Novel sensor systems for the future applications using UAV
Presented by Fraunhofer IZM, Germany
A workshop titled ‘Novel Sensor Systems For The Future Applications Using UAV’ will be given at DRONE Berlin by Fraunhofer Institute, one of the leading organisations of applied research in Europe. Today, mostly UAVs are used with cameras for FPV or optical surveillance. Recently IR and HSI sensors have also become an addition to the sensor tool box. Fraunhofer Institute is pursuing miniaturization of sensors, enabling future UAV´s to carry, albeit remaining lightweight, a multitude of sensor (arrays) for maximizing their usability in the industrial and R&D environment.
Thermal imaging system for drones
Presented by Workswell s.r.o. Czech Republic
Workswell WIRIS is unique thermal imaging system for unmanned aircraft. It is a compact system that combines thermal camera, a digital camera and a control unit. Workswell WIRIS system is a comprehensive solution that gives “airial” thermography completely new possibilities. Control of the system, measurement capabilities and ease of use are the same as in handheld thermal imagers. Except that in this case is the controlled camera a few hundred meters from the user, and everything can be done with switches of standard RC controller. Workswell WIRIS is revolutionary between the thermal imaging systems primarily due to its possibility of full control in real time during the flight via very standard RC controller. Remotely, it is possible to view and store fully radiometric image data (images and video) – ie. records that retain all the information about the capturing parameters, which can be subsequently fully processed in the supplied software.
Alien SkyWalker with Multi-payloads
Presented by South Surveying & Mapping Instrument Group. China
An alien-shaped and tactically designed hexacopter is perfectly facilitated with airborne RTK/PPK chipset based on SteadiCam system and other payload options such as integrated 5-lens camera unit, lightweight LiDAR scanner, thermal imager, multispectral camera, etc. This SkyWalker has been well prepared for your precise 2-dimensional productions, the extensive oblique 3D aerial photogrammetric modelings as well as other applications related to survey purposes, like inspection, investigation, broadcasting, etc. And such SkySolutions will definitely help you a great deal to get your jobs well done in the air.
Part 1: Artificial Intelligence Steering Behaviors for Autonomously Drone
Presented by Prof. Dr. Taoufik Nouri, Fachhochschule Nordwestschweiz
During this workshop, Steering Behaviors technics such as Seek a goal, Flee a drone, Arrive at position, Pursuit a drone, Evade a drone, Obstacle Avoidance, Interpose between two drones, Hide a done, Path Following, Offset Pursuit etc. will be presented. These behaviors were originally developed in the AI field. We adapt them to our drones equipped with six sonars and XBee devices.
Part 2: Artificial Intelligence for Autonomous Group Behavior Drone
Presented by Prof. Dr. Taoufik Nouri, Fachhochschule Nordwestschweiz
During this workshop we present drones group behaviors such as separation between drones, alignment of drones, cohesion of drones etc. These steering behaviors combined together let drones flying in a flocking. These behaviors were originally developed in the AI field. We adapt them to our drones equipped with six sonars and XBee devices.
Obstacle detection using a miniaturized radar sensor operating at 120GHz ISM band
Presented by Silicon Radar GmbH & University of Paderborn, Germany
Currently, all drone manufactures face the same problem: flight safety utility will become mandatory to obtain the legal admission for broad commercial use of drones. This means that on-board obstacle detection and collision avoidance is a must-have in order to overcome existing legal barriers and acceptance issues. Some of the currently available sensors are too large, too heavy, or can be poorly integrated into existing systems. During the exhibition a demonstration of a novel micro-sensor operating at 120 GHz will be given and participants will have the chance to experience the device first-hand.
Successful practice of using drones in agro insurance
Presented by Victor Yermak, CEO of Dataerion, Bulgaria
Claim assessment in crop insurance is a time- and cost-consuming process, which is also subject to fraud and the human error. In our workshop we will demonstrate how the use of aerial images obtained with a UAV allows not only to significantly speed up this process, but also to save money on payouts, due to more precise loss estimation, and eliminate the human factor and opportunities for fraud. We will also share our perspective on how drones will transform the process and procedures of agro insurance in the near future. In the next 5 years, drones will be incorporated in crop insurance products, making underwriting and claim processing objective and fraud-free. Aerial big data, collected by drones and stored in the cloud, will allow the prediction of insurance events and more precise calculation of premia.
Continuously Variable Bandpass Filters for Hyperspectral Imaging
Presented by Delta Optical Thin Film A/S. Denmark
Hyperspectral imaging has been used in applications such as satellite imaging, air reconnaissance and other not overly price sensitive markets. Classical HSI cameras use prisms or grating as dispersive elements. They are bulky, sensitive to misalignment and very expensive. Alternative approaches makes HSI attractive for use with drones, for example in precision farming and other applications. Continuously Variable Bandpass Filters for mid-size and full-frame CCD/CMOS sensors allow the design of very compact, robust and affordable HSI detectors that are ideally suited for drones and UAV.
Visual Navigation for Flying Robots
Presented by Dr. Kabir Mohammed, Project Artemis, India
Indoor and outdoor navigation for small UAVs like quadrotors is still far from being a solved problem and most research and demonstration of visual navigation solutions have been conducted on traditional CPU architectures. Due to high computation demands of a full vision-based navigation stack (depth extraction, odometry, mapping, planning, and control) a heavy and often power-hungry onboard computer is needed to simultaneously run all the tasks onboard. For this presentation, we demonstrate a quadrotor UAV equipped with Nvidia's Jetson TX1 embedded GPU compute module and high-speed stereo vision system, running our complete navigation stack onboard, at a tenth of the weight and power consumption of our previous generation vehicles running Intel processors. Our compact quadrotor is capable of tight, fast maneuvers and safe GPS-denied indoor hover, with onboard sense-and-avoid and precision landing.