Since Amazon announced the testing of drone deliveries (link resides outside of ibm.com) nearly a decade ago, commercial drones have continued their flight across a variety of industries. Organizations around the world deploy commercial drones for deliveries or to gather video or images with an onboard camera. Drone inspections are already popular in several industries, but commercial drone usage received a boost with the recent announcement (link resides outside of ibm.com) that the UK is set to become the world’s largest automated drone superhighway in two years.
The European Union Aviation Safety Agency defines an autonomous drone as “able to conduct a safe flight without the intervention of a pilot […] with the help of artificial intelligence, enabling it to cope with all kinds of unforeseen and unpredictable emergency situations.”
If drones can use artificial intelligence (AI) to determine when to take off, which direction to fly, how to deal with external factors and how to return once the mission is over, there will be less need for pilots or drone operators.
Many countries are drawing up regulatory frameworks for low-altitude traffic management to accommodate the future of drones. This framework will cover roles, responsibilities and protocols to share data as part of drone operations. In the U.S., federal agencies are creating Unmanned Aircraft System Traffic Management (UTM). In the UK, the Civil Aviation Authority (CAA) is working toward something similar.
Just like road vehicles, identification of a drone is one part of the requirement for UTM, and the FAA in the US already requires all drones to be identified. There are also plans to include Remote ID for drones that will provide identification and location information that others can obtain.
In the U.S., a drone operator is legally required to have visual line of sight (LOS) to the drone. To enable large-scale commercial drone usage like the UK’s superhighway, the regulatory framework needs to allow for “beyond visual line of sight” (BVLOS) piloting. Some countries with large amounts of remote locations, such as Iceland, Norway and Sweden, have already enabled BVLOS as means of supporting isolated communities.
Frost & Sullivan defined drone-in-a-box in a 2018 report on drone delivery (link resides outside of ibm.com): “Sensor, communications, hardware and software technologies have advanced to the point that innovative companies can offer semi- or fully autonomous vehicles that can be automatically launched and recovered to base stations or enclosures. These solutions are often referred to as ‘drone-in-a-box’ because structures are required to recharge, protect, or recharge and protect drones between mission legs or between different missions.”
Today many companies invest in drone-in-a-box as a mainstream component of future industrial drone operations. At least two other features will become part of this component as 5G becomes the connectivity infrastructure:
When adopting drone monitoring technology into an enterprise, it is vital to create a plan that maximizes efficiency. By combining drone-captured images and videos with these seven technologies, enterprises can automate workflows and improve the productivity of their business operations.
1. Storage for imagery
Drones capture high-resolution videos of the infrastructure or asset that needs to be monitored during a drone inspection. In general, a 4K-resolution video taken at 30 frames per second needs about 760 MB of storage for every minute recorded. Recording drone footage for even just a few days can add up to terabytes of storage. Therefore, enterprises have realized cloud storage is a cost-effective way to store and back up footage for later analysis.
2. Image stitching
Stitching videos or images together allows companies to see the full structure of an asset rather than spending time and money to monitor footage for changes. This is particularly useful in large structures like bridges or construction sites. This efficient tool helps managers identify issues and observe the pace and progress of solutions.
3. Other relevant datasets to support analytics
Initially, analytics may simply compare the change in the asset over time. When additional aspects of data are included, planners can achieve richer interpretation, analysis and pattern discovery. For instance, when data on the rate of rusting, types of rust, types of structural damage from rust and types of weather patterns are used with drone images of a bridge, it assists in predicting areas of potential structural damage versus superficial changes.
Urban planners can quickly complete planning activities when existing data of nearby topography, buildings, roads and infrastructure are used along with drone images of a particular area. Similarly, the use of weather data such as temperature, wind direction, potential for rain and past data of wildfires may help experts monitor and identify a change more quickly than with just the drone images.
4. Finding patterns with people
A bridge inspector who has spent 20 years on the job is able to look at a particular crack or concrete spalling and immediately tell if it is a cause of concern or not. The expert inspector considers depth, color, location and other factors to make this assessment. Human expertise and knowledge help identify patterns to create relevant datasets that can train computers.
5. Computer vision
Computer vision trains AI to identify the same patterns an expert inspector would see. For example, by training computers to identify imagery of a variety of concrete spalling, AI can automatically monitor images of the bridge to locate defects. This complementary drone solution eliminates the need for people to go through hundreds of hours of drone footage.
6. Rules and decision making
Once people identify a set of patterns in the imagery and teach AI to do the same, organizations can set up business rules. For example, if a particular type of structural defect is found on the roof of a house, run the drone inspection again in x months to see if there is a change. In a more critical scenario, such as if the construction blueprint and actuals are out of sync, a variety of departments will be prompted to act immediately.
7. Digital twins
Drone mapping of a building or set of structures, such as a telecommunication tower, can help create a digital twin. This digital twin can then help companies understand how the physical asset is functioning based on real data. For instance, with a digital twin, organizations can study and predict the ways a hurricane could impact the position of mobile antennas on a telecommunication tower. These predictions can inform engineers of individual towers that will need maintenance in advance of such an event. Moving from reactive to predictive maintenance can save organizations from downtime and support greater efficiencies of business operations.
Automate inspections and reducing manual effort with drones will drive significant growth in the coming years. The global drone services market is projected to grow (link resides outside of ibm.com) from USD 9.56 billion in 2021 to USD 134.89 billion by 2028 at a CAGR of 45.9% in forecast period 2021-2028. As this market grows, these industries will demand more specialized drone services.
Learn how IBM automation services can help maximize your business operations.