
Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. These cameras do not suffer from motion blur and have a very high dynamic range, which enables them to provide reliable visual information during high speed motions or in scenes characterized by high dynamic range. However, event cameras output only little information when the amount of motion is limited, such as in the case of almost still motion. Conversely, standard cameras provide instant and rich information about the environment most of the time (in low-speed and good lighting scenarios), but they fail severely in case of fast motions, or difficult lighting such as high dynamic range or low light scenes. In this paper, we present the first state estimation pipeline that leverages the complementary advantages of these two sensors by fusing in a tightly-coupled manner events, standard frames, and inertial measurements. We show on the publicly available Event Camera Dataset that our hybrid pipeline leads to an accuracy improvement of 130% over event-only pipelines, and 85% over standard-frames only visual-inertial systems, while still being computationally tractable. Furthermore, we use our pipeline to demonstrate—to the best of our knowledge—the first autonomous quadrotor flight using an event camera for state estimation, unlocking
flight scenarios that were not reachable with traditional visual inertial odometry, such as low-light environments and high dynamic range scenes.
Reference:
"Hybrid, Frame and Event based Visual Inertial Odometry for Robust, Autonomous Navigation of Quadrotors"
by Antoni Rosinol Vidal, Henri Rebecq, Timo Horstschaefer, Davide Scaramuzza
WeRobotics Webinar - Drone journalism in conflict zones
Published on Apr 3, 2018
Speaker: Gail Orenstein Gail has been a photographer for 23 years. Her drone work from Iraq, Bangladesh and Nepal has be syndicated around the world. In this webinar presentation, she shares her first-hand insights on balancing the powers and dangers of using small drones in high-risk areas are particularly instructive regardless of whether you work in disaster response, sustainable development, public health, environmental protection or climate change resilience.
Posting Permissions
Reply With Quote
Социальные закладки