Tag-based visual-inertial localization is a lightweight method for enabling autonomous data collection missions of low-cost unmanned aerial vehicles (UAVs) in indoor construction environments. However, finding the optimal tag configuration (i.e., number, size, and location) on dynamic construction sites remains challenging. This paper proposes a perception-aware genetic algorithm-based tag placement planner (PGA-TaPP) to determine the optimal tag configuration using 4D-BIM, considering the project progress, safety requirements, and UAV's localizability. The proposed method provides a 4D plan for tag placement by maximizing the localizability in user-specified regions of interest (ROIs) while limiting the installation costs. Localizability is quantified using the Fisher information matrix (FIM) and encapsulated in navigable grids. The experimental results show the effectiveness of our method in finding an optimal 4D tag placement plan for the robust localization of UAVs on under-construction indoor sites.

It's year five, or maybe ten, of "drones are going to revolutionize transport" and so far, we've got very little to show for it. Maybe it's time to put these foolish ambitions to rest and focus on where this technology could actually do some good, rather than pad out a billionaire's bottom line or let the rich skip traffic. The promise of drone deliveries, drone taxis, and personal drone attendants has never sat, or rather floated, right with me. There's so little to be gained, while braving so much liability and danger, and necessitating so much invention and testing. Why is anyone even pursuing this? I suspect it is the Jetsons-esque technotopianism instilled in so many of us from birth: It's only a matter of time and effort before we have the flying cars, subliminal learning pillows, and robot housekeepers we deserve, right?

A Chinese military contractor created a video showing off its terrifying new military technology, revealing a robot attack dog that can dropped off by a drone. The video that was initially released on the verified Weibo account of "Kestrel Defense Blood-Wing," a page affiliated with a Chinese defense contractor, shows a drone hovering over a building and then dropping off a robot on the roof. After the drone flies away, the robot gets up on four legs and then begins to scan for targets around the building with what appears to be some sort of automatic weapons attached to its back. According to a report from WarZone, the weapon mounted on the robot dog is possibly a Chinese QBB-97 light machine gun, which is capable of firing 650 rounds per minute at an effective range of 400 meters. A drone is displayed at a Chinese military parade.

Until recently, disruption in IT meant something very different than sending everybody home to work for a year. But the COVID-19 pandemic has shaken up the technology landscape, stalling some approaches and systems, while speeding the adoption of others. In our recent State of the CIO survey, tech leaders placed AI and machine learning at the top of their list of technologies most likely to significantly impact how businesses operate in 2021. IT leaders also see big data and analytics having a distinct impact, along with less widely adopted technologies such as blockchain. We reached out to IT leaders and industry analysts to get their take on which technologies pose the most disruptive potential in 2021, with some offering perspective on which technologies might be in favor as the pandemic subsides.

We propose the intermittently tethered unmanned aerial vehicle (iTUAV) as a tradeoff between the power availability of a tethered UAV (TUAV) and the flexibility of an untethered UAV. An iTUAV can provide cellular connectivity while being temporarily tethered to the most adequate ground anchor. Also, it can flexibly detach from one anchor, travel, then attach to another one to maintain/improve the coverage quality for mobile users. Hence, we discuss here the existing UAV-based cellular networking technologies, followed by a detailed description of the iTUAV system, its components, and mode of operation. Subsequently, we present a comparative study of the existing and proposed systems highlighting the differences in key features such as mobility and energy. To emphasize the potential of iTUAV systems, we conduct a case study, evaluate the iTUAV performance, and compare it to benchmarks. Obtained results show that with only 10 anchors in the area, the iTUAV system can serve up to 90% of the users covered by the untethered UAV swapping system. Moreover, results from a small case study prove that the iTUAV allows to balance performance/cost and can be implemented realistically. For instance, when user locations are clustered, with only 2 active iTUAVs and 4 anchors, achieved performance is superior to that of the system with 3 TUAVs, while when considering a single UAV on a 100 minutes event, a system with only 6 anchors outperforms the untethered UAV as it combines location flexibility with increased mission time.

Autonomous drones can operate in remote and unstructured environments, enabling various real-world applications. However, the lack of effective vision-based algorithms has been a stumbling block to achieving this goal. Existing systems often require hand-engineered components for state estimation, planning, and control. Such a sequential design involves laborious tuning, human heuristics, and compounding delays and errors. This paper tackles the vision-based autonomous-drone-racing problem by learning deep sensorimotor policies. We use contrastive learning to extract robust feature representations from the input images and leverage a two-stage learning-by-cheating framework for training a neural network policy. The resulting policy directly infers control commands with feature representations learned from raw images, forgoing the need for globally-consistent state estimation, trajectory planning, and handcrafted control design. Our experimental results indicate that our vision-based policy can achieve the same level of racing performance as the state-based policy while being robust against different visual disturbances and distractors. We believe this work serves as a stepping-stone toward developing intelligent vision-based autonomous systems that control the drone purely from image inputs, like human pilots.

The drone industry is diversifying and the number of pilots increases rapidly. In this context, flight schools need adapted tools to train pilots, most importantly with regard to their own awareness of their physiological and cognitive limits. In civil and military aviation, pilots can train themselves on realistic simulators to tune their reaction and reflexes, but also to gather data on their piloting behavior and physiological states. It helps them to improve their performances. Opposed to cockpit scenarios, drone teleoperation is conducted outdoor in the field, thus with only limited potential from desktop simulation training. This work aims to provide a solution to gather pilots behavior out in the field and help them increase their performance. We combined advance object detection from a frontal camera to gaze and heart-rate variability measurements. We observed pilots and analyze their behavior over three flight challenges. We believe this tool can support pilots both in their training and in their regular flight tasks. A demonstration video is available on https://www.youtube.com/watch?v=eePhjd2qNiI

Red Hat Device Edge Artificial Intelligence (AI) technology enhanced the flight characteristics and data processing of Lockheed Martin's Stalker.

Lockheed Martin and Red Hat, Inc. announced their collaboration to advance artificial intelligence (AI) innovation on Lockheed Martin's unmanned military platforms. The adoption of newly developed Red Hat Device Edge technology will enable Lockheed Martin's unmanned systems to operate safely in geographically constrained environments and improves the processing of sensor-derived information. In a recent demonstration, Lockheed Martin used Red Hat Device Edge on a Stalker UAS to show how AI-enhanced sensing can advance joint operations across domains. The Stalker used onboard sensors and AI to adapt in real time to a threat environment. As reported by the company, the Stalker was flying an intelligence, surveillance and reconnaissance (ISR) mission to detect a simulated military target.

EagleView announces the launch of EagleView Assess, an autonomous drone technology that provides residential property intelligence including the highest available resolution imagery, anomaly detection, and roof measurement. Launching from the ground, EagleView Assess lets contractors, adjusters, and insurance carriers obtain unbiased evidence of roof damage, including hail, wind, or aging – without the worries of actively piloting the drone. This level of autonomy plus property intelligence removes much of the friction from the claims process, speeding claim acceptance and ultimately, homeowner's repairs. Already used by industry leaders in Insurance, today contractors can join the waitlist to utilize and benefit from EagleView Assess. "Roofers spend inordinate amounts of time individually inspecting roof damage. From worrying about clear images of damage to climbing a roof, with EagleView Assess, we provide the level of quality our customers already trust and now damage detection all done autonomously. Now contractors can focus on the claim instead of being a better drone pilot," shared Allan York, VP and General Manager, Construction for EagleView.