Read all back issues online www.ust-media.com UST 45 : AUG/SEPT 2022 UK £15, USA $30, EUROPEe22 Working watchdogs Focus on performance monitoring All about the image The growing size and sophistication of gimbals Double duty How the TideWise Tupan teams a USV with a UAV or ROV to inspect offshore equipment
FOGs Go Photonic Coming Soon: Prism IMUs With outstanding reliability and environmental survivability over competing technologies, KVH’supcomingnewPrism lineof IMUs featuresexclusivephotonic tactical-gradegyrosmade with integrated chip (PIC) technology. This breakthrough technology reimagines fiber optic gyros (FOGs) by replacing individual fiber components with an integrated planar optical chip. Offering excellent shock and vibration resistance, KVH’s new photonic IMUs will also offer a wide range of inertial-grade accelerometers that further enhance system performance. The result is a series of robust inertial sensors designed to deliver the performance and survivability that autonomous platforms demand: ©2022 KVH Industries, Inc. KVH and PIC Inside are trademarks of KVH Industries, Inc. Protected by U.S. patent # 10,274,319 Additional patents pending. Learn more at: kvh.com/pic KVH Industries, Inc. | 50 Enterprise Center | Middletown, RI 02842 U.S.A. | fogsolutions@kvh.com | +1 401.847.3327 • Low Noise • Robust orientation stability • User-programmable Data Output • Excellent bias stability • High Bandwidth • Non-ITAR LAND SEA AIR See Precision in a New Light
48 24 58 80 108 3 August/September 2022 | Contents Uncrewed Systems Technology | August/September 2022 04 Intro Despite the doomsayers, practical and commercial uncrewed systems are now rolling out in a variety of markets 06Platform one: Mission-critical info Two-part radar architecture unveiled for all-weather sensors on UAVs, submarine designed with a skin of sensors, trans-Atlantic control of an inspection UAV, machine learning makes 3D mapping more cost-effective, tanker makes autonomous voyage from Texas to South Korea, and much more 20 In conversation: Kelvin Hamilton The CEO of Flare Bright explains how the company’s machine learning system optimises UAV safety and performance in a fraction of the time other approaches take 24Dossier: TideWise USV Tupan We look at how this USV-UAV/ROV combination was developed for inspecting offshore energy facilities 38Focus: Performance monitoring How technologies such as nanocarbon graphene platelets, solid-state sensors and machine learning are providing advances in how to monitor the performance of uncrewed systems 48Digest: Bayonet 350 The development story behind this UGV, which has been designed to do the work of UAVs and AUVs in shallow waters 58 Insight: UAVs Developers tell us about their particular approaches to UAV design, and how that has led to a growing vehicle diversity 68Show report: AUVSI Xponential 2022 The second part of our in-depth review of the latest systems and technologies on show at this pre-eminent event 80Dossier: ULPower UL350i and UL350iHPS We investigate this company’s best-selling 350i and the novel forced-air cooling system on the 350iHPS 92 In operation: Elroy Air Chapparal Courier services providers are already eyeing this prototype hybrid-electric VTOL-transitioning UAV with interest. Here’s why 98Focus: Gimbals Our update on the state of play in gimbals technologies, plus we point to some prospects for the future 108Digest: Clogworks Dark Matter Designed for all-weather BVLOS missions, this hexacopter has recently been given an extensive update. Here are the details 114PS: Visual navigation Why the task of providing uncrewed vehicles with reliable visual navigation is proving surprisingly difficult
Read all back issues online www.ust-media.com UST 45 :AUG/SEPT 2022 UK £15,USA$30,EUROPEe22 Working watchdogs Focus on performancemonitoring All about the image The growing size and sophistication of gimbals Double duty How the TideWise Tupan teams aUSV with aUAV orROV to inspect offshore equipment 4 Over the past few years there has been some negativity about the roll-out of uncrewed systems. Driverless cars would not be seen on the roads for a decade, for example, or the struggles with uncrewed shipping and regulations would kill off the technology. But driverless vehicles are already travelling unescorted on the roads of San Francisco, albeit at night and with some challenges where they stopped in the road and caused traffic jams. And suppliers are getting ready for the mass roll-out of driverless technology. For example, after acquiring software developer Five AI, automotive developer Bosch is field-testing its technologies for Level 4 autonomy. Similarly, Baidu in China has developed a driverless car, the Apollo RT6, without a steering wheel. It will cost around $37,000, whereas the previous version, the Apollo Moon, cost $75,000 last year, which even then was half that of the established cost of a Level 4 driverless vehicle. At the same time, ships are travelling across oceans without input from the crew, as our Platform One report on the Prism Courage shows. Granted, there are always ups and downs in developing any technology, but uncrewed systems are now being rolled out in practical, commercial projects. Nick Flaherty | Technology Editor Roll out, roll out Editorial Director Ian Bamsey Deputy Editor Rory Jackson Technology Editor Nick Flaherty Production Editor Guy Richards Contributor Peter Donaldson Technical Consultants Paul Weighell Ian Williams-Wynn Dr Donough Wilson Prof James Scanlan Design Andrew Metcalfe andrew@meticulousdesign.com UST Ad Sales Please direct all enquiries to Freya Williams freya@ust-media.com Subscriptions Frankie Robins frankie@ust-media.com Publishing Director Simon Moss simon@ust-media.com General Manager Chris Perry Intro | August/September 2022 August/September 2022 | Uncrewed Systems Technology Volume Eight | Issue Five August/September 2022 High Power Media Limited Whitfield House, Cheddar Road, Wedmore, Somerset, BS28 4EJ, England Tel: +44 (0)1934 713957 www.highpowermedia.com ISSN 2753-6513 Printed in Great Britain ©High Power Media All rights reserved. Reproduction (in whole or in part) of any article or illustration without the written permission of the publisher is strictly prohibited. While care is taken to ensure the accuracy of information herein, the publisher can accept no liability for errors or omissions. Nor can responsibility be accepted for the content of any advertisement. SUBSCRIPTIONS Subscriptions are available from High Power Media at the address above or directly from our website. Overseas copies are sent via air mail. 1 year subscription – 15% discount: UK – £75; Europe – £90 USA – £93.75; ROW – £97.50 2 year subscription – 25% discount: UK – £135; Europe – £162 USA – £168.75; ROW – £175.50 Make cheques payable to High Power Media. Visa, Mastercard, Amex and UK Maestro accepted. Quote card number and expiry date (also issue/start date for Maestro) ALSO FROM HPM THE COMMUNICATIONS HUBOF THE RACING POWERTRAINWORLD DARRENSANSUM: The revamped IndyCarV6 turbo recipe JULY 2022 UK £15,US/CN$25,EUROPEe22 www.highpowermedia.com HOWCOSWORTH POWERSCHAMPIONS Inside its 1994world-title 3.5 litreV8 ATTHEHEART OFTHEMATTER Monitoring combustion in real time KEEPING AWESOME SPIRIT ALIVE The challenge of Nostalgia dragV8s ISSUE015 | AUTUMN2022 UK£15 USA$30 EUROPE€22 E-MOBILITY ENGINEERING THE COMMUNICATIONS HUB OF THE ELECTRIFIED POWERTRAIN Climate control Magneticvariations Expertviewson HVAC issues inEVs Newapplications for Halleffectsensors Ground beetle HowEMotivedeveloped its6x6multi-terrainScarab The USE network Having now provided several enterprises around the world with the support and connections they need to implement efficient and sustainable technological solutions, we’re keen to continue expanding this free service. If the uncrewed vehicle and/or system you’re working on could benefit from some independent advice, from engineers specialising in the appropriate field, then please do get in touch. Email your question/challenge/dilemma/predicament to thenetwork@uncrewedsystemsengineering.comor visit www.uncrewedsystemsengineering.com and raise a case with us. All questions will be treated in the strictest confidence, and there’s no obligation whatsoever to follow any recommendations made.
UXV Technologies Portable ground control station G2NAV Customizable computers of choice Sunlight readable screens Multitouch, works with gloves and wet hands The G2NAV offers performance, durability, and a modular platform enabling a wide range of customizations. With the G2NAV you get a ground control platform that Is easy to transport and easy to mount with all the control options that you would expect from a professional ground control platform. www.uxvtechnologies.com PORTABLE GROUND CONTROL STATION G2NAV OSWINDOWS OR LINUX FLAVOUR OF CHOICE SUNLIGHT READABLE SCREENS CUSTOMIZABLE COMPUTERS OF CHOICE MULTITOUCH, WORKS WITH GLOVES AND WET HANDS THE G2NAV OFFERS PERFORMANCE, DURABILITY, AND A MODULAR PLATFORM ENABLING AWIDE RANGE OF CUSTOMIZATIONS. WITH THE G2NAV YOU GET A GROUND CONTROL PLATFORM THAT IS EASY TO TRANSPORT AND EASY TOMOUNTWITH ALL THE CONTROL OPTIONS THAT YOUWOULD EXPECT FROM A PROFESSIONAL GROUND CONTROL PLATFORM. WWW.UXVTECHNOLOGIES.COM SCANME
6 Mission-critical info for uncrewed systems professionals Platformone Cambridge Sensoriis has developed a radar architecture that can be used for lightweight, highly sensitive, all-weather sensors on UAVs (writes Nick Flaherty). The architecture is split into two parts – a high-power primary radar that can identify a variety of obstacles and aircraft, and a secondary radar that is much lighter and works specifically with the primary radar. The system operates in the 77 GHz band and was built using COTS devices. The secondary radar weighs 200 g and has a range of up to 1 km. It can be mounted on small UAVs in a swarm or on the ground, with the 1 kg primary unit mounted on a mid-sized UAV. “Several secondary radars could be on the landing pad on a moving ship, for example, or for a vertiport,” said Steve Clark, CEO and founder of Cambridge Sensoriis. This architecture allows a positioning accuracy down to 1 cm to allow an autonomous UAV to land in difficult conditions. The architecture allows the primary radar to focus only on the signals from the secondary, filtering out any reflections from the metal in the ship or a parking structure. “Our primary radar identifies cooperative and non-cooperative UAVs, and we have designed a way for the secondary radar to collaborate with the primary so that it is highly visible, while everything else is not,” said Clark. “The modulation of the primary is designed so that just the secondary is visible. We reinforce the incoming signal from the primary and clean it up. The design of both primary and secondary is to reinforce the primary signal and attenuate the background clutter. “We don’t need to increase the operating bandwidth, and both operate in the same band, which means we can use low-cost, lightweight hardware,” he said. The detection range of the primary is 300 m, and the company is working to extend this to 1 km in a UK-funded Future Flight project. The system is implemented in an FGPA with a radar front-end transceiver and custom beamforming phased array antenna designed in-house and mounted on a specialist PCB multi-layer stack. The technology is being used in a project called Portal, to develop a scalable capability for deployment in bespoke vertiports or retrofitted installations such as car parks or rooftops. Portal will support vertiports using the same flexible software architecture and with technology from Slink-Tech, Angoka, R4dar Technologies, Auriga Aerospace, Snowdonia Aerospace Centre and the University of Bristol. The Agile Integrated Airspace System (ALIAS) consortium is also using the technology to combine and demonstrate all the necessary elements of an agile and scalable airspace system. The consortium will use terrain and weather maps, and ground and UAV-installed sensing including Sensoriis’ radar, to plan safe UAV journeys and avoid obstacles on the ground or in flight. Consortium partners include Volant Autonomy, DroneCloud, DroneDefence and Sky-Drones. Sensors Two-part radar design August/September 2022 | Uncrewed Systems Technology The Sensoriis architecture allows several secondary radars to be mounted on the landing pad of a moving ship, for example
7 Platform one Uncrewed Systems Technology | August/September 2022 Microsoft has launched a softwarein-the-loop tool to build, train and test autonomous aircraft through high-fidelity simulation (writes Nick Flaherty). The AirSim tool was originally developed as a cross-platform open source system that combines the Unreal and Unity 3D display engines with popular flight controllers such as PX4 and ArduPilot in hardware in the loop with PX4 for physically and visually realistic simulations. The open source version has now been integrated into a fully tested simulator running in the cloud rather than using the Unreal or Unity plug-ins on a desktop computer. “In 2017, Microsoft Research created AirSim as a simulation platform for AI research and experimentation,” said Paul Stubbs, principal program manager for Microsoft AI, focusing on autonomous systems. “That project has served its purpose as a common way to share research code and test new ideas around aerial AI development and simulation. “Users will still have access to the original AirSim code, but there will be no further updates; instead, we will focus our efforts on a new product, Microsoft Project AirSim, to meet the growing needs of the aerospace industry. It will provide an end-to-end platform for safely developing and testing aerial autonomy through simulation.” AirSim was a popular research tool, but it required a lot of expertise in coding and machine learning, said Microsoft. The end-to-end version, Project AirSim, allows machine learning models to run through millions of flights in seconds, learning how to react to a wide range of variables. This synthetic data can be used to look at how a UAV would fly in rain, sleet or snow, and how strong winds or high temperatures would affect battery life. “Everyone talks about AI, but very few companies are capable of building it at scale,” said Balinder Malhi, engineering lead for Project AirSim. “We created Project AirSim to simulate the real world accurately, capture and process massive amounts of data and encode autonomy without the need for deep expertise in AI.” Developers will be able to access pretrained AI building blocks, including models for detecting and avoiding obstacles and executing precision landings. Microsoft is also extending the simulation to weather, physics and the sensors used on a UAV. It is working with physics-based simulation tool developer Ansys on models that can be used in AirSim, and with MathWorks so that developers can import their own physics models to the AirSim platform using Simulink. Helicopter and UAV developer Bell has been using an early version of the tool to improve the ability of its UAVs to land autonomously. AirSim enabled Bell to train its AI model on thousands of ‘what if’ scenarios in a matter of minutes. “AirSim allowed us to get a true understanding of what to expect before we flew in the real world,” said Matt Holvey, director of intelligent systems at Bell. “It’s going to be one of the tools that will accelerate the timeline for scaling aerial mobility. If we have to test and validate everything by hand, in a physical lab, or on a flying aircraft, we’re talking about decades, and it’s going to cost billions, but Project AirSim pulls that forward through high-fidelity simulation.” Simulation AI-based testing for UAVs Project AirSim is an end-to-end simulator to train AI systems for UAVs AirSim will be one of those tools that will accelerate the timeline for scaling aerial mobility. If we have to test everything by hand it will take decades
8 Platform one Smith Myers has developed a mobile phone detection, location and comms system with maritime connectivity (writes Nick Flaherty). Its Artemis system can detect and locate mobile phones, for example for search & rescue missions. This has been combined with dual-band maritime AIS identifiers and personal rescue beacons in its latest Artemis T-U system, which weighs 1.4 kg, for medium to large uncrewed airborne systems. A single I/O simplifies integration with a UAV, and a zero-airflow design offers integrators maximum flexibility in placement, requiring two small antennas to generate a latitude/longitude fix at ranges in excess of 30 km. The system also provides texting and calls in no-service areas, and links automatically to EO/IR cameras to help operators identify people in trouble at sea. “Incorporating all these capabilities into a single unit gives the ability to directly detect and locate Emergency Position Indicating Radio Beacons and Personal Locator Beacons ([OSPAS SARSAT], while performing the same actions with mobile phones will be invaluable for search & rescue or disaster relief missions,” said Nathan Herbert, senior development and integration engineer at Smith Myers. “The fusion of cellular and AIS sensor data in a single user interface/analysis tool also opens the path to more effective and efficient maritime patrol operations while reducing operator workload.” A simulator for the Artemis system allows different real-world scenarios to be created through a simple interface. This includes simulated mobile phones that are in or out of coverage, and simulated 2G, 3G, 4G and 5G networks, all of which behave as they would in the real world. The items created can then be dragged onto a worldwide map. When combined with the Artemis software, the mobile phones can be located as they would in a real mission. “At Smith Myers we use the simulator to test and refine our own software, as it gives the opportunity to repeatedly ‘fly’ missions with very realistic results,” said senior software engineer Simon Alford. Comms Maritime rescue system August/September 2022 | Uncrewed Systems Technology The Artemis T-U combines a mobile phone receiver with a maritime beacon receiver Researchers in Germany are developing a submarine robot with specialist sensors (writes Nick Flaherty). The Bionic RoboSkin project, supported by Germany’s Ministry of Education and Research and led by EvoLogics, is developing a compound fabric that is fitted with sensor elements and water-resistant connectors to supply the sensors with power and transmit the data to the water’s surface. Researchers from Fraunhofer IZM are integrating sensor modules so that the AUV, modelled on a manta ray, can detect the proximity of objects and ‘see’ and analyse their surroundings. The manta ray-inspired AUV has a flexible skin fitted with a range of sensors The permeable and therefore pressure-neutral fabric skin is fitted with touch, flow, motion and position sensors. This textile skin is then pulled tight over the robotic fins. The case itself works as a conductor by creating the mechanical and electrical contact with the sensor skin itself. Tiny hooks on the sensor module itself snap together to form an easily detachable/ attachable interface. The resulting system is modular to allow easy reconfiguration. Sub has sensors on its skin Underwater vehicles
9. HEX/Cubepilot – needs name Cubepilot ecosystem Acecore NOA - THE ULTIMATE The Acecore Noa is the first drone to combine heavy lifting with endurance in harsh environments. Its s i x effic ient ly dr i ven motors gi ve i t the endurance, redundancy and confidence that is required to get the most out of high-end payload sensors. With the Cube Orange flight control installed, the STM32H7 p roce s so r and t r i p l e r edundanc y IMU improves data processing speed efficiency and flight safety. Paired with a Riegl VUX-SYS or YellowScan LiDAR, the Acecore Noa t rans forms into a rel iable car r ier that thrives in large scale land and bathymetric surveys. RTK workflows are enabled by the on-board multiband F9P ai r uni t . Flight times of 60 minutes are easily achieved by the a l l - e l ec t r i c Noa , whe reas a f u t u re hybr i d version could t r iple that number. The upgraded Acecore-standard Herel ink 'George' provides users with an improved pilot and mission control experience by providing an on-board battery that lasts all day, as well as a mounting rails for an external tablet.
10 Platform one Engineers at Plextek in the UK have developed a low-cost millimetre-wave radar on a single PCB (writes Nick Flaherty). “Radar operating in the 60 GHz band offers detection ranges of many tens of metres, and is able to detect very small targets regardless of the time of day or adverse weather, including fine targets such as powerlines,” said Aled Catherall, CTO at Plextek. ”We have engineered a millimetre-wave radar so that it incorporates a phased array capable of fast scanning and the supporting electronics to achieve realtime data capture and processing. The 60 GHz band takes advantage of technology advances in consumer telecoms such as reduced antenna size as well as Low Probability of Intercept/Low Probability of Detection analyses.” For millimetre-wave radar applications, the antenna is a key component to enable scanning of a narrow beam rapidly in different directions. Phased array technology is a good approach but achieving an efficient implementation, such that the total sensor power consumption is only a few watts and within a small physical size, requires careful design and optimisation. Advances such as low-cost SiGe chipsets provide most of the required millimetre-wave functionality. Combining this technology with an electronically scanning, small, integrated and highly directional antenna offers a highperformance, low-SWaP-C solution suitable for UAV sense & avoid applications. “A high-resolution millimetre-wave radar may lack the fine detail that a camera creates, but it much more readily reflects the geometry of the world it views, since it directly provides range estimates to each object in the scene,” Catherall said. “Our radar also measures Doppler, which can provide a rapid estimate of how quickly something is moving toward the drone to support avoidance measures. A radar that scans in both azimuth and elevation provides a direct, 3D estimate of its location. “Test results of our radar demonstrate successful detection of small, static obstacles above ground clutter, such as metal poles, people and cars, at sufficient ranges to enable evasive action and route planning. In addition, Doppler processing enables discrimination of moving objects such as other, small UAVs or birds. Low-cost radar on one PCB Radar August/September 2022 | Uncrewed Systems Technology Plextek’s millimetre-wave radar incorporates a phased array to achieve real-time data capture MKS Instruments has developed a motorised infrared zoom lens optimised for the new generation of 10 µm pixel SXGA/ HD FPA (focal plane array) and 15 µm VGA FPA detectors (writes Nick Flaherty). The LightIR 18-225 mm MWIR f/4 lens takes advantage of the smaller pixels to reduce the size of the optical elements. That significantly decreases the length and weight of the lens to 84 mm long, 61.4 mm in diameter and 326 g, making it 19% smaller than similar lenses. The optics are designed to operate near the diffraction limit of the sensors at wavelengths of 3.4 to 4.9 µm and maintain focus throughout the entire zoom range. “The lens addresses the new market shift toward smaller pixel-size detectors,” said Dr Kobi Lasri, general manager, Ophir Optics Group. “It combines lowSWaP capabilities and a detection range of more than 16 km. That makes it an enabler for advanced UAV and small gimbal thermal imaging applications.” The lens is powered by a 6-12 VDC line with a peak current of 1.0 A. An RS422 interface is used to connect to most gimbals and camera systems. IR lens for new-gen sensors Imaging
T-Motor power makes your exploration www.tmotor.com Skypersonic has demonstrated a UAV being remotely piloted across the Atlantic Ocean using a standard mobile phone (writes Nick Flaherty). An operator in Orlando, Florida, controlled a Skycopter UAV inspecting a utility plant in Turin, Italy – a distance of 4800 miles. The cage-based spherical UAV is 35 cm in diameter, weighs 950 g and has a flight time of 14 minutes. The Orlando-based pilot had no advance knowledge of the Iren district heating plant in Turin. The signal latency was 68 ms, allowing safe piloting via the video feed alone, as the UAV is designed to be used without GNSS satellite navigation for inspections. The Skycopter’s radio controller connects to a PC with software that optimises the packets over a dedicated virtual network link via a mobile phone. “This is actually our third trans-Atlantic flight,” said Giuseppe Santangelo, CEO of Skypersonic, which builds the UAVs. “We learned that an internet connection via a mobile phone in the vicinity of the UAV is all that is needed to remotely pilot it from virtually anywhere – in fact, up to 8000 miles away. “The previous two flights had relied on a more sophisticated, non-mobile internet connection. We also learned that it is possible to navigate a very dense and complex interior environment from another continent using this set-up. Trans-Atlantic inspection Airborne vehicles The Skypersonic UAV was controlled from Florida to inspect this heating plant in Italy POWER MAKES YOUR EXPLORATION www.tmotor.com
12 Researchers in Switzerland have used machine learning to develop a way to make 3D mapping more cost-effective (writes Nick Flaherty). “Switzerland is currently mapping its entire landscape using airborne laser scanners – for the first time since 2000 – but the process will take 4 or 5 years, since the scanners have to fly at an altitude below 1 km if they are to collect data with sufficient detail and accuracy,” said Jan Skaloud, a senior scientist at the Geodetic Engineering Laboratory in the EPFL’s School of Architecture, Civil and Environmental Engineering, which developed the algorithms. “With our method, surveyors can send laser scanners as high as 5 km and still maintain accuracy. Our lasers are more sensitive and can beam light over a much wider area, making the process five times faster,” he said. The accuracy of Lidar scanners can be lost when mounted on UAVs or other moving vehicles, especially in areas with numerous obstacles such as cities, infrastructure sites and places where GNSS satellite navigation signals are interrupted. This results in gaps and misalignments in the data used to generate the 3D point cloud, and can lead to ‘double vision’ of scanned objects. These errors must be corrected manually before a map can be used. “For now, there’s no way to generate perfectly aligned 3D maps without a manual data correction step,” said Davide Cucci, senior research associate at the Research Center for Statistics of the Geneva School of Economics and Management of the University of Geneva, who also worked on the technology. “A lot of semi-automatic methods are being explored to overcome this problem, but ours has the advantage of resolving the issue directly at the scanner level, where measurements are taken, eliminating the need to subsequently make corrections. It’s also fully softwaredriven, meaning it can be implemented quickly and seamlessly by end-users.” The technique uses machine learning to detect when a given object has been scanned several times from different angles. It involves selecting correspondences and inserting them into a dynamic network to correct gaps and misalignments in the Lidar point cloud. That improves the point cloud registration accuracy by a factor of five in normal use and by a factor of 10 in simulations with a GNSS outage. AI speeds up 3D surveying Mapping August/September 2022 | Uncrewed Systems Technology EPFL researchers with their machine learning-enabled mapping UAVs
Platform one ModalAI has launched a Qualcommbased autopilot for its UAVs that weighs just 16 g (writes Nick Flaherty). The VOXL 2 autopilot integrates a PX4 real-time flight controller with an eightcore microcontroller with a performance of up to 15 TOPs, two TDK IMUs, a barometer and a 5G connection. There are interfaces to seven image sensors. VOXL 2 enables autonomy and comms for indoor and outdoor UAVs and robots with vision-based SLAM and AI for movement, and is designed specifically for GPS-denied autonomous UAVs with obstacle avoidance. With a 5G add-on card, VOXL 2 can be used beyond visual line of sight. The autopilot uses ModalAI’s Blue UAS Framework software developed as part of the US Department of Defense’s Blue SUAS2.0 project, and runs on Qualcomm’s Flight RB5 5G QRB5165 chipset to provide a US supply chain for parts. The company is also developing an autonomous mobile robot (AMR) reference design based on the same QRB5165 and VOXL 2 software. The AMR’s design uses the input from front and rear stereo 4K resolution image sensors for GPS-denied navigation in indoor environments. It also integrates ultrasonic object detection and 3D mapping from a 2D image sensor handled in the AI engine in the chipset. The VOXL2 autopilot integrates a PX4 real-time flight controller with an eight-core microcontroller Super-light autopilot Airborne vehicles ENABLING TECHNOLOGY EVERYWHERE Harwin’s connector products are proven to perform in extreme conditions, with shock, vibration and temperature range rigorously tested. Micro connectors start at 1.25mm pitch delivering 2A per contact, up to 8.5mm and 60A - we cover a wide range of applications for when SWaP matters most. With our quality, service, support, and highly reliable products, you can depend on Harwin. harwin.com Scan here for more Connect with confidence Connectors shown actual size Harwin UAV Uncrewed Systems June 22.indd 1 18/05/2022 13:55
14 Platform one August/September 2022 | Uncrewed Systems Technology Trimble has launched a dual-frequency OEM GNSS receiver module that supports its RTX correction services for autonomous applications (writes Nick Flaherty). The BD9250 has an industrystandard form factor of 71.1 x 45.7 x 11 mm and a standard 28-pin pinout, to allow easy integration. The module weighs 55 g and supports all the major GNSS constellations, including GPS, Galileo, GLONASS, BeiDou, QZSS and NavIC. Support for the Indian NavIC S-Band signal is also available with the Trimble BD9250s version. The module has 336 tracking channels for multi-constellation GNSS support with multi-path mitigation and low-elevation tracking. Maxwell 7 technology in the module uses three signals from each The BD9250 receiver has 336 tracking channels for multi-constellation GNSS support satellite for more accurate positioning. It also uses onboard RF spectrum analysis to protect against spoofing and interference. In addition, the module uses Trimble’s RTX correction subscription services to provide an accuracy to within 2 cm horizontally without the need for a base station. It also uses Trimble’s ProPoint positioning engine to improve the RTX performance in difficult conditions such as under canopies, highway overpasses and in dense urban areas, and uses sensor fusion to integrate the GNSS data with data from the IMU. It is also compatible with generic RTK services that use a separate base station to send radio signals to provide greater positioning accuracy. The receiver includes the ability to enable system integrators to choose between the L2 or L5 frequency bands to optimise signal performance and maximise the number of measurements available to the GNSS engine. An Ethernet connector allows highspeed data transfer and configuration via standard web browsers. USB, CAN and RS-232 are also supported. L2/L5 satcom receiver Satcom Mythic has ported its low-power analogue machine learning chip to the Sentinel UAV reference design from ModalAI (writes Nick Flaherty). Sentinel is a ready-to-fly craft with 2.4/5 GHz wi-fi or 1.8/2.3 or 2.4 Ghz pointto-point wireless links and an Analog Matrix Processor (AMP) machine learning chip from Mythic. The chip has been added to the UAV on an M.2 format board measuring 22 x 80 mm for image processing. The Sentinel uses the latest PX4 autopilot running on Qualcomm’s QRB5165 chipset, which also runs ROS 1/2 or Ubuntu 18.04 Linux. There is also a Docker build environment for the CPU, graphics GPU and digital signal processor on the chipset to run machine learning models. The first AMP chip is the MNP1076, which has 76 tiles that handle the machine learning frameworks in a more powerThe Sentinel reference design uses a low-power AI chip from Mythic efficient way than a digital GPU. This gives a typical power consumption of 3 W, making it suitable for UAV applications. Because the chip handles machine learning frameworks in a different way, the key is the software compiler. Deep neural network models developed in standard frameworks such as Pytorch, Caffe and TensorFlow are optimised for the chip, reduced in size and then retrained for the Mythic Analog Compute Engine before being processed through Mythic’s compiler. The resulting binary code and model weights, typically 80 m parameters, are then programmed into the AMP for inference. All the weights are stored on the chip, which avoids having to use off-chip memory, saving a lot of power. Pre-qualified models such as the YOLOv3 image recognition framework are also available for developers. Imaging AI fitted to UAV Airborne vehicles
World’s First FAA Certified Micro Transponder to Have ADS-B In/Out Sagetech’s next-gen MXS miniature transponder provides Mode A, C, S, and 1090 MHz ADS-B In/ Out and is suitable for use worldwide by crewed or uncrewed systems. Each transponder comes with user-friendly command and control software with a built-in traffic display for situational awareness or can be used plug and play with PX4, Ardupilot, and many other autopilots. The MXS is the ideal transponder for improving aircraft visibility and safety, especially when small size and low power consumption are critical. DETECT AND AVOID CORNERSTONE The certified MXS is the cornerstone of Sagetech’s Detect and Avoid (DAA) architecture which will support Beyond Visual Line of Sight (BVLOS) operations by their customers. Sagetech’s DAA products will accelerate the next generation of UAV-based services for both defense and civil customers. Together with the MXS, Sagetech’s ACAS-based DAA platform will provide the most advanced, certifiable DAA system for crewed and uncrewed aircraft with onboard, full power, low SWaP collision avoidance capability. INTEGRATED SOLUTION The MX family represents the only logical solution for an OEM positioning their aircraft in both the civil and military markets. UAS providers can simply install the MX12B for their military customers or swap it out with an MXS for their civil customers. No additional integration, no software changes, no aircraft changes. The MXS provides uncrewed and crewed aircraft OEMs with exciting options they didn’t have before. • One box solution including ADS-B In/Out • Unprecedented micro-SWaP • Full Diversity • 1090 MHz ADS-B In/Out with Flexible I/O – RS232, RS422, ethernet #FlySaferWithSagetech To learn more, visit: www.sagetech.com “Certification means safety and trust, to know that you will reliably detect all 1090 MHz ADS-B traffic.” — Tom Furey | CEO
16 August/September 2022 | Uncrewed Systems Technology SK Shipping has demonstrated the first autonomous operation of a super-large liquid natural gas (LNG) carrier in a month-long transoceanic voyage (writes Nick Flaherty). The Prism Courage carrier was equipped with the HiNAS 2.0 Level 2 autonomous navigation system developed by Avikus and operated over a 10,000 km journey. The HiNAS 2.0 system created optimal routes to reduce fuel consumption by 7% and avoided more then 100 collisions with other ships. The Prism Courage departed from Freeport in Texas on the southern coast of the Gulf of Mexico on May 1, passed through the Panama Canal and arrived at the Boryeong LNG Terminal in South Korea after 33 days. Around half the 20,000 km journey was under the control of the HiNAS 2.0 system. The AI system recognises the surrounding environment, such as weather, wave heights and nearby ships, and then controls the vessel’s steering commands in real time. The Level 2 autonomous navigation technology can control and operate the ship in addition to the functions of recognition and judgement (Level 1). The system uses both IR and EO cameras. The IR camera has a resolution of 640 x 512 pixels, a horizontal field of view (FoV) of 50º and a total FoV of 140º, while the EO camera has a resolution of 1920 x 1080 pixels and a horizontal FoV of 110º, for a total FoV of 180º to cover the horizon. This image data is fused with data from S-band and X-band radars and AIS identification system on the vessel. The vision processing is handled on an eight-core ARM processor on a single-board computer, and the AI runs on an Intel server with 16 Gbytes of DDR4 DRAM memory and a 2 Tbyte hard drive. The voyage was conducted under realtime monitoring by the American Bureau of Shipping (ABS) and the Korea Register of Shipping to verify the performance and stability of the technology. Avikus plans to commercialise HiNAS 2.0 before the end of this year after receiving a certification from ABS. The next stage is to upgrade the recognition system to identify and avoid small leisure boats so that the system can be used closer to the shore. Tanker’s pan-ocean debut Surface vessels Crew on the ‘Prism Courage’ examine the Avikus HiNAS 2.0 autonomous navigation system during its voyage from Texas to South Korea
17 Platform one Uncrewed Systems Technology | August/September 2022 The Exploration Company is using a mid-band satellite terminal for a key test of its autonomous reuseable space capsule (writes Nick Flaherty). The Nyx capsule is designed for orbiting the Earth for 3 to 6 months with payloads up to 4000 kg, as well as landing on the Moon to resupply a lunar base with a cargo of 1600 kg. A subscale re-entry demonstrator of Nyx will be launched on the maiden flight of the new Ariane 6 rocket later this year. Once in orbit, the capsule will detach and begin reentry to Earth. The data from the test flight will be relayed via the Iridium Next satellite network using a Certus DLS-100 transceiver from Skytrac. The transceiver weighs 742 g and is capable of real-time command and control, telemetry streaming and photo/video transmission with 22 kbit/s uplink speeds. As the capsule is an unrecoverable technology demonstrator it will crash into the sea after collecting and transmitting the data. “Starting at an altitude of 360 miles, the capsule will collect data from systems and sensors, which will be transmitted over the Iridium network to the ground from the DLS-100,” said Thomas Nussmann, lead avionics and power engineer at The Exploration Company. “The ruggedised data link will provide the low latency, global, and reliable satellite connectivity the capsule requires to conduct this demonstration.” Space systems Dr Donough Wilson Dr Wilson is innovation lead at aviation, defence, and homeland security innovation consultants, VIVID/futureVision. His defence innovations include the cockpit vision system that protects military aircrew from asymmetric high-energy laser attack. He was first to propose the automatic tracking and satellite download of airliner black box and cockpit voice recorder data in the event of an airliner’s unplanned excursion from its assigned flight level or track. For his ‘outstanding and practical contribution to the safer operation of aircraft’ he was awarded The Sir James Martin Award 2018/19, by the Honourable Company of Air Pilots. Paul Weighell Paul has been involved with electronics, computer design and programming since 1966. He has worked in the real-time and failsafe data acquisition and automation industry using mainframes, minis, micros and cloud-based hardware on applications as diverse as defence, Siberian gas pipeline control, UK nuclear power, robotics, the Thames Barrier, Formula One and automated financial trading systems. Ian Williams-Wynn Ian has been involved with uncrewed and autonomous systems for more than 20 years. He started his career in the military, working with early prototype uncrewed systems and exploiting imagery from a range of uncrewed systems from global suppliers. He has also been involved in groundbreaking research including novel power and propulsion systems, sensor technologies, communications, avionics and physical platforms. His experience covers a broad spectrum of domains from space, air, maritime and ground, and in both defence and civil applications including, more recently, connected autonomous cars. Professor James Scanlan Professor Scanlan is the director of the Strategic Research Centre in Autonomous Systems at the University of Southampton, in the UK. He also co-directs the Rolls-Royce University Technical Centre in design at Southampton. He has an interest in design research, and in particular how complex systems (especially aerospace systems) can be optimised. More recently, he established a group at Southampton that undertakes research into uncrewed aircraft systems. He produced the world’s first ‘printed aircraft’, the SULSA, which was flown by the Royal Navy in the Antarctic in 2016. He also led the team that developed the ULTRA platform, the largest UK commercial UAV, which has flown BVLOS extensively in the UK. He is a qualified full-size aircraft pilot and also has UAV flight qualifications. Uncrewed Systems Technology’s consultants Satcom test for orbiter One application for the Nyx capsule will be to orbit the Earth for 3 to 6 months at a time
18 Platform one August/September 2022 | Uncrewed Systems Technology With international travellers returning to the sky in numbers, preparations for the 2022 Commercial UAV Expo are nearing completion, and it aims to be the biggest iteration of this world-leading show yet. Taking place at Caesars Forum in Las Vegas from September 6 to 8, the event is set to feature more than 200 exhibitors from across Asia, Australia, Europe and North and South America. The companies will showcase their latest offerings and innovations in UAVs as well as key related technologies such as Lidar, batteries, antennas and AI. The conference programme meanwhile will present ground-breaking research and discussions for UAV suppliers and customers in markets such as construction, delivery, energy, utilities, forestry, agriculture, infrastructure, transportation, mining and mapping. Keynotes will be announced soon but will include leading figures from the FAA, DroneUp, Matternet, Wing and Zipline. Other features of the show floor include dedicated pavilions for start-ups and universities, as well as special receptions for welcomes and networking, with educational programming in the Exhibit Hall Theatre. For more information, visit www.expouav.com Commercial UAV Expo 2022 Industry Following its successful first year, the DroneX trade show and conference is returning to the ExCeL in the London Docklands on September 7 and 8. Attendees will be able to network with more than 3000 like-minded professionals from every corner of the industry, and learn about the latest happenings across UAVs for surveillance, disaster response, logistics and many more use cases. As the UK’s largest event dedicated to uncrewed aircraft, around 300 exhibitors are expected to appear on the show floor, including UAS technology innovators such as Network Rail and Honeywell Aerospace, who will be showcasing their products and services. The conference will also feature 100-or-so seminars packed into a 2-day schedule to provide insightful tips from industry leaders in the commercial, defence, and emergency services markets, giving attendees and exhibitors the opportunity to discover the latest trends and advances needed to continue moving the industry forwards. For more information, visit www.dronexpo.co.uk DroneX 2022 Industry
Commercial UAV Expo Americas Tuesday 6 September – Thursday 8 September Las Vegas, USA www.expouav.com DroneX Wednesday 7 September – Thursday 8 September London, UK www.dronexpo.co.uk Space-Comm Expo Wednesday 7 September – Thursday 8 September Farnborough, UK www.space-comm.co.uk AutoSens & InCabin Monday 12 September – Wednesday 14 September Brussels, Germany www.auto-sens.com/events/brussels InfraTech Tuesday 20 September – Thursday 22 September Essen, Germany www.infratech.de UAV Technology Monday 26 September – Tuesday 27 September London, UK www.smgconferences.com/defence/uk/ conference/UAV-Technology Unmanned Maritime Systems Technology USA Wednesday 28 September – Thursday 29 September Arlington, VA, USA www.smgconferences.com/defence/northamerica/ conference/umst-usa Unmanned Systems West Thursday 29 September – Friday 30 September San Diego, CA, USA www.americanconference.com Intergeo & Interaerial Solutions Tuesday 18 October – Thursday 20 October Essen, Germany www.intergeo.de/en Global Drone Conference Wednesday 19 October – Thursday 20 October Kuala Lumpur, Malaysia www.globaldroneconference.com Airborne ISR Wednesday 19 October – Thursday 20 October London, UK www.smgconferences.com/defence/uk/ conference/airborne-isr Bahrain Airshow Wednesday 9 November – Friday 11 November Sakhir Airbase, Kingdom of Bahrain www.bahraininternationalairshow.com Air and Missile Defence Technology Wednesday 16 November – Thursday 17 November London, UK www.smgconferences.com/defence/uk/ conference/Air-Missile-Defence Counter UAS Technology USA Monday 5 December – Tuesday 6 December Arlington, VA, USA www.smgconferences.com/defence/northamerica/ conference/counter-uas-tech IoT Tech Expo Wednesday 1 December – Thursday 2 December London, UK www.iottechexpo.com/global UVS-Oman Conference Monday 6 February – Wednesday 8 February 2023 Oman, Muscat www.uvsc.om Geo Week Monday 13 February – Wednesday 15 February 2023 Denver, CO, USA www.geo-week.com Oceanology International Americas Tuesday 14 February – Thursday 16 February 2023 San Diego, USA www.oceanologyinternationalamericas.com Uncrewed Systems Technology diary 19 Uncrewed Systems Technology | August/September 2022
20 Artificial intelligence that learns by trial and error, much like a human toddler, and the virtual twin of a real-world UAV, combine to develop flight control software automatically at unprecedented speed using tiny data sets. That is the capability that Flare Bright is developing in its Machine Learning Digital Twin (MLDT) system, according to CEO Kelvin Hamilton. Born in the mid-1970s in a small village in mid-Wales, Hamilton recalls being impressed by Cold War jets roaring overhead in the low-flying training area there, particularly Vulcan bombers, which constituted his introduction to aviation as a boy. An education in electrical and electronic engineering led him initially into underwater robotics, but these days he runs a company dedicated to making UAVs safer and optimising their performance using MLDT technology. Flare Bright runs sparse flight test data and environmental measurements through its own software. “First, we use the drone’s flight characteristics that we calculate from a few seconds of flight data, which is a big advantage over most AI, which requires huge data sets,” Hamilton says. “Second, we factor in wind and environmental influences. We don’t need complex fluid dynamic models here, because we throw every possible scenario at the situation and, more or less, cover a year’s worth of flight tests in a simulated environment in a few hours.” Key to autonomous flight He emphasises that ML unlocks the potential of modelling and simulation in the development of complex technologies. “ML is fantastic at optimising in a huge solution space, which a human brain simply cannot cope with,” he says. “To understand that space and train drones to fly safely is the key to unmanned and autonomous flight.” Flare Bright uses many different types of ML, their selection depending on the problem to be solved and most being optimisation techniques. “Knowing which types of ML to use, and which data sets to throw at them, is one of our key skills,” Hamilton says. “What we avoid is the need to use lots of computing power and large training data sets. We optimise using the data we create, and use edge computing [laptops and desktops] to ensure our code is hyper-efficient, meaning that it solves problems in as few steps as possible.” The use of digital twins is increasingly common for product development, because it can avoid the costs of building physical prototypes. Their application (in conjunction with ML) to creating flight control software is challenging though, because it has to run very fast to achieve worthwhile savings in time and money Flare Bright’s CEO tells Peter Donaldson how the company solves UAV flight control issues at high speed using a machine learning digital twin Twin turbo August/September 2022 | Uncrewed Systems Technology Flare Bright created a digital twin of this UAV under a Defence And Security Accelerator contract to demonstrate autonomous flight without GPS or remote control (Images courtesy of Flare Bright)
21 – ideally orders of magnitude faster than real time, Hamilton says. It is here that the ability to write ‘hyper-efficient’ code becomes essential. Back to efficient code He points out that in the early days of personal computers, their relatively meagre processing power and memory made it essential to write efficient code, but the art has faded as computing power and software complexity have grown. “Because software is so complex now, most people don’t write efficient code,” he says. “What they do is write blocks of code, and then if you have to go through that block 10 times in order to achieve the answer it doesn’t matter, because everything runs so quickly. So efficiency is not something that coders have really been taught properly for 20-odd years.” Hamilton points out that the company’s CTO, Conrad Rider, is a former champion at solving Rubik’s Cube, with a particular knack for solving it in the fewest moves. “That same sort of thinking is how he implements the software architecture and code,” Hamilton says. “That is part of the DNA of all our software engineers now, and we assess new recruits on their ability to learn these techniques rapidly. Rider wrote the entire company software ecosystem from scratch to be optimised for ML.” Solving problems in as few steps as possible is directly relevant to writing efficient code that can characterise a UAV using a minimum of real-world data to create its digital twin, then have the computer run through a very large number of scenarios in which it learns by trial and error to reproduce the behaviour of the real aircraft, checked periodically against flight test results. Hamilton emphasises that Flare Bright’s software needs relatively very small amounts of real-world data, which he refers to as “ground truth”, on which to build. He says, “Most AIs need a lot of ground truth, a huge data set of, say, 100,000 pictures of a bridge and 100,000 pictures of a pylon, tasking the computer with looking at them all and working out which are which. It will get better and better at that through reinforcement learning.” Tiny data sets “Our data sets when we were developing our aircraft were six one-second flights,” he says. “That’s all the data we need because it gives us a good enough approximation for our model to throw every scenario we can imagine at it, and because it works so quickly, we can do that overnight. “We can run hundreds of thousands of scenarios with different wind vectors, angles of flying through the wind, strengths, gusts and so on. From the sensor feeds on the aircraft we’ll know enough in those six one-second flights to know roughly how it flies. Then the digital twin tunes and optimises the flight control program by getting it closer and closer to the way it thinks the aircraft should fly. “Normally we get it pretty much right – over 90% – first time. It’s not always perfect, but then we can use the process again. That means we are saving about 90% of costs and time on any standard flight test programme.” Accelerated development Hamilton says MLDT can accelerate development times by a factor of 10, and also produces some remarkable capabilities almost as a by-product. “For example, using our MLDT we can sense the wind in flight without using pitot tubes or any other direct measurement systems,” he says. “In turn, that allows the crucial wind modelling needed for flight path planning in complex urban areas to be verified by every drone that flies, which in turn allows optimal paths to be flown. The paths themselves can be optimised using MLDT, taking into account not just the wind around buildings but accurate capabilities of each drone.” This path optimisation process can yield some counter-intuitive results, he adds, citing a flight profile that the computer was optimising for maximum time spent observing a selected target before returning the UAV to the launch point. “What the MLDT gave us resembled a handbrake turn at apogee,” he says. “Our initial inclination was to Kelvin Hamilton | In conversation Uncrewed Systems Technology | August/September 2022 Through multiple flight iterations, the Machine Learning Digital Twin system closes the gap between the predicted and real-world flight paths of the virtual and real UAVs
www.highpowermedia.comRkJQdWJsaXNoZXIy MjI2Mzk4