An inertial navigation system (INS) is the key enabler for stable UAV navigation when the GNSS signal is degraded or unavailable — and that happens a lot. High-rise buildings, dense vegetation, electromagnetic emissions from nearby structures, or targeted UAV jamming frequently cause signal loss and costly equipment loss. 

That shouldn’t be your case, however. Recent advances in sensor fusion and artificial intelligence (AI) enable drones to autonomously navigate complex droughts in GPS-compromises and denied environments. 

Here are the top four AI navigation solutions for UAVs, available on the market right now. 

1. Bavovna 

Bavovna offers a versatile AI navigation kit, compatible with multi-rotor, VTOL, and fixed-wing models. The low-SWAP system includes IMU and Al-powered flight control, encased in an EMI-shielded, carbon case (which has been field-tested for reliability). For extra protection, SIGINT RF modules can be added to the INS to identify and overcome EW/EM threats. 

The Airtower use case needs to be covered.

Bavovna H-INS got a proven 0.85-meter deviation of single-point positioning without any GPS, RTK, and optical navigation on board, at altitudes 500 meters with a wind up to 18 m/sec.

Unlike other INS, Bavovna’s solution can provide complete autonomous navigation in GNSS-denied environments using a proprietary sensor-fusion AI algorithm. The algorithm is already pre-trained on standard sensor data (multivector aerial speed, multi-vector air flow, aileron feedback, barometer, compass, gyroscope, and magnetometer) to ensure high positional accuracy and situational awareness. Then further Bavovna fine-tune the model, using approximately 100 hours of flight data from a particular airframe to ensure the best possible performance. 

Bavovna H-INS stays sensor agnostic and AI-driven sensor fusion can be easily extended to integrate extra navigation aid systems, lidars, or computer vision. For example, if you also want to use simultaneous localization and mapping (SLAM) for mapping the terrain or to use object detection for your applications.

The hybrid approach currently allows Bavovna to provide ultra-low end point positioning error (EPPE) of under 0.5% at a range of 30 km / 18.6 miles — a substantially longer range than non-AI INS and radio-based navigation systems can deliver. 

Competitive Strengths 

• No GPS, RTK, RC ground, or network signal is required to pilot UAVs using the Bavovna AI navigation system to perform autonomous take-off, Return-To-Home, and landing.

• Sensor fusion algorithm fine-tuned for each customer’s flight gear and application scenarios.  

• Modular, scalable unit design with low power consumption, protected with composite radio shielding.

2. George Autopilot 

Source: uAvionix

George autopilot system by uAvionix is a robust UAV navigation system, based on certified DAL-C hardware and CubePilot autopilot architecture. Both proved their mettle in a range of enterprise UAV operations. 

To power safe flights, George 2 replies on data from the IMU units and military-grade geomagnetic sensors. You also have the option to add detect and avoid (DAA) protection by adding pingRX Pro or ping200X Mode S Transponder. On the downside, George doesn’t use SLAM or odometry to provide extra situational awareness, unlike Bavona.ai.  

Another advantage is that the entire navigation system weighs only 80 grams (2.8 oz). It’s also optimized to minimize power consumption for longer flight times and hardened to withstand abnormal power conditions, lightning, and other magnetic interference. The system is certified according to DO-160G and MIL-810H, guaranteeing high resistance to environmental stress. 

Competitive Strengths 

• Engineered to meet aviation and military environmental standards and compatible with a range of UAVs, including larger VTOL and fixed-wing models. 

• George incorporates top-of-time GPS, C2 Radio, IMU, and military-grade sensing technologies, ensuring unprecedented accuracy and situational awareness. 

• Plug-and-play solution with an option to integrate additional avionics modules and different ground infrastructure.

3. Spatial FOG Dual 

Source: Advanced Navigation

Advanced Navigation is a long-standing leader in inertial navigation systems (INS), offering a range of Micro-Electro-Mechanical Systems (MEMS) and Fiber Optic Gyroscopes (FOG) INS/GNSS solutions. FOGs provide greater accuracy in measuring rotational movements and perform better in dynamic conditions (e.g., rapid maneuvers). They also generate less noisy measurements and require less frequent recalibration.

Spatial FOG Dual combines high-accuracy fiber optic gyroscopes, accelerometers, magnetometers, and a pressure sensor with a dual antenna RTK GNSS receiver.  Its EMCORE TAC-450 fiber optic gyro IMU, provides superior inertial data accuracy, surpassing the best MEMS technology.  The RTK GNSS receiver provides positioning accuracy of up to 8mm (0.3 in) and a timing accuracy of 20 ns.  It also supports post-processing kinematics (PPK). 

Similar to Bavovna, Advanced Navigation uses a pre-trained AI neural network sensor fusion algorithm to ensure smooth aerial navigation, even in challenging conditions. The company says its algorithm is 10X more accurate than a traditional Kalman Filter. This allows for extended reckoning, even without GNSS. 

The navigation unit is based on a safety-oriented real-time operating system, with all software designed with high fault tolerance in mind. Hardware is rugged and environmentally protected, in line with IP67 and MIL-STD-810G standards. 

Competitive Features 

• Horizontal position accuracy of 0.01 m with RTK or Kinematica PPK, and velocity accuracy of 0.005 m/s.

• Gyroscopes with a bias instability of 0.1 °/hr and accelerometers with a bias instability of 15 µg. 

• Proprietary, pre-trained neural network sensor fusion algorithm that demonstrated strong results in the field. 

4. Honeywell Compact Inertial Navigation System

Source: Honeywell 

Honeywell Compact Inertial Navigation System (INS) is another great compact option (with a weight of 115 gr/4oz) that packs a punch in terms of hardware. The system includes tactical-grade inertial sensors, dual-antenna GNSS heading, RTK, and closed-loop integration with Pixhawk 2.1 — flexible autopilot. It can be also extended with extra data sources to support specific use cases. For example, you can combine it with a radar velocity system for extra precision or a third-party anti-jamming system for navigating in high EMI environments. 

In an RTK configuration, Honeycomb CINS delivers an ultra-low positioning error of 0.03/0.015 meters (and 2. Meters without RKT). The velocity error is just 0.02-0.04 m/s. It’s a great solution for applications where accuracy is critical.

On the downside, Honeycomb doesn’t use AI for sensor data fusion, unlike Bavovna and Advanced Navigation to provide a greater degree of autonomy and reliability in GPS-compromised environments.

Competitive Strengths:

• Compact INS offers high-accuracy output position, orientation, and velocity data, thanks to top-of-the-range hardware. 

• Redundant sensors and ruggedized system design lend extra safety to flight missions. 

•  Easily extendable with extra Honeycomb or third-party navigation aids systems. e.g. velocity aiding systems

TL: DR: Comparison of the Best INS for UAVs  

Here’s how the top solutions stack in four key areas: customization, SLAM support, non-GPS navigation, and AI sensor fusion. 

	Customizable IMU integrations	SLAM support	Non-GPSnavigation	Custom AI sensor fusion algorithm
Bavovna AI Navigation Kit	✔️	✔️	✔️	✔️
George Autopilot from Avionics	✔️	❌	✔️	❌
Spatial FOG Dual from Advanced Navigation	✔️	❌	✔️	✔️
Honeywell Compact INS	✔️	❌	✔️	❌

Mining is critical for a steady supply of energy resources and rare earth metals for technological advancements. Yet, it’s also a tough business with enduring operating conditions, safety hazards, and stringent regulations.

Many operating processes require aerial visibility – drones have become indispensable for land surveying, risk assessments, stockpile management, and an array of other use cases.

3 Use Cases of Drones in The Mining Industry 

Since 2016, 70% of large mining companies have gone from using drones for fringe cases to fully integrating the technology into surveying, engineering, and monitoring workflows.

Learn how leaders are using drones to optimize operations, cut costs, and increase employee safety.

Streamlined Land Surveying

Mines need land surveying services constantly and in large quantities. Aerial monitoring ensures safe on-site operations, resource assessments, and expansion planning.

Traditional land survey methods like triangulation, tachymetry, chane and tape surveying are time-consuming and require a large on-foot workforce. Surveying personnel at an active mine can interfere with operating equipment, leading to costly downtime. Larger projects like pit-to-port road construction or new mineral exploitation require coverage of large distances. 

Drones are a more time- and cost-effective alternative to conventional land surveying methods. The best fixed-wing and quadcopters with a gas-electric powertrain can stay in the sky for several hours, covering 250-1000+ acres in one flight.

The selection of land-surveying drone payloads available is impressive: HD RGB, oblique, thermal, and multispectral cameras, LiDAR sensors with centimeter-level positioning accuracy, magnetometers, and photogrammetric cameras. Thanks to advances in aerial autonomous navigation, the best drones for mining now have automated data capture modes and can generate 3D environment maps for better situational awareness.

Roughly 83% of mining companies use drones for mapping and surveying, including the Baorixile Open Pit Mine. With a 50 square kilometer mining license area and 640 million tons of coal reserves, the mine is crucial for the local market. However, harsh environmental conditions — snow, sub-zero temperatures, icing — make land surveying missions challenging. Likewise, naturally occurring electromagnetic interference (EMI) hampered drone navigation, causing GPS signal loss and IMU instability. So instead of sending personnel, the operators switched to using Jouav CW-25E UAV with LiDAR technology. 

The drone collected 125 times more data points per square meter than conventional RTK surveying, with under 5 cm accuracy. Data acquisition times were reduced from 13 days to 2 — a 6.5X increase in efficiency. Personnel no longer had to endure the harsh climate, controlling the drone from a parked vehicle.

Stockpile Management

Stockpile management is another labor-intensive task in mining operations. Accurate volume and mass calculations are challenging due to extreme heights and irregular shapes (which also change frequently). However, ensuring structural stability is crucial to prevent accidents. Stockpile collapses and nearly avoided accidents trigger regulatory investigations and fines.

With drones in mining, companies can produce aerial terrain models of their inventory and keep track of stockpile changes over time to ensure safe and effective operations.  Ferrexpo Yeristovo Mine regularly employs drones to conduct land surveys, create up-to-date stockpile maps, and minimize risk to personnel. 

DroneUA helped Yeristovo mine operators create a 3D model of an 82-hectare / 202-acre open pit, collecting data from 410 meters/1345 feet below ground. The team collected over 1,000 data points for 2D/3D models. 

The second major project involved mapping an ore stockpile. The team created pre-planned navigation routes to automate data collection and ensure high data fidelity. Stockpiles occupy large areas with uneven terrain, making hand-held tools less effective. Drones, equipped with photogrammetric cameras, allow greater precision and keep personnel out of dangerous areas. In both cases, drone-led data collection took 90% less time than traditional methods.

Mineral Exploration 

Drones in mining provide a new vantage point for exploring new mineral sites, as well as resource evaluation and subsequent excavation planning. Thanks to advanced onboard sensing technologies and specialized payloads (e.g., an echosounder, metal detector, magnetometer, etc), drones can be used to perform geological mapping missions at faster speeds. For example, identify ore bodies’ spatial distribution or detect tramp metal in stockpiles to prevent costly crusher outages during the excavation phase. 

Yet, drone deployments on mining sites can be challenging due to high EMI levels. Some minerals (e.g.,  magnetite or pyrrhotite), as well as mining equipment like proximity sensors or high-voltage power cables, can interfere with the navigation systems. Bavovna developed an AI-driven hybrid navigation kit for VTOL, Fixed Wing, Multirotor, or Quad to safely cruise in high EMI environments. With Bavovna’s AI navigation kit drones can maintain ​​99% positional accuracy in high EMI/GPS-denied environments and reliably follow the original flight path despite the interferences. The navigation unit is housed in an EMI-protected box, attenuating interferences at 92dB per mm. 

Unlike computer vision-based systems, which require substantial computing resources, Bavovna’s solution relies only on device sensor data, streamed into a lightweight AI model for fully autonomous operations.

Underground tunnel mapping is another labor-intensive task at new mining sites. Irregular tunnel shapes and confined spaces complicate equipment placement and safety. Physical obstructions and geological interferences render traditional surveying methods ineffective. High dust and low lighting limit the usage of optical surveying tools.

Confined space drones have emerged to address these challenges. Featuring a rugged, caged design and advanced obstacle detection, the best indoor drones can cruise through narrow passages and access restricted areas to collect mapping data. Elios 3 from Flyability uses LiDAR and computer vision technologies to generate real-time 3D-environment maps for piloting in GPS-denied environments.

Similar to above-ground land surveying, indoor drones create operational efficiencies and savings. At Glencore Kidd Mine in Ontario operators used Elios 3 to eliminate time-consuming drilling and expensive equipment movement. Within 15 minutes, the team inspects flagged areas and gains video footage and 3D maps of underground conditions.

Conclusion

The usage of drones in mining has grown at a massive clip over the years and for some good reasons. Aerial surveillance capabilities, coupled with a great array of payloads, help miners conduct faster site assessments, survey underground tunnels, and improve asset management lifecycles. 

Thanks to advances in onboard sensing capabilities and new navigation technologies like Bavovna’s kit, drone flights have also become much safer even in GNSS-denied and tough environmental conditions, paving the way for even more deployment scenarios. 

Global Navigation Satellite Systems (GNSS) systems such as GPS have been a staple technology in land, maritime, and aerial navigation for decades. Super useful? Absolutely. But, GNSS has its fair share of downsides too.

Weather, buildings, natural obstacles, and some electronic systems cause inevitable signal degradation and latency in signal acquisition. Heavy reliance on a network of satellites and ground stations, attractive targets for physical or cyber-attacks, also raises rightful security concerns. For UAVs and ROVs, signal spoofing, jamming, and other forms of electromagnetic warfare (EW) are also a problem. 

For many mobility scenarios signal loss or high latency is unacceptable, even more so if we’re to advance to full autonomy. But if not GNSS, what other technologies can provide reliable positioning and navigation data? A couple of options are on the table. 

Sensor Fusion with AI 

Every commercial UAV is equipped with a set of standard sensors, such as an accelerometer, gyroscope, compass, airflow sensor, and altimeter, for situational awareness. More advanced enterprise models may also include LiDAR distance sensors or ultrasonic sensors to detect proximity to obstacles.

Combined, these provide real-time information on the drone’s location, orientation, and movement, and a GPS/GNSS receiver tallies this with geo coordinates, which allow the drone to follow a pre-planned flight route. When GPS is down, the best models will hold position or attempt to automatically return home. 

Yet, recent advances in sensor fusion also enable autonomous navigation scenarios. Instead of the GPS signal and pilot commands, the drone can rely on data from its Inertial Measurement Unit (IMU) and AI algorithms to safely continue the route. By integrating and processing sensor data streams on the device, AI pilot models can provide precise situational awareness to drones and full autonomy. 

Bavovna Navigation Kit includes an 800gr/28 oz onboard edge devices and SaaS access to a fine-tuned AI Hybrid navigation model, pre-trained on historical data from the available sensors. Already implemented on eight UAV platforms, ranging from fixed-wing and VTOLs to multi-copters and FPVs, the system maintains an End Point Positioning Error (EPPE) of under 0.5% on complex trajectories of up to 30 km or 18.6 miles. 

Intended for dual use, Bavovna’s hardware sits in an EMI-protected case and can be further augmented with a SIGINT RF module for bypassing EW and EM obstacles. AI pilot system, not only enables more reliable autonomous navigation but also improves obstacle detection, UAV routing, and ultimately operating efficiencies. 

LiDAR-Based SLAM Systems

An alternative approach to sensor fusion is the Simultaneous Localization and Mapping (SLAM) technique. While sensor fusion primarily relies on IMU data, SLAM algorithms use camera and LiDAR data to general a real-time map and localize the piloted system in a GPS-denied environment. Opposed to cameras, 3D LiDARS provides an immediate point cloud of the environment, eliminating the latency. Data processing software has to be installed both on the flight controller and the onboard computer. 

SLAM algorithms like LOAM and Cartographer have demonstrated great performance during scientific experiments in terms of trajectory execution and landing errors. Commercially, Elios 3 from Flyability and Hovermap series from Emesent, and Scout 137 from ScoutDi rely on SLAM for indoor navigation in GNSS-denied environments (with an added bonus of advanced mapping scenarios). 

The downside of photo-SLAM, however, is high resource consumption: CPU, memory, and processing, especially for photo-realistic mapping scenarios. This, in turn, requires heavier and more expensive onboard units, which increase the system operating costs. Likewise, high resource consumption results in faster battery drainage on smaller UAVs, undercutting the precious flight time. Although some recent advancements in processing frameworks help optimize resource usage. 

AI Pilots: Navigation Guided by Magnetic Fields 

Commercial and military aircraft are also increasingly relying on AI-assisted navigation, oftentimes powered by hybrid INS/GPS signals. For security reasons, however, the military is looking to progressively minimize reliance on satellite networks.  

The US Air Force has been continuously testing different AI pilots to autonomously pilot fighter jets. Technologically, we’re already there — AI systems successfully piloted an F-16 in a dogfighting exercise over California’s Edwards Air Force Base in May 2024. But there’s always room for further improvements. 

The Air Force research team is working on a new AI navigation pilot to potentially navigate the plane using the Earth’s magnetic fields. So far, such scenarios haven’t been feasible as the aircraft generate too much electromagnetic noise, interfering with onboard magnetometer measurements.

However, a recent model, tested on C-17, showed very promising results that could lead to “tactical airdrop quality” and a potential solution to “things we can do, should we end up operating in a GPS-denied environment.“, according to Col. Garry Floyd, director of the Department of Air Force-MIT Artificial Intelligence Accelerator program.

While we may not be there yet, widespread autonomous AI piloting without GNSS is no longer a question of “if”, but rather “when”, especially for unmanned aerial vehicles.

Patrolling, land surveying, topography mapping, search and rescue missions — drones have become a staple tool for the AI border security forces. The EU border agency Frontex deployed drones successfully in Greece and Malta to monitor illegal migration. In 2023, the agency spent another €144 million on new drone purchases to support wider deployments. The US Department of Homeland Security also purchased over $1.8 million of drones for border patrolling last year. 

Compact, cost-effective, and easily deployable, drones are also becoming more sophisticated, featuring pre-trained AI models for navigation, object detection, and land surveying. 

Combining Drones and AI for Border Security 

Drones offer many advantages to AI border security patrol — rapid coverage of wider areas, more effective maritime monitoring, and greater cost-efficiency compared to deploying helicopter flights. The new generation of AI-powered drones is also capable of supporting even more advanced security and surveying use cases. 

Navigation in GPS-Denied Environments

Border patrolling drones are an effective deterrent to criminals contemplating smuggling operations or illegal border crossings. On the downside, drones are prone to signal jamming. Anti-drone guns can be purchased for several hundred dollars online, often without any ID required. Criminals are often taking advantage of that. Jamming is also a major issue during military conflicts or security training operations conducted in hostile environments. 

US manufacturer Bavovna developed an AI-powered navigation system, for effectively operating in GPS-denied environments. The system combines modular hardware and AI technology to deliver precise and dependable navigation even in GPS-denied environments amidst aggressive electronic warfare scenarios.

By combining ES capabilities with Sensor Fusion AI navigation, Bavovna’s solution ensures dependable drone operations even under heavy signal interference, jamming, and meaconing.  Pre-trained on real flight logs in GNSS-enabled and denied environments, the onboard AI system can navigate the drone along the pre-programmed flight plan using real-time sensor fusion. During recent field tests featuring a Radiobird Defender VTOL, Babovna’s AI navigation system helped pilot over 18 miles (30 km) of complex positioning without GNSS connectivity with an end-point positioning error of 0.42 – 0.63%. 

Moreover, Bavovna recently presented a new EW-resilient, low-SWAP signal intelligence (SIGINT) capture solution. The drone-mounted system can detect the location of radio-emitted sources in a range from 500MHz to 12GHz during a fully autonomous flight, even in GPS-denied environments. The system can provide coastal guards with greater situational awareness, enabling the detection of communication between the mainland and unauthorized boat traffic. 

Automated Patrolling and Intruder Detection

The latest drones performing AI border security functions are equipped with advanced computer vision systems and thermal cameras for a better object, vehicle, and human detection, even in poor lighting conditions. The pre-trained computer vision algorithms can detect heat signatures of people with high accuracy, enabling faster response from security forces. 

For example, the Skydio X10 drone is pre-trained to detect and auto-follow people, vehicles, and other objects, allowing border officers to concentrate their attention in the right areas. Skydio NightSense algorithm also helps navigate drones more effectively in low and no-light conditions. Onboard sensors, paired with AI navigation algorithms, also support automatic obstacle detection and collision prevention. The algorithm also automatically reduces obstacle avoidance margins when piloting through narrow spaces — a handy feature for running environment scans indoors. 

Land Surveying and Mapping 

Drones as AI border security also help border forces collect geospatial data to map the border terrain better and inspect the current infrastructure in place (if any) for a fraction of the cost of chartered flights. 

Details scans help determine new reinforcement areas, close gaps, and ensure all protective infrastructure is in good shape without conducting on-foot inspections. 

Anafi AI from Parrot has a survey-grade accuracy of 0.46cm/px GSD at 100ft (30m), thanks to a 48 MP 1/2” CMOS sensor. Developed primarily for photogrammetry, Anafi AI includes several AI-assisted flight modes for creating (and flying) 3D asset scanning missions. During each flight, the AI technology continuously builds and updates an occupancy grid to ensure safer navigation. The algorithms also determine the best flight trajectory to avoid obstacles. 

Using AI-powered drones responsibly in border operations

Although drones can substantially increase border safety, their usage also raises some rightful concerns about privacy. 

The technology can be abused by law enforcement and used outside the authorized areas. 

A 2020 NGO investigation found that US border patrol drones were found flying miles away from the country’s borders. In February-March 2020, one border patrol UAV conducted 20 flights in Panama’s airspace. Countless occasions of border patrol drones hoovering miles away from the designated border areas have also been recorded. 

Such detours are problematic as they may be breaching unknowing citizens’ privacy. Border guards have also been found to use drones to collect and share non-immigration-related data with law enforcement in border communities, according to the flight logs. 

AI-enabled drones must be used responsibly within authorized areas only and for a select number of approved use cases. Border forces must also maintain transparent records about the type of data being collected and how it’s being stored and used. Doing so is essential to protect the citizens’ rights to privacy. 

Aircraft autopilot systems have been around since the early 20th century. Modern autopilot systems effectively support pilots at every phase of the flight, enabling greater safety, efficiency, and comfort. Unmanned aerial vehicles (UAVs) have even more advanced navigation and safety systems. 

But how technologically far are we from achieving full autonomy? Given the latest advances in sensor fusion, computer vision, deep and reinforcement learning, reliable autonomous navigation systems will become a reality once we resolve the last cluster of challenges.  

5 Challenges of Creating Autonomous Navigation Systems for UAVs 

Autonomous UAVs have many great use cases — from urban package delivery to automated industrial asset inspections, border patrols, or land surveying missions. What prevents the technology from going mainstream is the reliability requirements. Autonomous navigation systems must be ultra-safe with minimal possibility of error. To make that happen, industry leaders are working on solving the next five problems. 

Dynamic Environmental Awareness 

UAVs need continuous spatial awareness about flight conditions and obstacles to operate autonomously without posing risks to people and infrastructure. Modern drones already include advanced sensing capabilities, ranging from HD cameras to LiDAR and optical flow sensors. Computer vision and navigation algorithms can process all of these data points on-device to provide real-time environmental awareness to drones for autonomous operations. 

The Fly4Future team recently presented INEEGO — an indoor inspection drone with an autonomous navigation system. The drone can effectively glide through the premises using only a partially known map and adjust its path based on the data from onboard sensors to avoid obstacles. With INEEGO, pilots can seamlessly inspect AC pipelines, carrier beams, and other industrial structures for signs of deterioration with little risk of collision. 

GPS Denied Environments

GPS has long been a bottleneck in UAV reliability. If the signal is down or unreliable (which happens often in dense urban areas), the drone loses all positioning navigation. Drone signals can also be jammed or spoofed, further affecting the safety of autonomous flights. 

Soundly, there are alternatives to GNSS connectivity. US manufacturer Bavovna developed a hybrid AI-powered navigation system for operating in GPS-denied/compromised environments. The company’s flagship product is a SWAP,  low-cost, modular solution, combining an onboard hardware processing unit and pre-trained AI algorithms to provide precise Position, Navigation, and Timing (PNT), crucial for autonomous operations. With Bavovna’s system, UAVs can fly fully autonomous complex missions, relying exclusively on onboard sensors like IMU array (accelerometer, gyroscope), airflow sensor, compass, and barometer, among others. 

Battery Management 

Drones have limited battery capacity. If an autonomous UAV runs out of charge mid-route and fails to safely land, that’s no good. So, researchers are evaluating different options for improving drone battery management. 

NTIS Research Centre, for example, created an experimental mechatronic system for automatic drone battery management. Droneport can autonomously swap batteries on UAVs without any human intervention.  Compact and easily assembled, the Droneport robo-arm can perform scheduled battery swapping tasks on drones, equipped with a specialized battery holding case with high accuracy. 

Self-charging drones are another actively explored option. Drones4Safety technology, developed in Denmark, allows charging UAVs using railway and power line cables. When a drone reaches a low battery status, an autonomous navigation systems navigates it toward the nearest overhead line for charging, using data from GNSS and EGNOS. On-board sensors also provide extra detection and navigation towards the nearest power lines. Several field trials have already proven the viability of such an approach. However, the team still needs to work on the systems’ accuracy to avoid potential damage to the power lines. 

Autonomous Take-Off and Landing

Present-day drones require a pilot to facilitate take-off and landing. In autonomous operations, drones will have to auto-locate suitable landing sites and ensure that no obstacles or humans are in the way of a safe takeoff/landing. Again, this problem requires improvements to current navigation capabilities and some upgrades to hardware design. 

Evolve Dynamics is working in this direction. The manufacturer recently showcased its 

Sky Mantis UAV can perform fully autonomous landing, loitering, and zonal position holds with high accuracy. The model relies on ground-based radar beacons communicating with a Sensoriis airside radar mounted on the Sky Mantis UAV, which is used to make decisions based on precision positioning data.

A group of Polish researchers, in turn, proposed a lightweight deep learning vision algorithm to support autonomous UAV landings and take-offs. It demonstrated near real-time performance on modern embedded GPU devices, and high safety and robustness in human presence detection and positioning error estimation. However, it’s yet to be tested in the field. 

Reliable Connectivity 

Autonomous UAVs with autonomous navigation systems will still require strong communication links with ground stations for localization and data exchanges (e.g., streaming video feeds, receiving updated flight plans, etc). Present-day communication ranges are limited to about 60 miles (35 km). Using lower frequencies allows higher ranges but limits the maximum data rate (i.e., results in higher latency). 

Software-defined networks (SDNs) for drones are emerging as a solution to this problem. With SDNs, the communication between the control layer and data link layer is commonly performed with OpenFlow protocol. OpenFlow protocol allows the network’s forwarding plane control over the network’s switch or router functionality. SDN design also improves the packet delivery ratio by tuning network speeds and UAV network security. 

The groundwork for enabling autonomous navigation systems for UAVs has already been substantial. In the coming years, we expect more solutions to move from the labs to the mainstream, ushering a new era of safe, autonomous aerial navigation. 

Machine learning and deep learning are staples in many industries. Ground transportation systems use predictive algorithms to optimize travel flows, predict congestion, and improve fuel usage. The sky’s the new limit. 

Impressive advances in AI navigation move from research labs to the mainstream, promising greater reliability, safety, and efficiency to aeronautics.

Inertial AI navigation for UAVs in GPS-compromised environments

GPS signal, necessary for most UAV operations, can be unavailable after a natural disaster or in military situations. Bavovna.ai, a graduate of the US Air Force Labs Mass Challenge acceleration program, is developing an AI-powered PNT navigation system for aerial, surface, and subsurface vehicles.

Designed for dual use, Bavovna’s inertial navigation system uses sensor fusion and pre-trained ML/DL algorithms to offer autonomous operations. Thanks to hardened core electronics, the system is resistant to common electromagnetic warfare threats. It’s also a low-SWaP solution with minimal power requirements and weight, suitable for UAV models and Class II aerial vehicles.

During trials, the Aurelia X6 Max multicopter could fly autonomously without remote control, GPS, or any other communication, collect location intelligence, and return to the home position. Bavovna AI navigation system aims for a 0.5% positioning error, even in complex journeys up to 30 miles (48 km). The team is working to extend the system use cases to cover Signals Intelligence, mine detection, automatic target engagement, and security surveillance.

AI copilots for commercial aviation flights

Modern aircraft have highly sophisticated autopilot systems to help pilots control altitude, course, thrust, and navigation. However, the onslaught of alerts and system interfaces requiring the pilot’s attention can be intimidating. NASA estimated that 34 different competing activities distract or preoccupy the pilots, ranging from communication to searching for VMC traffic. These can lead to human errors and dangerous consequences.

Air-Guardian, a new MIT CSAIL project, aims to improve the HMI of existing autopilot systems to ensure safer operations. The AI system uses eye-tracking to detect pilot distraction and “saliency maps” to understand aircraft behavior.

Based on a continuous-depth neural network model, the copiloting system can identify early signs of risks and take over the controls when needed. During trials, the Air Guardian system reduced flight risks and improved navigation success.

Advanced airflow traffic management to clear up congestion 

Unforeseen events like bad weather conditions adversely affect air traffic, causing congestion in a specific sector of the air navigation space. This, in turn, affects all network participants, leading to a cascade effect of delayed flights. 

Co-funded by the European Union and led by the Universita Ta Malta, the ASTRA project is short for AI-enabled tactical FMP hotspot prediction and resolution. The goal is to improve the prediction of air traffic congestion areas one hour in advance and suggest optimal resolution paths to traffic controllers.

The prediction algorithm will be trained on historical data (from 2019 to today) from the EUROCONTROL organization. The AI navigation system will provide FMPs with prescriptive scenarios to optimize flow management positions, ensuring safety, efficiency, lower fuel consumption, and environmental impacts.

AI has untapped potential in airborne navigation, and we expect more innovation in sensor fusion, AI-powered PNT, and aerial traffic management to happen in the next several years. 

GPS and INS are core components of global navigation systems, but both have inherent limitations. GPS is prone to signal blockage and jamming, as well as reflection on buildings and terrains, leading to signal distortion and poor position estimation. Signal accuracy also degrades at high speeds and rapid directional changes, making it less reliable for ultra-fast UAVs.

INS sensors are prone to drift due to poor initial calibration or sensor noise caused by mechanical vibration, temperature variations, cross-axis sensitivity, and wear. They also require periodic recalibration, especially for high-precision positioning.

Different machine learning and deep learning methods can improve GPS/INS signal reliability and quality—and, in some cases, even fully replace it.

The new era of Inertial navigation and AI GPS systems  

Artificial neural networks have already demonstrated strong results in real-time object recognition and signal processing in the automotive and manufacturing sectors. AI GPS in navigation systems are the next frontier.

Researchers tested different deep learning algorithms to optimize inertial sensing and sensor fusion tasks for land, aerial, and maritime vehicles. One group developed visual-inertial odometry (VIO), an integrated inertial and image sensor fusion technique based on deep learning to predict the UAS’s position with 0.167 Mean Square Error (RMSE).

Another group successfully used a convolutional neural network (CNN) to analyze noise information from the inertial measurement units using the Kalman filter, which improves the position and orientation estimation of the navigation system. Validation on real data from an autonomous underwater vehicle showed a 35.4% higher position accuracy than conventional methods.

AI GPS effectively compensates for individual sensor limitations by enabling rapid data processing from auxiliary sources. By leveraging an array of sensors and integrating AI algorithms, the vehicle can autonomously recalibrate, correct positional data, and operate smoothly in signal-compromised environments.

Advantages of AI-assisted navigation:

• Higher situational awareness and adaptability 
• Reduced dependence on satellite infrastructure 
• Lower vulnerability to signal jamming
• Better performance on complex terrain 
• Smarter collision detection and prevention 
• Improved coordination for drone swarms 

Real-world applications of AI sensor fusion for navigation 

At Bavovna, we’ve been developing a new AI-powered PNT navigation system to enhance existing inertial navigation systems of UAVs. By using AI for sensor fusion, Bavovna’s algorithms can safely pilot vehicles at high speeds and complex trajectories, even in GPS-compromised environments.

During a recent test, we successfully piloted a Radiobird Defender 001, a multi-weather VTOL, through its 30-km flying mission with an end-point positioning error of 0.42-0.63% on average.  

Sensor fusion from the onboard IMU array and airspeed provided navigation. We use sensors like a compass and barometer, with analysis performed on the edge using Bavovna AI Navigation Kit. We use a proprietary Kalman filtration algorithm and fine-tuned sensor fusion neural network trained on 100 hours of fight logs minimum.

SWaP efficient, the hardware kit is enclosed in a protective enclosure to minimize environmental and electromagnetic warfare impacts. The core electronics are also hardened with an EMI composite shield (-92 dBA/mm). 

AI algorithms and sensor fusion enable a higher degree of precision comparable to GPS and GNSS but with more reliability and resilience. This results in more efficient drone operations due to enhanced autonomy, obstacle avoidance, and route optimization, even in GPS-denied environments.