AT 309: Lab 2, The Digital Transformation

 Introduction

    Big Data, Cloud computing, Internet of things (IoT), and Artificial Intelligence (AI) are all the buzz words of this past decade, but what do they really mean and how will they impact uas usage. Uas is related to all of the different aspects of the information age, as the goal of many commercial uas missions is to collect information.  

    The digital transformation drives uas development through the creation of different uas and parts for uas. Big data drives the development of uas that are able to carry different sensor platforms to collect various types of data. Cloud computing is driving the development of diffrent technologies like unmanned traffic management (UTM). IoT is also allowing for uas to begin to communicate with each other to allow for UTM. AI is now driving the development of uas that are able to use visual navigation for beyond visual line of sight operations (BVLOS). The digital transformation is also driven by uas, as the diffrent application requires diffrent solutions. Uas now provide new abilities to gain data that was never before collected, this allows for more data to be collected than before, 

Internet of Things

UAS that use IoT currently use it for many diffrent reasons, but a few that stand out are for Unmanned Traffic Management (UTM). UTM is going to have a massive impact on the industry with the next few years as it is implemented with a remote ID. The internet of things relates to UTM as it will be how the drones will likely communicate with each other, as well as accessing a cloud-based flight plans. IoT will allow for operations in airspace with a higher traffic density locations, and could potentially reduce the need for human operators of deliver uas as they can communicate with each other. 
An implication of using IoT for UTM is that there could be malitious attacks on the system. Someone could send up a drone that brodcast signals of hundreds of uavs in an area and black out the system. Another implication is that all the uas using UTM would constantly be brodcasting their positon and anyone looking to attack the drone or steal packages that were delivered would know exactly where they are located if they could get into the UTM system. 

-1 https://www.iot-now.com/2019/08/02/97962-innovative-ways-use-iot-enabled-drones-near-future/

-2 https://www.computer.org/publications/tech-news/research/flying-iot-toward-low-power-vision-sky

3- https://www.gsma.com/iot/connectedskies/

4-  https://www.gsma.com/iot/wp-content/uploads/2020/05/Telefonica-Drones-CV2X-Road-Hazard-Warning-Case-Study-Final-1.pdf

Cloud Computing 

Uas can use cloud Computing for many different reasons, but the most prominent use case I see is live inspections. Having the ability to have a UAV uploading data while in flight, and having it processed while the UAV is still in the air allows for easily looking at things again quickly. This allows for getting a closer inspection and components that were flagged as issues when the cloud processed the data. This leads to increased efficiency in the inspection process.

One implication is the security of the cloud, as all the data collected could be accessed by anyone from anywhere. So lots of different inspections could not use the cloud, like power grids or other critical infrastructure. This gives cloud-based computing for live examinations some limitations on uses and the ability to operate in different industries. 

-2 https://www.researchwithnj.com/en/publications/mobile-cloud-computing-with-a-uav-mounted-cloudlet-optimal-bit-al-2

-3 https://www.researchgate.net/publication/338673494_Mobile_Edge_Computing_in_Unmanned_Aerial_Vehicle_Networks

-4 https://www.aquilinedrones.com/vision-brief/

Big DATA

Big Data is used in many of the drone applications, as the majority of current drone missions have some data as the product. For some precision ag applications, the drones can collect as much as 60 gigabytes per flight, which is a ton of data to store, and process. Many operations may be flying ten or more fields a day and generating over half a terabyte of data. Drones also capture many different types of data from geospatial information, LiDAR, RGB, Hyperspectral, and even thermal.
This creates some challenges and implications when managing the data, as no current software can handle all the different information that needs to be processed by various apps. This creates some issues as having lots of data to process, but not being able to process it all in the same place, could lead to errors in some of the outputs. Also, the amount of data can affect the time it takes to process the data, which could lead to flying a location again before the data has been processed and analyzed. 

-1 https://www.forbes.com/sites/colinsnow/2019/02/06/what-every-cio-needs-to-know-about-commercial-drone-data/#7299b62489ba

-2 https://www.droneblog.com/2020/02/05/how-drones-are-transforming-big-data-analytics/

-3 https://www.droneii.com/drone-data-analytics

-4 https://quantumtechhd.com/blog/2020/02/20/from-napa-valley-to-silicon-valley-how-drones-and-big-data-are-shaping-the-wine-industry-for-the-next-generation/

Artificial Intelligence 

Drones and AI are used in many different uses together, from Vision-based navigation to augmented railway inspection. One of the most exciting ways AI is being used with UAS currently is to achieve see and avoid capabilities for BVLOS waivers. The Casia system by Iris Automation was approved for flying BVLOS, and that gives drones a vast benefit allowing for easier operations for pipelines and other similar missions. AI is also being used in Skydios products to help create a 3d map around the drone while it is flying to ensure it does not run into obstacles. Both of these uses of AI to augment drones' flight capabilities will have an immense benefit to the applications of uas. 
Some implications of using AI in UAS, are that currently many of the algoritims have not been developed yet to fully optmise the sensors onboard both the skydio and the Casia. This could lead to the drones making the worng decision when they come into a situation that they havent encountered or been trained on before. To solve this issue, the drones would need to be tested more and their vision systems would need to be optmised for other senarios. 



Comments

Post a Comment

Popular posts from this blog

Setting up a vtol in mission planner

Image
Introduction Setting up a vertical take off or landing (VTOL) uav is one of the more complex aspects of mission planner, for programming a pix hawk flight controller. The vtol that will be set up in this blog is a 2.5 meter wingspan, custom quad rotor, with all four motors tilting uav. Figure 1. A screen capture of the firmware installation page of mission planner  To begin install arduplane on your pixhawk, using the install firmware page in mission planner, figure 1 shows the pop up window that should appear. Next once the firmware is installed go through each of the settings of the mandatory setup, including the accelerometer calibration, compass calibration and the radio calibration, but skip the servo output for now. The next step is going to the full parameter list under the configuring and tuning tab, and enable Qplane, which stands for quadplane, and allows for all the vtol settings to be shown. Then the frame style and setup has to be configured, these have t...
Read more

DoakBurn (Again)

Image
 Introduction The goal of this lab was to use ArcGIS Pro to view the various band stacks of orthomosaic imagery and a normalized difference vegetation index (NIVD). The data was collected by Dr.Hupy, William Weldon and Zack Miller, and the data was of a controlled burn with multispectral cameras. Methods The methods of this lab was to look at the areas that were burned and compare them to the areas around them that were not burned. This could be done with RGB, or band stacking for the imagery, which allows the ability to see things that are not able to be seen with the human eye.  Metadata from the Flight Vehicle: Bramor PPX Sensor: Altum Flight Number: 2 Takeoff Time: 12:18 Pm Landing Time: 12:35 Pm Altitude (m): 121 Sensor Angle: NADIR Results  The data collected with the band stacking shows the differences between the pre-burn and post-burn data. Figure 1,2,4,5,6,9 are in a 5,3,2 band stack, meaning the red represents near-infrared, the green represents th...
Read more

Designing a Vtol Mechanism from scratch

Image
Introduction A project that I have been working on needed a Vertical takeoff or landing (VTOL)  tilt mechanism for the the front 2 motors, so here is how I went about designing and testing it. It can be challenging to hand launch a twin motor plane as you have to worry about both prop disc areas, while managing controls, and adding a vtol system can allow for operations where a wheel based takeoff is not a possibility  The specifications of the propulsion system are a Emax 2213-935KV brushless motor, that spins a 8045 prop, with a spider 20apm opto esc, using a 4 lithium polymer cell battery. This power systems is typically used in quad copters such as a dji flamewheel 450. The servos for tilting the motor varied depending on the design of the tilting mechanism. Figure 1. A dji flamewheel 450 quadcopter, with a propulsion system similar to the VTOL's system Goals  The goals of this project was to be able to develop a vtol tilt system for a uav that ...
Read more