Autonomous aircraft

An autonomous aircraft is an aircraft which flies under the control of on-board autonomous robotic systems and needs no intervention from a human pilot or remote control. Most contemporary autonomous aircraft are unmanned aerial vehicles (drones) with pre-programmed algorithms to perform designated tasks, but advancements in artificial intelligence technologies (e.g. machine learning) mean that autonomous control systems are reaching a point where several air taxis and associated regulatory regimes are being developed. The global autonomous aircraft market was valued at USD 11.67 billion in 2024 and is projected to reach USD 48.34 billion by 2033, growing at a CAGR of 16.25%.

History

Unmanned aerial vehicles

Main article: History of unmanned aerial vehicles

Winston Churchill and others waiting to watch the launch of a de Havilland Queen Bee target drone, 6 June 1941

The earliest recorded use of an unmanned aerial vehicle for warfighting occurred in July 1849, serving as a balloon carrier (the precursor to the aircraft carrier) Significant development of radio-controlled drones started in the early 1900s, and originally focused on providing practice targets for training military personnel. The earliest attempt at a powered UAV was A. M. Low's "Aerial Target" in 1916.

Autonomous features such as the autopilot and automated navigation were developed progressively through the twentieth century, although techniques such as terrain contour matching (TERCOM) were applied mainly to cruise missiles.

Some modern drones have a high degree of autonomy, although they are not fully capable and the regulatory environment prohibits their widespread use in civil aviation. However some limited trials have been undertaken. In 2024, significant breakthroughs occurred with DARPA's Air Combat Evolution (ACE) program achieving the first AI-versus-human dogfight using real aircraft, where an X-62A VISTA (AI-controlled F-16) successfully engaged a human-piloted F-16 in September 2024.

Passengers

As flight, navigation and communications systems have become more sophisticated, safely carrying passengers has emerged as a practical possibility. Autopilot systems are relieving the human pilot of progressively more duties, but the pilot currently remains necessary.

A number of air taxis are under development and larger autonomous transports are also being planned. Joby Aviation has made significant progress with its eVTOL air taxi, completing Stage 3 of FAA's five-stage type certification process in 2024 and securing a $500 million investment from Toyota, bringing Toyota's total investment to $894 million. The company acquired Xwing's autonomy division in June 2024 to advance autonomous flight capabilities and plans to launch commercial air taxi services by 2025.

The personal air vehicle is another class where from one to four passengers are not expected to be able to pilot the aircraft and autonomy is seen as necessary for widespread adoption. Urban air mobility solutions are projected to become a $30.9 billion market by 2033, with autonomous capabilities being essential for safe operations in dense urban environments.

Market Economics

The autonomous aircraft industry has experienced rapid expansion across multiple sectors. The commercial aircraft segment is expected to dominate the market, with cargo aircraft currently representing 61.3% of market share due to high efficiency and lower risk in autonomous operations.

Regional market distribution shows North America maintaining leadership with the United States holding 80% of the North American market in 2024. The region benefits from substantial defense investments, with the U.S. Department of Defense planning to invest more than USD 2.6 billion in unmanned systems during fiscal year 2023. The Asia-Pacific region is projected to experience the fastest growth due to rising air travel demand and increasing adoption of autonomous technologies.

Control system architecture

The computing capability of aircraft flight and navigation systems followed the advances of computing technology, beginning with analog controls and evolving into microcontrollers, then system-on-a-chip (SOC) and single-board computers (SBC). Modern autonomous aircraft now employ advanced AI-powered flight management systems that integrate machine learning algorithms, computer vision, and sensor fusion for real-time decision-making.

Sensors

Position and movement sensors give information about the aircraft state. Exteroceptive sensors deal with external information like distance measurements, while exproprioceptive ones correlate internal and external states.

Non-cooperative sensors are able to detect targets autonomously so they are used for separation assurance and collision avoidance.

Degrees of freedom (DOF) refers to both the amount and quality of sensors on board: 6 DOF implies 3-axis gyroscopes and accelerometers (a typical inertial measurement unit – IMU), 9 DOF refers to an IMU plus a compass, 10 DOF adds a barometer and 11 DOF usually adds a GPS receiver.

Modern autonomous aircraft increasingly employ advanced sensor fusion combining LiDAR, radar, cameras, and inertial measurement units for comprehensive environmental awareness. Computer vision systems enable autonomous navigation and obstacle detection, while AI-powered sensors provide real-time adaptation to changing flight conditions.

Actuators

UAV actuators include digital electronic speed controllers (which control the RPM of the motors) linked to motors/engines and propellers, servomotors (for planes and helicopters mostly), weapons, payload actuators, LEDs and speakers.

Software

UAV software called the flight stack or autopilot. The purpose of the flight stack is to obtain data from sensors, control motors to ensure UAV stability, and facilitate ground control and mission planning communication.

UAVs are real-time systems that require rapid response to changing sensor data. As a result, UAVs rely on single-board computers for their computational needs. Examples of such single-board computers include Raspberry Pis, Beagleboards, etc. shielded with NavIO, PXFMini, etc. or designed from scratch such as NuttX, preemptive-RT Linux, Xenomai, Orocos-Robot Operating System or DDS-ROS 2.0.

Flight stack overview

Layer	Requirement	Operations	Example
Firmware	Time-critical	From machine code to processor execution, memory access	ArduCopter-v1, PX4
Middleware	Time-critical	Flight control, navigation, radio management	PX4, Cleanflight, ArduPilot
Operating system	Computer-intensive	Optical flow, obstacle avoidance, SLAM, decision-making	ROS, Nuttx, Linux distributions, Microsoft IOT

Civil-use open-source stacks include:

• ArduCopter
• CrazyFlie
• KKMultiCopter
• MultiWii
  • BaseFlight (forked from MultiWii)
    • CleanFlight (forked from BaseFlight)
      • BetaFlight (forked from CleanFlight)
      • iNav (forked from CleanFlight)
      • RaceFlight (forked from CleanFlight)
• OpenPilot
  • dRonin (forked from OpenPilot)
  • LibrePilot (forked from OpenPilot)
  • TauLabs (forked from OpenPilot)
• Paparazzi
• PX4 autopilot
  • DroneCode (Umbrella organization managing PX4 within the Linux Foundation)

Due to the open-source nature of UAV software, they can be customized to fit specific applications. For example, researchers from the Technical University of Košice have replaced the default control algorithm of the PX4 autopilot. This flexibility and collaborative effort has led to a large number of different open-source stacks, some of which are forked from others, such as CleanFlight, which is forked from BaseFlight and from which three other stacks are forked from.

Modern autonomous aircraft increasingly use AI-enhanced flight software that incorporates machine learning algorithms for adaptive control and neural networks for complex decision-making scenarios.

Loop principles

Typical flight-control loops for a multirotor

UAVs employ open-loop, closed-loop or hybrid control architectures.

• Open loop – This type provides a positive control signal (faster, slower, left, right, up, down) without incorporating feedback from sensor data.
• Closed loop – This type incorporates sensor feedback to adjust behavior (reduce speed to reflect tailwind, move to altitude 300 feet). The PID controller is common. Sometimes, feedforward is employed, transferring the need to close the loop further.

Modern autonomous systems increasingly employ AI-driven control loops that use machine learning algorithms to continuously adapt and optimize flight performance based on real-time environmental conditions and mission requirements.

Communications

Most UAVs use a radio for remote control and exchange of video and other data. Early UAVs had only narrowband uplink. Downlinks came later. These bi-directional narrowband radio links carried command and control (C&C) and telemetry data about the status of aircraft systems to the remote operator. For very long range flights, military UAVs also use satellite receivers as part of satellite navigation systems. In cases when video transmission was required, the UAVs will implement a separate analog video radio link.

In most modern autonomous applications, video transmission is required. A broadband link is used to carry all types of data on a single radio link. These broadband links can leverage quality of service techniques to optimize the C&C traffic for low latency. Usually, these broadband links carry TCP/IP traffic that can be routed over the Internet.

Communications can be established with:

• Ground control – a military ground control station (GCS). The MAVLink protocol is increasingly becoming popular to carry command and control data between the ground control and the vehicle.
• Remote network system, such as satellite duplex data links for some military powers. Downstream digital video over mobile networks has also entered consumer markets, while direct UAV control uplink over the cellular mesh and LTE have been demonstrated and are in trials.
• Another aircraft, serving as a relay or mobile control station – military manned-unmanned teaming (MUM-T).

As mobile networks have increased in performance and reliability over the years, drones have begun to use mobile networks for communication. Mobile networks can be used for drone tracking, remote piloting, over the air updates, and cloud computing.

Modern networking standards have explicitly considered autonomous aircraft and therefore include optimizations. The 5G standard has mandated reduced user plane latency to 1ms while using ultra-reliable and low-latency communications, enabling real-time autonomous flight operations.

Autonomy

Autonomous control basics

Basic autonomy comes from proprioceptive sensors. Advanced autonomy calls for situational awareness, knowledge about the environment surrounding the aircraft from exteroceptive sensors: sensor fusion integrates information from multiple sensors.

Basic principles

One way to achieve autonomous control employs multiple control-loop layers, as in hierarchical control systems. As of 2024, the low-layer loops (i.e. for flight control) tick as fast as 32,000 times per second, while higher-level loops may cycle once per second. The principle is to decompose the aircraft's behavior into manageable "chunks", or states, with known transitions. Hierarchical control system types range from simple scripts to finite state machines, behavior trees and hierarchical task planners. The most common control mechanism used in these layers is the PID controller which can be used to achieve hover for a quadcopter by using data from the IMU to calculate precise inputs for the electronic speed controllers and motors.

Examples of mid-layer algorithms:

• Path planning: determining an optimal path for vehicle to follow while meeting mission objectives and constraints, such as obstacles or fuel requirements
• Trajectory generation (motion planning): determining control maneuvers to take in order to follow a given path or to go from one location to another
• Trajectory regulation: constraining a vehicle within some tolerance to a trajectory

Evolved UAV hierarchical task planners use methods like state tree searches or genetic algorithms.

Modern autonomous systems increasingly employ machine learning algorithms and neural networks for real-time decision-making and adaptive behavior in complex environments.

Autonomy features

UAV's degrees of autonomy

UAV manufacturers often build in specific autonomous operations, such as:

• Self-level: attitude stabilization on the pitch and roll axes.
• Altitude hold: The aircraft maintains its altitude using barometric pressure and/or GPS data.
• Hover/position hold: Keep level pitch and roll, stable yaw heading and altitude while maintaining position using GNSS or inertial sensors.
• Headless mode: Pitch control relative to the position of the pilot rather than relative to the vehicle's axes.
• Care-free: automatic roll and yaw control while moving horizontally
• Take-off and landing (using a variety of aircraft or ground-based sensors and systems; see also:Autoland)
• Failsafe: automatic landing or return-to-home upon loss of control signal
• Return-to-home: Fly back to the point of takeoff (often gaining altitude first to avoid possible intervening obstructions such as trees or buildings).
• Follow-me: Maintain relative position to a moving pilot or other object using GNSS, image recognition or homing beacon.
• GPS waypoint navigation: Using GNSS to navigate to an intermediate location on a travel path.
• Orbit around an object: Similar to Follow-me but continuously circle a target.
• Pre-programmed aerobatics (such as rolls and loops).

Modern autonomous aircraft also feature:

• AI-powered collision avoidance using computer vision and machine learning
• Autonomous weather adaptation with real-time route optimization
• Predictive maintenance algorithms for operational efficiency
• Swarm coordination capabilities for multi-aircraft operations

Functions

Full autonomy is available for specific tasks, such as airborne refueling or ground-based battery switching; but higher-level tasks call for greater computing, sensing and actuating capabilities. One approach to quantifying autonomous capabilities is based on OODA terminology, as suggested by a 2002 US Air Force Research Laboratory, and used in the table below:

United States Autonomous control levels chart

Level	Level descriptor	Observe	Orient	Decide	Act
		Perception/Situational awareness	Analysis/Coordination	Decision making	Capability
10	Fully Autonomous	Cognizant of all within battlespace	Coordinates as necessary	Capable of total independence	Requires little guidance to do job
9	Battlespace Swarm Cognizance	Battlespace inference – Intent of self and others (allied and foes). Complex/Intense environment – on-board tracking	Strategic group goals assigned Enemy strategy inferred	Distributed tactical group planning Individual determination of tactical goal Individual task planning/execution Choose tactical targets	Group accomplishment of strategic goal with no supervisory assistance
8	Battlespace Cognizance	Proximity inference – Intent of self and others (allied and foes) Reduces dependence upon off-board data	Strategic group goals assigned Enemy tactics inferred ATR	Coordinated tactical group planning Individual task planning/execution Choose target of opportunity	Group accomplishment of strategic goal with minimal supervisory assistance (example: go SCUD hunting)
7	Battlespace Knowledge	Short track awareness – History and predictive battlespace Data in limited range, timeframe and numbers Limited inference supplemented by off-board data	Tactical group goals assigned Enemy trajectory estimated	Individual task planning/execution to meet goals	Group accomplishment of tactical goals with minimal supervisory assistance
6	Real Time Multi-Vehicle Cooperation	Ranged awareness – on-board sensing for long range, supplemented by off-board data	Tactical group goals assigned Enemy trajectory sensed/estimated	Coordinated trajectory planning and execution to meet goals – group optimization	Group accomplishment of tactical goals with minimal supervisory assistance Possible: close air space separation (+/-100yds) for AAR, formation in non-threat conditions
5	Real Time Multi-Vehicle Coordination	Sensed awareness – Local sensors to detect others, Fused with off-board data	Tactical group plan assigned RT Health Diagnosis Ability to compensate for most failures and flight conditions; Ability to predict onset of failures (e.g. Prognostic Health Mgmt) Group diagnosis and resource management	On-board trajectory replanning – optimizes for current and predictive conditions Collision avoidance	Self accomplishment of tactical plan as externally assigned Medium vehicle airspace separation (hundreds of yds)
4	Fault/Event Adaptative Vehicle	Deliberate awareness – allies communicate data	Tactical group plan assigned Assigned Rules of Engagement RT Health Diagnosis; Ability to compensate for most failures and flight conditions – inner loop changes reflected in outer loop performance	On-board trajectory replanning – event driven Self resource management Deconfliction	Self accomplishment of tactical plan as externally assigned Medium vehicle airspace separation (hundreds of yds)
3	Robust Response to Real Time Faults/Events	Health/status history & models	Tactical group plan assigned RT Health Diagnosis (What is the extent of the problems?) Ability to compensate for most failures and flight conditions (i.e. adaptative inner loop control)	Evaluate status vs required mission capabilities Abort/RTB is insufficient	Self accomplishment of tactical plan as externally assigned
2	Changeable mission	Health/status sensors	RT Health diagnosis (Do I have problems?) Off-board replan (as required)	Execute preprogrammed or uploaded plans in response to mission and health conditions	Self accomplishment of tactical plan as externally assigned
1	Execute Preplanned Mission	Preloaded mission data Flight Control and Navigation Sensing	Pre/Post flight BIT Report status	Preprogrammed mission and abort plans	Wide airspace separation requirements (miles)
0	Remotely Piloted Vehicle	Flight Control (attitude, rates) sensing Nose camera	Telemetered data Remote pilot commands	N/A	Control by remote pilot

Medium levels of autonomy, such as reactive autonomy and high levels using cognitive autonomy, have already been achieved to some extent and are very active research fields. In 2024, the autonomous aviation software market reached USD 8 billion and is expected to grow to USD 32.36 billion by 2033 at a 15% CAGR, driven by increasing applications across diverse industries.

Reactive autonomy

See also: Perceptual control theory

Reactive autonomy, such as collective flight, real-time collision avoidance, wall following and corridor centring, relies on telecommunication and situational awareness provided by range sensors: optic flow, lidars (light radars), radars, sonars.

Most range sensors analyze electromagnetic radiation, reflected off the environment and coming to the sensor. The cameras (for visual flow) act as simple receivers. Lidars, radars and sonars (with sound mechanical waves) emit and receive waves, measuring the round-trip transit time. UAV cameras do not require emitting power, reducing total consumption.

Radars and sonars are mostly used for military applications.

Reactive autonomy has in some forms already reached consumer markets: it may be widely available in less than a decade.

Cutting-edge (2024) autonomous levels for existing systems

Simultaneous localization and mapping

SLAM combines odometry and external data to represent the world and the position of the UAV in it in three dimensions. High-altitude outdoor navigation does not require large vertical fields-of-view and can rely on GPS coordinates (which makes it simple mapping rather than SLAM).

Two related research fields are photogrammetry and LIDAR, especially in low-altitude and indoor 3D environments.

• Indoor photogrammetric and stereophotogrammetric SLAM has been demonstrated with quadcopters.
• Lidar platforms with heavy, costly and gimbaled traditional laser platforms are proven. Research attempts to address production cost, 2D to 3D expansion, power-to-range ratio, weight and dimensions. LED range-finding applications are commercialized for low-distance sensing capabilities. Research investigates hybridization between light emission and computing power: phased array spatial light modulators, and frequency-modulated-continuous-wave (FMCW) MEMS-tunable vertical-cavity surface-emitting lasers (VCSELs).

Swarming

Further information: Swarm robotics

Robot swarming refers to networks of agents able to dynamically reconfigure as elements leave or enter the network. They provide greater flexibility than multi-agent cooperation. Swarming may open the path to data fusion. Some bio-inspired flight swarms use steering behaviors and flocking.

Modern swarm technology has advanced significantly, with DARPA's ANCILLARY program demonstrating five VTOL unmanned systems capable of coordinated operations. These systems, weighing under 150 kilograms each, can operate for 12 hours at 100 nautical mile range with 27-kilogram payload capacity, showcasing the potential for autonomous swarm operations.

Commercial Aviation Developments

Air Taxi and Urban Air Mobility

The urban air mobility sector has emerged as a transformative application for autonomous aircraft technology, with companies like Joby Aviation, Archer Aviation, Beta Technologies, and Lilium leading development efforts.

Joby Aviation has achieved several breakthrough milestones:

• Completed Stage 3 of FAA's five-stage type certification process in 2024
• Received $500 million investment from Toyota in 2024, bringing total investment to $894 million
• Acquired Xwing's autonomy division in June 2024 to advance self-flying capabilities
• Delivered its first eVTOL aircraft to the United Arab Emirates in 2024 for 2026 service launch
• Achieved record 523-mile flight with hydrogen-electric power, demonstrating extended range capabilities

Commercial Aircraft Automation

Major aerospace manufacturers are advancing autonomous capabilities in traditional commercial aviation. Airbus has made significant progress with its A350-1000, which has successfully demonstrated fully autonomous taxiing, takeoffs, and landings using advanced computer vision and machine learning technologies.

Boeing continues developing autonomous systems through its Aurora Flight Sciences subsidiary, conducting tests of AI-controlled aircraft formations reaching speeds of 167 mph.

Military and Defense Applications

DARPA Advanced Programs

The Defense Advanced Research Projects Agency (DARPA) has achieved groundbreaking advances in autonomous military aircraft through several key programs:

Air Combat Evolution (ACE) Program: In September 2024, DARPA achieved a historic milestone by conducting the first AI-versus-human dogfight using real aircraft. The X-62A VISTA (Variable In-Flight Simulator Aircraft), an AI-controlled F-16, successfully engaged in combat maneuvers against a human-piloted F-16 without violating safety protocols.

Collaborative Combat Aircraft (CCA) Program: The U.S. Air Force has committed $8.9 billion over five years starting in FY 2025 for this program, which aims to deploy over 1,000 autonomous drones that can operate alongside manned aircraft. In April 2024, Anduril and General Atomics were selected to develop production representative test articles.

ANCILLARY Program: Five new vertical takeoff and landing (VTOL) unmanned aerial systems, each weighing under 150 kilograms, began flight testing in 2025. These systems demonstrate 12-hour endurance at 100 nautical mile range with 27-kilogram payload capacity, representing a significant advancement in autonomous battlefield support capabilities.

Regulatory Framework

Federal Aviation Administration (FAA) Developments

The 2024 FAA Reauthorization Act represents a transformative advancement in autonomous aircraft regulation, directing the FAA to establish comprehensive rules for beyond visual line of sight (BVLOS) operations by September 2024.

Key regulatory developments include:

• $107 billion in funding for fiscal years 2024-2028 to support autonomous aircraft integration into the national airspace system
• Streamlined acceptance processes for autonomous aircraft based on manufacturer compliance declarations
• Enhanced integration of varying levels of automated control in aircraft operations
• Creation of additional test sites for autonomous package delivery and commercial operations
• Expanded BEYOND program for five additional years to support advanced autonomous operations

The FAA's Part 107 regulations continue to evolve to accommodate autonomous operations, with new provisions for operations over people, at night, and beyond visual line of sight under specific conditions.

Future military potential

In the military sector, American Predators and Reapers are made for counterterrorism operations and in war zones in which the enemy lacks sufficient firepower to shoot them down. They are not designed to withstand antiaircraft defenses or air-to-air combat. However, the landscape has changed dramatically with DARPA's ACE program demonstrating that AI-controlled fighter aircraft can engage in complex combat scenarios.

The Department of Defense's Unmanned Systems Integrated Roadmap FY2025-2040 foresees a more important place for UAVs in combat. Issues include extended capabilities, human-UAV interaction, managing increased information flux, increased autonomy and developing UAV-specific munitions. DARPA's Collaborative Combat Aircraft program represents a $8.9 billion investment in autonomous fighter aircraft that will operate alongside manned platforms.

The U.S. Air Force's CCA initiative aims to deploy over 1,000 autonomous aircraft capable of performing diverse missions including electronic warfare, intelligence gathering, reconnaissance, and direct combat operations without step-by-step human control.

Cognitive radio

Cognitive radio technology may have UAV applications.

Learning capabilities

UAVs may exploit distributed neural networks. Modern autonomous aircraft increasingly employ deep learning algorithms and neural networks for complex decision-making, with machine learning models enabling real-time adaptation to changing operational conditions. The autonomous aviation software market has grown to USD 8 billion in 2024 and is projected to reach USD 32.36 billion by 2033, driven by advances in AI and machine learning technologies.

Future Outlook and Challenges

Technological Integration

The integration of artificial intelligence and machine learning technologies continues to advance autonomous aircraft capabilities. Modern systems employ:

• Advanced sensor fusion combining LiDAR, radar, cameras, and inertial measurement units
• Real-time decision-making algorithms powered by neural networks
• Predictive maintenance systems that optimize operational efficiency
• Adaptive flight control that responds to changing environmental conditions

Market Projections

Industry analysts project continued rapid growth with various market research firms forecasting:

• Grand View Research: Market growth at 32.40% CAGR from 2024 to 2035
• Fortune Business Insights: Market reaching USD 22.71 billion by 2030 at 17.8% CAGR
• Market.US: Market growing to USD 30.9 billion by 2033 at 18.2% CAGR

Safety and Certification

Despite technological advances, several challenges remain:

• Cybersecurity concerns regarding autonomous flight systems requiring robust protection protocols
• Public acceptance of fully autonomous passenger aircraft, particularly for commercial aviation
• Regulatory harmonization across international aviation authorities for consistent global standards
• Technical reliability in adverse weather conditions and emergency scenarios requiring fail-safe systems

Industry Applications

Key sectors driving autonomous aircraft adoption include:

• Defense and military operations accounting for 45% of the market in 2024
• Cargo and logistics representing 61.3% of operational deployments due to reduced risk
• Urban air mobility for passenger transport in dense metropolitan areas
• Emergency services including search and rescue, medical transport, and disaster response

The autonomous aircraft industry continues to evolve rapidly, with 2025 expected to mark the beginning of commercial autonomous air taxi operations and expanded military deployment of collaborative combat aircraft systems.

See also

• International Aerial Robotics Competition
• Satellite Sentinel Project
• Tactical Control System
• Xwing (aviation)
• Single pilot operations
• Automated flight attending
• Urban air mobility
• Electric vertical takeoff and landing aircraft
• Advanced air mobility