Issue 45 | Uncrewed Systems Technology Aug/Sept 2022 Tidewie USV Tupan | Performance monitoring | Bayonet 350 | UAVs insight | Xponential 2022 | ULPower UL350i and UL350iHPS | Elroy Air Chaparral | Gimbals | Clogworks Dark Matter

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 industry- standard 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 high- speed 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 point- to-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 power- The 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