Parrot Anafi Ai is a completely new unique solution from a well-known French developer, adapted primarily for commercial use both in manual and fully automatic modes in various fields of human activity, including: survey of buildings, infrastructure, telecommunications towers, wind turbines, solar batteries, pipelines, refineries, as well as in mapping, geodesy, 3D modeling, orthophotography, construction monitoring, automated surveillance, real estate, insurance, video content creation.
The business card of Anafi Ai is the built-in 4G module, thanks to which the drone got the opportunity to use the fourth generation of mobile communications as the main data transmission channel between the drone and the control equipment, which actually removes all restrictions on the flight range and predetermines the operation of the UAV beyond the line of sight. Looking ahead, we note that the declared potential of the car turned out to be incredibly powerful and, more than ever, corresponds to its futuristic appearance, the creation of which French engineers were inspired by nature.
Developer about car
Martin Liné, Marketing Director at Parrot, on how the ANAFI Ai drone was created: “At Parrot, we are driven by one passion: biomimicry. Up to this point, Parrot drones did not offer an obstacle avoidance feature. But we thought about it for a long time and tried to find an elegant solution to achieve this without having to multiply the cameras around the drone, because it simply complicates the hardware. We noticed that there are no known species in nature that have a system of vision distributed throughout the body, but this does not prevent them from visualizing the world around them in all directions. This is how we created ANAFI Ai.”
Key features of the Parrot Anafi AI:
- Drone flight weight: 898 grams
- Ready to fly time 60 seconds
- Unique portable foldable design
- Built-in 4G communication module for full drone/control equipment interaction without restrictions in any environmental conditions
- Compatibility with LTE worldwide
- Equipped with an omnidirectional signal transmission system (4 directional reflector antennas (with gain: 2.5 dBi / s antennas). The aircraft determines the best pair of antennas depending on its orientation and position relative to the position of the pilot)
- Equipped with a unique omnidirectional visualization system of the surrounding world built on a pair of stereoscopic cameras mounted on a specialized gimbal with a 330-degree rotation range (from ‑120° to + 210°), working in tandem with an intelligent flight path optimization system
- Adapted for indoor flight
- Live video streaming in 1080p quality with low latency (300 m/s) with no limits on flight range anywhere in the world, with a video bit rate of 12 Mbps
- Ability to transfer files to cloud storage directly in flight
- Built-in Wi-Fi communication module (Wi-Fi 802.11a/b/g/n) for full interaction of the drone / control equipment (as an alternative connection option)
- Slave. WiFi frequency band: 2.4GHz/5.8GHz
- Max. Wi-Fi FPV Range: 9km
- The unique automatic mode of operation of 4G / Wi-Fi modules allows, based on network congestion, to seamlessly switch from one communication technology to another without data loss
- Drone protection class IPX3
- Max. flight time 32 min
- Max. horizontal flight speed 61 km/h
- Max. wind resistance: 13 m/s
- Max. ceiling above sea level 5000 m
- 48MP 4K camera built on a 1/2‑inch CMOS sensor with a pixel size of 0.8μm; with built-in Bayer color filter array
- Lens Optical LD-ASPH
- Hybrid 6‑Axis Image Stabilizer (3‑Axis Mechanical + 3‑Axis Digital EIS)
- Controlled gimbal range ‑90° to +90°
- 6x lossless digital zoom (2x in 4K mode/4x in FHD mode)
- Max. video bitrate 200 Mbps
- HDR8/HDR10 video recording formats
- Max. dynamic range 14EV
- P‑log color profile for post-processing
- 5 × automatic flight and shooting modes (Photogrammetry/Flight Plan/Cameraman/Smart RTH/Vehicle)
- Built-in slots for microSD and SIM cards
- Compatible with PIX4D Suite
- Photogrammetric flight modes are available in mob. FreeFlight 7 app and OpenFlight software
- Ability to create a flight plan in one click
- 48MP photogrammetry at 1fps: twice as fast as the competition
- Shooting accuracy: 0.46 cm/px. GSD at 30m
- Parrot SDK support (with the ability to inject your own code into the drone using the Air SDK, create mobile applications using the Ground SDK, set up an open source ground station using OpenFlight, interact with the modern Sphinx drone simulation tool, as well as the ability to develop Python scripts using Olympe and video and metadata processing via PdrAW)
- Compatible with third party software: PIX4Dscan, PIX4Dinspect, PIX4Dcloud, PIX4Dreact, PIX4Dsurvey
- ANAFI Ai complies with the European Union General Data Protection Regulation (GDPR)
- High-End Data Privacy with Embedded NIST FIPS140‑2 Level 3 Compliant WISeKey Secure Element with Common Criteria EAL5+ Certification
- Video and controls are secured using SRTP/DTLS protocols in accordance with webRTC
- New portable control equipment Parrot Skycontroller 4
- New Parrot FreeFlight 7 mobile app
The developer offers the drone in a single configuration, which will include:
- Drone ANAFI AI
- Hard transport case
- Control equipment Parrot Skycontroller 4
- 1×Smart battery
- USB charger
- Spare Prop Kit (2CW/2CCW)
- Companion cable (USB‑C to Lightning)
- 2 × companion cables (USB‑C to USB‑C)
- Calibration table
Prelaunch deployment time:
Max. flight time:
Max. horizontal flight speed:
Max. vertical takeoff speed:
Max. wind resistance:
Max. number of propeller revolutions:
Max. ceiling above sea level:
5 000 m
Slave. temperature range:
-10°C to 40°C
82 dB at 1 m
MicroSD and SIM card
Video stream quality:
1920 × 1080 at 30 fps
GPS, Glonass and Galileo
2 × 6‑axis inertial units
2 × 3‑axis accelerometers
2 × 3‑axis gyroscopes
Stereoscopic cameras mounted on a 311° gimbal (-107° to +204°)
Intelligent Flight Trajectory Optimization System
Dimensions without smart device:
Max. the size:
Operating range frequencies:
2.4GHz — 5GHz
The quality of the displayed FPV picture:
3350 mAh 7.2V
Max. compatible device size:
2 × USB‑C (charging + connection), micro-HDMI
Drone Intelligent Battery
high density lithium polymer (262 Wh/kg)
6800 mAh 4.4 V
Max. memory power:
Parrot FreeFlight 7 (free; no fee)
iOS 12 and above
3 free 3D models courtesy of PIX4Dcloud
48MP 1/2″ CMOS
Array of color filters:
Quad bayer array
14EV in HDR mode
Optical LD-ASPH (Low Dispersion Aspherical Lens): Aperture: f/2.0
Focal length in 35mm equivalent: 24mm
Depth of field:
from 4.5 m to ∞
from 50 to 6400
1/15 to 1/10000 s
6x Lossless Zoom:
up to 4x (in 1080p mode) and 2x (in 4K UHD mode)
Mechanical: 3‑axis (Pitch, Roll, Yaw)
Electronic (EIS): 3‑axis (Pitch, Roll, Yaw)
Slave. gimbal tilt range:
-90° to + 90°
Depth of field:
from 4.5 m to ∞
MP4 (H.264, H.265)
4K UHD: 3840 × 2160 @ 24/25/30/48/50/60 fps
1080P: 1920 × 1080 @ 24/25/30/48/50/60/90/100/120 fps
4K UHD/1080p@24/25/30 fps
for all modes
Horizontal FOV (HFOV):
JPEG, DNG (Digital Negative RAW)
48MP (8000×6000), 12MP (4000×3000)
Horizontal FOV (HFOV):
73° (Wide), 69° (Wide with EIS), 65° (Straight with EIS)
Single, Bracketing, Burst (10 fps), Panorama (4 formats), Time-lapse, GPS-lapse
Autonomous flight modes
Single grid/Double grid/Orbit
Multiple Waypoints/Points Of Interest
Automatic framing with visual tracking
auto return to takeoff point with adjustable flight altitude
the flight is tied to the controller that sets the location (allows you to land on moving vehicles)
Zero data is transmitted without user consent
FIPS140‑2 compliant and CC EAL5+ security feature certification
Strong authentication for 4G
Photos digitally signed
Transparency and continuous security check of Bug Bounty
built-in encoding capabilities
iOS and Android app development kit
Free-Flight 7 open source core
3D photorealistic simulator
Python controller programming interface
video and metadata toolkit
Below you can read the Parrot Anafi Ai key information, which will allow you to learn more about the declared potential of the machine, as well as what improvements have been made compared to the commercial version of the Parrot Anfi Thermal drone and other drones from leading brands.
ANAFI Ai includes a 4G radio module (in addition to a Wi-Fi radio module) that allows you to broadcast a video stream in 1080p quality with a maximum bit rate of 12 Mbps, with very low latency (300 ms) without range limitation and anywhere in the world.
The ANAFI Ai 4G module supports over 28 frequency bands covering over 98% of the frequencies deployed worldwide.
Automatic network switch
The quality and throughput of 4G and Wi-Fi networks are measured every 100ms to adapt streaming to network conditions. Combined with routing algorithms, the connection between the aircraft and its controller is maintained even during severe Wi-Fi disruption. So when the effective bandwidth (useful bandwidth) of Wi-Fi is below 1.5 Mbps, the system will automatically switch to 4G.
To limit the consumption of mobile data when the pilot is within range of the aircraft’s Wi-Fi network, the transition from 4G to Wi-Fi is also performed automatically without clipping the video stream.
Max. range with 4G connection
Developer’s video shows max. flight range of Anafi Ai with 4G connection in one direction on one battery charge. The total flight time was 29 minutes at an average horizontal flight speed of 58 km/h (16 m/s). During this time, the drone was able to cover 27 km. You can also notice that the flight was carried out in strong wind conditions, which the drone system constantly warned about.
Implemented video stream optimization algorithms
4G congestion control
The overload control algorithm allows:
- Measure packet loss over the entire network cycle.
- Measure latency (round trip time).
- Adjust the bandwidth according to these two parameters.
The ultimate goal of the algorithm is to maximize the available bandwidth while maintaining the lowest possible latency. This algorithm is implemented on each of the interfaces available in the drone, each with its own parameters optimized according to the network. Based on the information provided by this algorithm, the link manager decides on the routing and active interface.
Drone control via 4G connection
ANAFI Ai connects to the remote controller via 4G in less than 30 seconds if the aircraft is out of Wi-Fi range and in less than 15 seconds if the aircraft is in Wi-Fi range. And also 4G connection provides:
- Connection discovery and initiation based on the VOIP SIP protocol.
- Using a relay server to establish a connection in secure networks.
Video stream performance
- Latency: 300ms.
- Security: Videos and controls are secured using SRTP/DTLS in accordance with webRTC.
- Antennas: 28 LTE bands from 700 MHz to 2.6 GHz.
Omnidirectional transmission system
- ANAFI Ai has 4 directional reflector antennas (gain: 2.5dBi/s antenna). The drone determines the best pair of antennas based on its orientation and position relative to the pilot’s position.
- With a recombined gain of 3.5 +/- 1.5 dBi in the horizontal plane of the drone, the gain of the ANAFI Ai radio signal is highly uniform.
- Downward radiation from the antennas has been improved by +4 dB compared to ANAFI.
High Power Radio External Design
The front of the radio allows power to be maximized at the base of the antenna with a very good level of linearity and sensitivity (-94 dBm at 6.5 Mbps) to reach the maximum FCC power limit.
Reliability of Wi-Fi connection
A subset of the protocol parameters was chosen to optimize performance in drone environments such as relatively low throughput, low latency, variability in reception due to aircraft speed, long range, and interference. These parameters include aggregation, retries, MiMo technology (STBC), control frame datarate, and disconnect conditions.
Smart Interference Prevention System
ANAFI Ai has an algorithm for eliminating channels (in two bands 2.4 GHz and 5 GHz) in case of interference.
Adaptation and flow monitoring
ANAFI Ai constantly monitors the status of its connection at a frequency of 4 Hz and can detect the presence of interference. This allows you to dynamically optimize the throughput and size of transmitted packets. It also warns the pilot if he is in a particularly noisy environment or close to losing signal.
At the limit of its range, and if conditions allow it, ANAFI Ai can switch to 10 MHz bandwidth to improve its sensitivity by 3 dB and increase its range by 40%.
Video link metrics
Implemented video stream optimization algorithms
Parrot Gen4 Streaming (4th generation)
This algorithm reduces the visual impact of network loss and allows all decoders to communicate while providing a syntactically complete stream: missing parts of the image are reconstructed as missing parts that are identical to those in the reference image.
Thus, glitches are contained only in those areas that are prone to loss, and do not apply to the entire image.
The graphs below show the macroblock decoding success rates at 5% network loss, with and without advanced ANAFI Ai streaming features. The algorithm provides correct decoding of 75% of macroblocks. They allow the user to continue their mission without screen freezes or loss of streaming.
The algorithm also evaluates the Wi-Fi and radio environment to anticipate and avoid packet loss and network congestion, which helps reduce latency. The algorithm is based on an estimate of the channel throughput calculated from the data rate and the error rate at the physical layer; it then affects the network encoding and encapsulation parameters.
Metadata is transmitted with the video stream. In particular, they contain elements of drone telemetry (position, altitude, speed, battery level, etc.) and video metrics (camera angle, exposure value, field of view, etc.).
Synchronization of images and open metadata performs the functions of precise positioning on the map, tracking flight instruments in the HUD, or enabling augmented reality elements.
Inclusion of metadata is carried out by standard methods (RTP header extension); the data format defined by Parrot is open: it is available in the ANAFI Ai SDK.
The ANAFI Ai sensor includes a large number of megapixels to provide detailed aerial photography.
It uses Quad Bayer color filter array technology, where groups of 4 adjacent pixels have the same color. Thus real-time HDR capture can be obtained in both photo and video modes by adding signals from four neighboring pixels.
Its dynamic range is 4 times greater than standard Bayer matrices. Even complex scenes can be captured with minimal highlight highlights or loss of shadow detail.
The ANAFI Ai lens was specially designed for Parrot. It combines 6 aspherical elements and is optimized to reduce optical glare. This lens delivers 68° HFOV in standard video mode and 64.6° HFOV in standard photo mode.
ANAFI Ai shoots smooth 4K video at 60fps, including in P‑Log, as well as HDR10 4K video at up to 30fps. The table below lists all ANAFI Ai video modes.
Users can choose between H.264 (AVC) and H.265 (HEVC) formats.
The following pixel formats are used for all resolutions:
- YUV420p (8 bits/component, BT.709 color space) for standard mode and HDR8.
- YUVJ420p (8 bits/component, full range — BT.709 color space) for P‑log style.
- YUV420p10 (10 bits/component, BT.2020 color space) for HDR10 recording, H.265 only.
When recording video in HDR8 and HDR10, ANAFI Ai covers a dynamic range of 14EV. The HDR10 format provides a maximum brightness of 1000 nits and a color depth of 10 bits. It provides a billion color palette versus 16 million for the standard dynamic range. Compared to HDR8, HDR10 delivers images that are more than twice as bright with a corresponding increase in contrast. HDR8 can be displayed on any standard screen, while HDR10 is for TVs and HDR10 screens.
Description of modes
The mode control section contains settings that affect the number of shots that are taken each time the shutter is released.
single capture mode
Standard frame mode. After each shutter release, the captured image is immediately processed by the system.
Users can shoot a series of 3, 5 or 7 frames with different exposures for each frame. The following presets are available:
- [-1 EV, 0, +1 EV] (default settings)
- [-2 EV, ‑1 EV, 0, +1 EV, +2 EV]
- [-3 EV, ‑2 EV, ‑1 EV, 0, +1 EV, +2 EV, +3 EV]
Burst mode will allow the user to take a series of 10 frames in 1 second.
Panorama mode includes four different panorama shots:
- Spherical (360°) — This panoramic mode includes three options for shooting a spherical panorama: Sphere (Sphere) / Little Planet (Little Planet) / Tunnel (Tunnel).
- Horizontal (180°)
- Vertical (109°)
- superwide — new ultra-wide mode that provides stitching of 9 images (HFOV 110°, rectilinear panorama)
See the table below for details on the characteristics of panoramic modes:
This mode allows you to take pictures at the following fixed intervals:
- 48Mp: 1, 2, 4, 10, 30 or 60s.
- 12Mp: 0.5, 1, 2, 4, 10, 30 or 60s
GPS lapse mode
This photo mode was developed for inspection and photogrammetry. It allows you to take pictures at the following fixed distance intervals: 5, 10, 20, 50, 100 or 200 meters.
The table below shows the shooting modes and resolutions, including the Sensor Readout mode:
The following table lists the available settings for each mode.
Zooming is available in all photo and video modes. Combined with a 48-megapixel sensor, precise sharpening algorithms produce high-definition images even when using 6x digital zoom. ANAFI Ai users can now see 1cm details from 75m away. The high pixel count also allows 4K videos to be cropped to 1080p without quality loss.
The ANAFI Ai camera has the most accurate stabilization on the micro-UAV market.
It combines combined stabilization:
- 3‑axis mechanical (3‑axis mech. gimbal)
- 3 axis electronic (EIS)
Mechanical stabilization stabilizes the camera’s pointing axis regardless of the aircraft’s flight position. Electronic image stabilization corrects the effect of micro-vibrations for frequencies above 100 Hz, which cannot be handled by a mechanical drive.
Main camera gimbal
Mechanical stabilization allows you to stabilize and orient the horizontal axis of view of the camera along all 3 axes.
3 axes of rotation mech. suspension of the main camera ANAFI Ai.
- 3 axis mechanical stabilization for the main camera
- 292° vertical offset, ‑116° to +176° field of view
- The EIS algorithm corrects the effects of wide-angle lens wobble and distortion, as well as 3‑axis digital image stabilization (Roll, Pitch and Yaw).
- The method consists in applying a geometric transformation of the image. The geometry transformation is linked to the timestamp and precise position thanks to the IMU.
- A geometric transformation is applied to each image according to the optical distortions, oscillations and movements of the measured camera module.
Swivel range 292°
The camera has gained a horizontal swivel range of ‑116°/ +176° around the Pitch axis, thus providing observation above and below the drone, which is a unique opportunity in the micro-UAV market.
Aerial photography using unmanned aerial vehicles is changing the way specialists conduct inspections and geodetic works. Photogrammetry methods are used to process images collected by UAVs to create 2D and 3D models, which subsequently allow customers to plan the maintenance of surveyed objects in a timely manner.
4G provides unparalleled reliability of the data transmission channel from the drone. Users can operate the UAV in large areas, near metal structures, buildings, without fear of loss of communication.
Inspection and cartography
By combining the AI of the ANAFI Ai drone with the PIX4Dinspect online platform, users will be able to conduct inspections faster and more efficiently than ever. Machine learning algorithms recognize antennas on cell towers, determine their size, height, tilt, azimuth and verticality.
Click on the images below to explore the 3D demo models generated by ANAFI Ai .
Best in class matrix
The ANAFI Ai drone camera is equipped with a 48MP 1/2‑inch CMOS sensor built with Quad Bayer color filter technology, which is more than ever suitable for inspection and photogrammetry. The matrix involved allows you to get detailed images with a wide dynamic range.
High resolution photos
ANAFI Ai is capable of generating 48-megapixel still images, thereby capturing all the details in high resolution and creating a high-density point cloud.
Inspection missions require the ability to identify minute details such as serial numbers, connectors, rust spots and incipient cracks.
Wide dynamic range
10 stops of dynamic range in standard mode, 14 stops in HDR mode. Optimal image gradation is essential to create consistent cloud points and high quality 2D or 3D reconstructions.
55% more detail than 1″ sensors
The 48MP 1/2‑inch Quad Bayer sensor of the ANAFI Ai drone is superior in sharpness to the 20MP 1‑inch sensors that are used in a number of modern professional drones. The following images taken during the same height inspection of the roof with ANAFI Ai and DJI Phantom 4 Pro V2.0 drones clearly demonstrate this fact.
Ideal for inspections
The ANAFI Ai gimbal includes a 6‑axis hybrid (mechanical + electronic) stabilization system that compensates for flight fluctuations and guarantees image sharpness. The ANAFI Ai camera has an adjustable range of ‑90° to +90°, making it the ideal aerial tool for viewing the underside of the bridge base.
Controlled tilt ± 90°
ANAFI Ai allows users to achieve a GSD of 0.46 cm/px from a height of 30 m, which means a relative planimetry accuracy of up to 0.92 cm.
By comparison, at the same height, the DJI Phantom 4 Pro V2 only delivers a GSD of 0.82cm/px. In other words, the ANAFI Ai can map the same target while flying more than 1.5 times higher than the Phantom at an equivalent level of detail.
AI and 4G Capabilities
One application. Any flight plan
The potential of the FreeFlight 7 mobile application allows the user to launch all survey, inspection and photogrammetry missions.
Available photogrammetric flight modes
The following photogrammetric flight modes are now available in the FreeFlight 7 mobile app:
Create a flight plan in one tap
One tap on the FreeFlight 3D interactive map is all it takes to quickly scan a building. Artificial intelligence automatically determines the optimal flight parameters and trajectory. 48MP images with precise geo-reference of ANAFI Ai sensors (IMU, GNSS and Time of Flight) enable accurate 3D reconstruction.
Automatic flight plan created with one tap in 3D land registry.
- The map background for the FreeFlight 7 application is from ArcGIS software. The 3D building representation is based on OpenStreetMap data covering cities around the world.
- Visualization systems ensure the safety of a given flight plan: users do not have to worry about obstacles. ANAFI Ai autonomously avoids them.
Based on stereoscopic vision, the ANAFI Ai omnidirectional sensor system automatically orients itself in the direction of travel.
The drone detects obstacles at a distance of 30 m. As the flight plan is executed, the artificial intelligence technology constantly builds and updates the infill grid. It represents the environment of the drone in voxels.
Algorithms determine the best trajectory to avoid obstacles while the drone remains focused on its goal: the intended flight mission.
ANAFI Ai is the first commercial microdrone equipped with a 4G module. It covers over 98% of the frequencies used worldwide.
Inspection of high-voltage power lines. Shot with ANAFI Ai, processed with Pix4Dmatic. Scene size: 4060 × 60 × 70 m. Number of images: 2172. GSD: 1.3 cm/px. Height: 90 m. Front/side overlap: 90%/65%.
The drone is able to seamlessly switch from Wi-Fi to 4G and vice versa, thus providing the most reliable connection, which in turn guarantees:
- Ability to perform BVLOS flights
- Stable connection, even when flying in environments cluttered with obstacles and buildings
- Safe flight in high interference environments
- Video link quality 1080p at 30 fps
- Direct upload of images to cloud servers
Flight time optimization
According to the developer, significant time savings have been achieved due to the high image performance of ANAFI Ai:
- 48MP allows the drone to fly more than 1.5 times higher than drones with 20MP 1‑inch sensors while achieving the same GSD. In other words, higher altitude and faster mission go hand in hand.
- 1fps photography: ANAFI Ai shoots twice as fast as Autel EVO 2 and DJI Phantom 4 Pro V2.0.
4G in-flight transmission on PIX4Dcloud
In the process of creating a digital model from aerial photographs of a drone, file transfer and photo processing are two time-consuming tasks. ANAFI Ai helps users speed up their workflow. In particular, the drone system allows:
- Transfer images to secure servers during flight using the drone’s 4G connection.
- Immediately start computing objects at the end of the flight: orthomosaics, point cloud, elevation models and textured mesh.
- Easily share 2D maps and 3D survey-quality models with employees and customers.
Compatible with PIX4D Suite
ANAFI Ai is fully compatible with a unique software suite of mobile, desktop and cloud photogrammetry applications, consisting of:
Photogrammetry or lidar
Why choose photogrammetry for surveys and inspections? In addition to affordability and ease of use, aerial photogrammetry is the best choice when visual interpretation of data is required.
- Provides several visualizations: orthomosaic, colored point cloud, textured mesh.
- Creates a higher density point cloud, each containing a significant amount of information (height, texture, color).
- Outperforms LIDAR in accuracy of photorealistic 2D and 3D renderings — LIDAR does not provide a high level of contextual detail.
- It costs 100 times more than an RGB UAV.
- Complexity of data processing and possible errors of interpretation.
- Adding color information is possible, but it complicates the process.
- LIDAR only generates a point cloud and is designed for specific cases and situations.
The Parrot Software Development Kit is a set of open source tools and software for developers. Since the creation of the first AR Drone, the company’s open source code has been at the heart of developer platforms and tools, and Parrot has continuously contributed to the open source developer community.
The developer clarifies that all the company’s SDK resources are available free of charge, without registration and tracking, on the Parrot Developer Portal. You can also join thousands of developers on the Parrot forum where you can discuss hot topics directly with the company’s engineers.
Run your code on ANAFI Ai
The Air SDK provides a revolutionary technology architecture for downloading and running code directly on the ANAFI Ai. Developers can program tailor-made flight missions with access to all drone sensors, connectivity interfaces, and autopilot features.
Air SDK provides onboard access to:
- All sensors (IMU, GPS, TOF) and flight modes
- Video stream and metadata from all cameras
- Communication interfaces Wi-Fi, 4G, USB
- Depth maps and infill grids
- Creating an obstacle avoidance trajectory
Any developer can:
- Change the state of the drone by creating flight tasks
- Change navigation mode
- Add embedded Linux processes (for example, transfer data over a 4G channel or use computer vision)
Air SDK supports C++ or Python programming language. The Air SDK comes with a detailed installation guide and API documentation. Many application examples illustrate all the possibilities offered by its unique architecture.
Build a powerful mobile app
The Ground SDK is a ground control station (GCS) software platform for mobile devices (both iOS and Android are supported). It allows any developer to create a mobile application for ANAFI Ai to control the drone directly from a mobile device. All WAN functions (control, video, settings) are available through an easy to use and fully documented API.
Open source ground control station
For the first time, Parrot is open source for its ground control station application. OpenFlight is the core of our famous open source FreeFlight 7 application. This allows the developer to focus on adding their own features and get a professional-looking app ready to be published to the AppStore right away.
Open Flight contains:
- All UX FreeFlight 7
- All interface settings
- Code for real-time 3D visualization of obstacles
- 4G communication control code
- OpenFlight is published under a BSD‑3 license with a complete installation guide and comprehensive documentation.
3D photorealistic modeling
Parrot Sphinx is a state of the art drone simulation tool. Parrot engineers use it to develop and test all ANAFI Ai features. The general concept is to simulate the actual firmware of a drone with all of its sensors in a visually and physically realistic environment.
Parrot Sphinx allows you to:
- Simulate all cameras and sensors
- Model depth maps and image segmentation
- Navigate through many realistic 3D scenes
- Connect to different types of remote controls
- Use scripts to control simulation
- Add pedestrians and vehicles
- Visualize and record flight data
- Customize drone sensors and surrounding physical elements
- Control the real time factor
The Parrot Sphinx is built with industry-leading standard components:
Python to control ANAFI Ai
Olympe provides a Python controller programming interface for ANAFI Ai. The original purpose of Olympe is to interact with the Sphinx modeling environment. Olympe can also control the physical ANAFI Ai from a remote computer.
The Olympe framework allows you to:
- Connect to a simulated or physical ANAFI Ai
- Send command messages (piloting, camera orientation, return home, flight plan)
- Start and stop streaming video from all cameras
- Record video stream and synchronized metadata
Advanced media player
PDrAW is an advanced video viewer for ANAFI Ai media. The viewer supports both streaming (RTP/RTSP) and recorded (MP4) video on Linux, macOS, Android and iOS platforms. PDrAW comes as a library (libpdraw), a wrapper library (libpdraw-backend), and a standalone executable (pdraw).
PDrAW also manages video metadata. On the ANAFI Ai, both streamed and recorded video include metadata that is publicly available and documented, allowing advanced aerial video processing.
Parrot provides 3D models of its drones to be integrated into your CAD design for rapid prototyping and accessory integration.
MAVLink and GUTMA Compatibility
ANAFI Ai is compatible with the standard open source MAVLink v1 protocol, which allows real-time data exchange between the UAV and the control station. The ANAFI Ai can be flown manually or using automatic flight planning from a MAVLink compatible base station such as QGroundControl.
ANAFI Ai is compatible with the standard open source GUTMA protocol for flight data. The Global UTM Association is a consortium of major players in the air traffic management industry.
The largest partner ecosystem for Parrot drones
Parrot continues to expand the global ecosystem of drone software providers through its SDK Partner Program, offering tailored and unique solutions to the growing and evolving needs of professional users.
Parrot for every business need
To get the most out of the inspection process, Parrot offers its customers an ecosystem of compatible drone software, from fleet management, flight planning and flight log import, to surveying, mapping, monitoring and analysis of acquired data.
PIX4D × Parrot
Applications for 2D/3D modeling. A unique set of mobile, desktop and cloud applications for photogrammetry.
Verizon x Skyward x Parrot
4G LTE enabled drone solution in the United States. The first of its kind ANAFI Ai robotic drone connected to the Verizon 4G LTE network with Skyward software pre-installed. Opens the way for near real-time data transfer, remote deployment and non-line-of-sight flights.
Skyward × Parrot
Integration and learning within the ANAFI potential. Aviation management platform including airspace, access to LAANC, and training, equipment and connectivity to deploy an enterprise drone fleet.
DroneSense × Parrot
Build, manage and scale your drone programs. Public safety drone professionals can take advantage of DroneSense’s full suite of capabilities, specifically designed for the needs of first responders.
Partners in the Parrot ecosystem
Parrot Affiliate Program
The developer offers to expand the capabilities of its drone program by integrating its SDK.
The developer notes that it does not collect any data without the consent of users. The decision whether or not to transfer data to the Parrot infrastructure rests solely with the users themselves. The data hosted by Parrot allows the user to synchronize flight data and flight plans between different devices, and facilitates support and enables Parrot to improve its products.
ANAFI Ai complies with the European Union General Data Protection Regulation (GDPR) and goes further, for example, it allows you to delete all data in 1 click, thus giving users the easiest control possible. This one-click issue is resolved in the FreeFlight7 mobile app or in the privacy settings of your Parrot.Cloud account. Thus, users at any time can not only stop exchanging data, but also easily request their deletion.
When ANAFI Ai is connected to the Skycontroller 4 via 4G, the Parrot infrastructure is used to pair the drone and remote controller. If the user is not logged into the Parrot.Cloud account, he can still use the 4G connection with a unique temporary account. When using the Parrot infrastructure for 4G pairing, the video is encrypted using a key agreed between the aircraft and the remote controller, Parrot does not have access to unencrypted videos.
FIPS140‑2 compliant and CC EAL5+ Secure Element Certified
The ANAFI Ai incorporates a Wisekey security element that is NIST FIPS140‑2 Level 3 compliant and Common Criteria EAL5+ certified. A similar safety element is also built into the Skycontroller 4 control equipment.
Security element functions:
- Performs cryptographic operations
- Stores and protects confidential information
It uses a personal ECDSA key with domain parameters P521, unique for each drone. It cannot be retrieved from a security element. And the certificate associated with this key is signed by a certificate authority.
Wisekey protects the integrity of the firmware, provides unique drone identification for 4G pairing and strong authentication, and uniquely digitally signs photos taken by the drone.
Secure 4G connection and strong authentication
When the user turns on the 4G connection, the standard Wi-Fi connection is primarily used, which is used for the process of secure pairing of devices. During this process, the user securely confirms that he is connected to a particular drone. Thanks to the ANAFI Ai Secure Element, it can do this without entering a password inside the drone.
Next, the Parrot servers register the connection between the user and the drone. When the Wi-Fi connection between the user and the drone is lost, ANAFI Ai will automatically switch to 4G connection. ANAFI Ai performs strong authentication against Parrot servers using its private key stored on the Secure Element. Parrot servers look for related users and provide pairing between ANAFI Ai and Skycontroller 4.
To protect the drone control and video streams coming to the Skycontroller 4, ANAFI Ai supports TLS, DTLS and SRTP protocols.
Secure provisioning and updating
The sequence of the drone boot process is secure: the system verifies that it is using the Parrot software and that the software has not been tampered with. A security check is performed at each initialization. The Update Service also controls the digital signature of software updates.
Setting up custom keys on the Secure Element
ANAFI Ai users have access to a special Secure Element operator account. This account is used to configure keys that are relevant for this user. Users can configure the public keys of flight providers they trust in the Secure Element. ANAFI Ai will only perform flight missions that are signed with these keys. This process prevents attackers from performing malicious flight missions on the drone.
Photos digitally signed
ANAFI Ai’s Secure Element can digitally sign pictures taken by a drone. This signature is proof that:
- Said signed image was taken by said unmanned aerial vehicle.
- Neither the image itself nor its metadata has been processed (whether voluntarily or not) — metadata, also known as EXIF and XMP, contains information about the date, time, and location of the image.
In other words, a digital signature protects all data related to an image, including the location and time it was taken and by which ANAFI Ai drone.
Users, as well as partners offering software solutions using drone photos, can verify the digital signature of ANAFI Ai photos either with the drone certificate or through a public key catalog provided by Parrot.
Transparency and continuous security checks with Bug bounty
Whenever possible, Parrot uses standard protocols and file formats. There is no obfuscated code, no hidden features. This allows the user to understand how Parrot products work and to test their safety. In addition, OpenFlight, the software used to control the drone, is open source, so users have full control.
In April 2021, Parrot launched the “Bug Bounty” program with YesWeHack, Europe’s first crowdsourced security platform. Through this partnership, Parrot is leveraging YesWeHack’s extensive cybersecurity research community to identify potential vulnerabilities in its drones, mobile apps and web services.
The Bug Bounty program takes place in two stages:
The private programs initially provide exclusive access to select security researchers and include future Parrot drone models. The experience and diverse skills of the researchers will confirm the high level of security of the products before they go to market, which will help improve the security of Parrot users and protect their data.
After this first phase of the private Bug Bounty program and once commercialized, the products move into the public program. Their security is then rigorously reviewed by the entire YesWeHack community of over 22,000 cybersecurity researchers.
The Parrot Cloud allows users who choose to share their data to manage flight and fleet data, as well as multimedia data received by their drones.
The Parrot cloud collects 4 types of data:
“Static” (product data):
- Drone serial number
- Battery serial number
- Firmware Version for Drone and Battery
- Aircraft hardware version and battery
- Device Model
- FreeFlight 7 release version
- Alerts: battery, autopilot, sensors
- Connection: connect/disconnect, start streaming, interference warning, weak signal
- Camera: streaming statistics, settings changes
- Flight: state change (takeoff, landing, hovering, etc.), flight task activation (flight plan, photogrammetry)
- Timelapse snapshots (once every 2 minutes)
- Deep learning (matching more objects, terrain for improved flight autonomy, tracking, avoiding obstacles)
- Stereo vision (depth map)
- Event triggered images
- Beginning and end of precise hovering formulations, precise landing
- drone crash
- When transferring faces are automatically blurred
End use of collected data
Parrot collects and uses data only from customers who have agreed to share it in order to improve the quality of their products.
Preventive maintenance: our tools collect all information related to missions (mission type, takeoff and landing times, number of missions, drone location, flight speed, flight plan and AirSDK settings). This allows you to receive accurate information about the status of the ANAFI Ai drone fleet (as well as their controllers and batteries) in real time.
Corrective maintenance: The collected information is useful for quickly determining the status of a particular drone or battery.
Improving artificial intelligence (AI)
The artificial intelligence elements that ANAFI Ai is equipped with (PeleeNet, convolutional networks, etc.) offer users unsurpassed services and features: obstacle avoidance, target following, multiple flight modes. The quality of AI depends on the quantity and quality of the collected data (images and videos): this data feeds machine learning. In this regard, data quality is not the only decisive element: the metadata associated with these data is also of fundamental importance. For this reason, our tool collects images and metadata on a regular basis and depending on events, for a total of 30 to 50 MB per minute.
Drives and aerodynamics
CFD image of ANAFI Ai propeller blades
The new biomimicry propeller blades have a leading edge that resembles the shape of humpback whale fins. This approach made it possible to increase the propulsion efficiency of the power plant, which at the output provided an increase in thrust at the same rotation speed. This effect is comparable to an increase in the rotor diameter.
Acoustic noise is also reduced, especially tonal noise coming from the leading edge. Therefore ANAFI Ai is quieter [71.5 дБ SPL (A) на высоте 1 м]than Skydio 2 [76.4 дБ SPL (A) на высоте 1 м].
- Flight time over 32 minutes
- Thanks to the optimized aerodynamic characteristics of the fuselage and the ANAFI Ai power plant, the maximum speed in forward flight is 61 km/h, in side flight and rearward flight 58 km/h.
- Max. wind resistance 12.7 m/s.
- Thanks to the high torque efficiency of the motor/propeller and the high autonomy of the battery, the range is 22.5 km (at a constant speed of 50 km/h in calm weather).
CFD images of ANAFI Ai beams
To ensure a safe flight, ANAFI Ai is equipped with:
- 2 × IMUs (ICM-40609‑D and ICM42605)
- Magnetometer LIS2MDL
- GPS module UBX-M8030
- TI OPT3101 time-of-flight (ToF)
- Barometer LPS22HB
- Vertical Camera
Flight IMU: ICM-40609‑D
- 3 axis gyroscope
- Range: ± 2000°/s
- Resolution: 16.4 LSB/°/s
- Offset/accuracy: ± 0.05°/s (after thermal and dynamic calibration)
- 3‑axis accelerometer
- Range: ±16g
- Resolution: 2.048 LSB/mg
- Offset/accuracy: ± 0.5 mg (XY) ± 1 mg (Z) (after thermal and dynamic calibration)
- Temperature control: controlled heating system in relation to the ambient temperature, stabilized within: ± 0.15°C
- Measurement frequency: 2 kHz
- Range: ±49.152G
- Resolution: 1.5mG
- Offset/accuracy: ± 15 mG (after compensation, at maximum motor speed)
- Measurement frequency: 100 Hz
Barometer: LPS22HB 1
- Range: 260 to 1260 hPa
- Resolution: 0.0002 hPa
- Offset/accuracy: ± 0.1 hPa
- Temperature control: controlled heating system in relation to the ambient temperature, stabilized within: ± 0.2°C
- Measurement frequency: 75 Hz
- Measurement noise: 20cm RMS
GNSS: UBX-M8030 1
- 25 x 25 x 4mm ceramic patch antenna with +2dB gain improvement over ANAFI 1
- Sensitivity: cold start ‑148 dBm / tracking and navigation: ‑167 dBm
- Time-To-First-Fix: 40 seconds
- Accuracy/Accuracy: Position (standard deviation 1.4 m), Velocity (standard deviation 0.5 m/s)
- Matrix format: 1/6 inch
- Resolution: 640 × 480 pixels
- Global shutter sensor
- black and white
- FOV: Horizontal FOV: 53.7°/Vertical FOV: 41.5°
- Focal length: 2.8 mm
- Measurement of the speed of movement of the optical flow on the ground at 60 Hz
- Point of interest calculation for fine hovering at 15 Hz and fine landing at 5 Hz
ToF: TI OPT3101
- Range: 0–15m
- Resolution: 0.3mm
- Accuracy: ± 2 cm (after calibration)
- Measurement frequency: 64 Hz
Vertical Camera IMU: ICM-42605
- 3 axis gyroscope
- Range: ±2000°/s
- Resolution: 16.4 LSB/°/s
- Offset/accuracy: ± 0.1 °/s (after dynamic calibration)
- 3‑axis accelerometer
- Range: ±16g
- Resolution: 2,048 LSB/mg
- Offset/accuracy: ± 2.0 mg (XY) ± 5.0 mg (Z) — after dynamic calibration
- Measurement frequency: 1 kHz
- Hardware synchronization with vertical camera, accuracy: 1 µs
The ANAFI Ai flight controller provides simple and intuitive piloting: no training is required to operate it. It allows you to automate many flight modes (Flight Plan, Cameraman, Hand take-off, Smart RTH). Sensor fusion algorithms combine data from all sensors to estimate the attitude, altitude, position, and velocity of ANAFI Ai.
Condition assessment is essential for the proper functioning of drones. Quadcopters are inherently unstable when the flight controller is used in open loop; to easily control them, not to mention autonomous control, it is necessary to stabilize them using closed-loop control algorithms. These algorithms calculate and send the commands needed by the ANAFI Ai to the engines to achieve the desired trajectories.
In the absence of a GPS signal, ANAFI Ai relies heavily on vertical camera measurements to estimate speed and position. The vertical camera performance is determined by two main algorithms:
- Optical flow for speed estimation
- Detection and matching of key points for position estimation
The vertical camera algorithms can work in low light conditions due to the fact that ANAFI Ai is equipped with a pair of LED lights located next to the vertical camera. They allow the drone to maintain stability, especially when flying indoors or in conditions without GPS, at a height of less than 5 m above the ground. The power of the LED lights adapts automatically, depending on the needs of the algorithm.
- Swiveling sensing system with wide field of view
- Selection of the depth of the surrounding space based on stereo matching and depth by motion
- Representing the Environment as an Infill Grid
- Autonomous detection and avoidance of obstacles at speeds up to 29 km/h
This chapter details the sensors, hardware, and algorithms used by the ANAFI Ai to enable autonomous flight. It is organized as follows:
- Detailed description of the ANAFI Ai perception system
- Perception algorithms used to reconstruct the 3D environment surrounding drones
- Replanning and avoiding obstacles
Perceptual system strategy
The perception of the 3D environment is a key ability to achieve autonomous flight, especially in confined spaces. It is a condition for guaranteed detection and avoidance of obstacles, which reduces the load on the drone operator, increases the success of the mission and ensures the safety of the aircraft.
Unleashing the full potential of a flying camera that can move freely and rotate in all directions without restriction requires an efficient sensing solution. In particular, the perception system must be able to receive information about the environment in directions that correspond to translational movement in flight — regardless of the orientation of the camera.
ANAFI Ai relies on a unique technical solution based on two mechanical suspensions to separate the orientation of the main camera and the perception system:
- The main camera is mounted on a 3‑axis gimbal, which makes its 3D orientation independent of the drone’s orientation.
- The perception system is mounted on a single-axis gimbal — connected to the drone’s yaw movement, it can be oriented in any direction.
Dual ANAFI Ai stabilizer for perception and visualization.
The tilt axes of the two gimbals are collinear and combined to achieve an ultra-compact design.
Thanks to this solution, it is possible to direct the main camera and the perception system in two different directions. This design avoids the use of costly cameras on the sides, top, bottom and rear of the drone while providing a large available field of view for the sensing system.
This section is organized as follows:
- Detailed information about the sensors used for the sensing system
- Specifications for both the main camera gimbal and the sensing system gimbal
- Perception System Orientation Strategies to Harness the Potential of the Dual Suspension Design
The perception system is based on a pair of identical cameras with the same pitch axis.
1‑axis mechanical joint of ANAFI Ai perception system.
The specifications of the sensors are as follows:
- Model: Onsemi AR0144CSSM28SUD20
- Color: monochrome
- Resolution: 1280×800 pixels
- Frame rate: 30fps
- global shutter
- Total horizontal field of view: 118° (110° used for perception)
- Total vertical field of view: 72° (62° used for perception)
- Focal length: 1.47 mm (0.039 inches — 492.94610 pixels)
- Aperture: f/2.7
The technical characteristics of the stereo pair are as follows:
- Common Pitch Axis
- Baseline/Distance: 62 mm (2.44 inches)
- Synchronous capture at 30fps
The main camera’s mechanical gimbal is a 3‑axis pitch-roll-yaw mechanical hinge with the following features:
- Pitch Limiters: ‑116°/+176°
- Roll limiters: +/- 36°
- Yaw Limiters: +/- 48°
The sensing system mechanical gimbal is a single-axis gimbal with the following characteristics:
- Pitch limiters: ‑107°/+204°
- Travel time from one end stop to another: 300 ms
The perception system has 311° travel (of which 296° is not masked by the body of the drone), which allows for rear perception as well.
Instantaneous vertical field of view and limiters of the ANAFI Ai perception system.
The system has been designed in such a way that:
- Propeller blades do not fall into the field of view of the main camera
- The main camera does not cover the field of view of the perception system
- Main camera and sensing system can be fully folded back to protect lenses, during storage or in case of an in-flight emergency
Horizontal field of view of the ANAFI Ai perception system.
When leaning back, the perception system moves to the highest position, thereby providing a clear view.
Perception of ANAFI Ai in fully reclined position for backward flight.
Reconstruction of the 3D environment for autonomous flight is performed in two stages:
- Extracting depth information from perception as depth maps
- Combining depth map data into a 3D infill grid
Two methods are used to obtain depth maps from perception sensors:
- Depth based on stereo matching
- Depth from motion
Depth from Stereo Match
The main method for extracting depth information is based on parallax between the two stereo cameras of the perception system. By photographing the environment in the same direction but from two different positions, objects in the field of view of the perceptual system appear in different positions in the images taken by the two cameras. The closer the object, the greater the difference in position.
Thus, the strategy is to determine the points in the images taken by the left and right stereo cameras corresponding to the same object in the field of view of the perceptual system, and measure the difference in the position of these points in the two images. This difference is called disparity and is measured in terms of pixels.
An illustration of the principle of stereo vision — a red 3D dot is in different positions on the left and right images.
The disparity can then be related to the depth of each of these points using the following relationship: depth = focal (focal length) * baseline (baseline) / disparity (disparity), where the depth and baseline are expressed in the same units, and the focal length and disparity are expressed in number of pixels.
The result of the calculation takes the form of a 176 × 90 pixel depth map, for which the value of each pixel corresponds to a depth in meters. The depth map is updated at a rate of 30 Hz.
An example of an image taken with the right camera of the ANAFI Ai sensing system (left) and the corresponding depth obtained using stereo mapping (right). The colormap transitions from red (Closer) to purple (Farther) — white means “Out of reach”.
The immediate result of this is that the depth measured by this method is discretized, since disparity can only take on discrete values (number of pixels). A 3D point that is sufficiently far from the perceptual system to produce a theoretical disparity of less than one pixel would be considered infinite, since the corresponding actual, discrete disparity would be 0. The accuracy of the stereo matching method decreases with increasing distance, although there are methods to reduce this phenomenon by achieve subpixel sampling.
In addition, the disparity diverges as depth approaches zero. Since the number of pixels in images is limited, the disparity value is also limited. As a consequence, there is a minimum depth at which the perceptual system is blind. This minimum depth value is 36 cm for ANAFI Ai.
About calibration: each pair of stereo cameras is factory calibrated to accurately measure small discrepancies that may exist between two cameras and compensate for them in the onboard depth calculation.
The user can also re-calibrate a pair of stereo cameras using the test pattern supplied with the drone. In particular, to some extent, the drone is able to detect potential calibration errors that may occur during its lifetime. In this case, the aircraft software will attempt to adjust and compensate for them, and if it fails, a notification will appear asking you to recalibrate.
Depth from motion
Drone movement can also be used to collect images of the environment from different angles and thus recover depth information. This method is called motion depth or monocular perception because a single moving camera is enough to collect depth information.
The principle of operation is similar to stereo vision, but instead of comparing images of the environment obtained by different observers at the same time, perception compares images of the environment obtained by the same observer at different times. If the drone is moving, then images from this unique observer will be taken from different angles. Knowing the position at which each frame was taken, it is possible to triangulate points corresponding to the same feature in different images and return them to 3D.
The output is a three-dimensional point cloud containing up to 500 points for ANAFI Ai, generated at a frequency of 10 Hz.
An example of a point cloud generated from motion depth — the colormap transitions from red (Nearer) to purple (Farther).
The motion-based depth algorithm in ANAFI Ai typically generates less information (sparse point cloud) than the stereo matching algorithm and requires the aircraft to move to collect information. In addition, this algorithm cannot extract information in the exact direction of motion (at least for live broadcasts), because in this direction the objects in the images look almost stationary (expansion focus).
However, it also has a better detection range (theoretically infinite range) than the stereo matching method.
Depth information derived from the stereo and monocular perception algorithms is integrated into the fill grid. This grid discretizes the 3D environment into 3D cubes called voxels. Each voxel is assigned a probability of being occupied by an obstacle or, conversely, being free of an obstacle.
A ray transmission algorithm is used to integrate depth information into the infill mesh. For each pixel of the depth map obtained as a result of stereo matching, it is converted to a three-dimensional point, and for each point of the point cloud — to the depth obtained as a result of movement:
- In the fill grid, a ray is drawn from the position of the perception system to the position of the 3D point.
- The probability of occupancy of a voxel containing a 3D point increases.
- The probability of occupancy of all voxels crossed by the ray, except for the one containing the 3D point, decreases.
In this way, the reticle acts as a temporal filter for depth information, absorbing any potential depth measurement noise, and as a memory of previous measurements, allowing navigation in complex environments even in the absence of a continuous 360° field of view of the perception system.
Fill grid example. Overlaid on the right stereo camera view are voxels with a high degree of confidence that they are occupied, ranging in color from red (Near) to purple (Far).
The infill grid is the basis for the motion planning algorithms used by ANAFI Ai for autonomous flight and obstacle avoidance.
With the knowledge of the 3D environment of the drone’s environment stored in the infill grid, it is possible to provide the ANAFI Ai with the ability to avoid obstacles. This provides significant additional safety for autonomous missions, but is also useful for manual flight, especially if the line of sight between the pilot and the drone is degraded.
Every 30 ms, ANAFI Ai predicts what the nominal flight path will be on a short time horizon in the future. This prediction is derived from links sent by the user, whether it be pilot commands from the console, waypoints to join a flight plan, or an input trajectory. Then, using the simulated drone internal model, the replanning algorithm calculates the smallest possible corrections to this predicted nominal trajectory that make it collision-free and feasible for the drone.
An example of a corrected trajectory computed by the obstacle avoidance algorithm in response to a reference trajectory colliding with a tree.
The ANAFI Ai obstacle avoidance system has been designed to operate at speeds up to:
- Level flight: 29 km/h
- Climb: 14 km/h
- Descent: 11 km/h
Avoidance performance is limited in rain or strong wind conditions, in low light conditions, or in conditions of impaired satellite navigation. In addition, before flying, you must make sure that the lenses of the perception system are clean.
The Air SDK (see SDK section) allows developers to access every drone sensor, camera, connection interface, and standalone function. Therefore, they can customize the behavior of the drone to create flight missions. Each flight mission contains a set of basic behaviors or modes:
- On the ground: behavior when the motors are stopped, e.g. sensor calibration.
- Takeoff: various takeoff strategies
- Hangup: fixed point hold
- Flight: manual and autonomous flight functions
- Landing: various landing strategies
- Critical: when a critical condition is detected
Custom flight missions can create new behaviors or reuse them from the default mission.
Price and availability
According to the latest official information, ANAFI Ai will be available for purchase from January 2022. The cost of the drone will be determined by the equipment. The standard kit will cost the consumer $5,476 (tax included).
Documentation for download
Documentation for familiarization with the product from the developer:
- Download full technical documentation from the developer
- Download the product specification from the developer
Top ANAFI Ai Reviews from Developer and Users
Unpacking and first flight.
Testing 4G connectivity on Parrot Anafi Ai.
Demonstration of the unique obstacle avoidance system based on mobile stereo cameras from Parrot.
Drone takeoff and landing test from a moving vehicle.
Installing a 4G SIM card.
Test flight of a drone at a distance with a 4G connection. The total flight time was 29 minutes at an average horizontal flight speed of 58 km/h (16 m/s). During this time, the drone was able to overcome 27 km. You can also notice that the flight was carried out in strong wind conditions, which the drone system constantly warned about.
3D house modeling in 1 click.
An example of a drone in 3D mapping mode.
5 km of power lines are mapped in 3D.
3D mapping of the Italian city of Positano.
To realize this pharaonic project, Parrot drew on the experience of Erwan Renaudin of the French company Logiroad, an expert in the creation of digital copies of cities. An ANAFI Ai drone has mapped 100 acres of an urban canyon. In total, the drone took 4,800 48-megapixel photos. All flights were carried out in 4G mode to avoid interference in the city. To create the final 3D model, Erwan had to use three different software: Pix4Dmapper, Metashape and Reality Capture. The final 3D mesh consists of 800 million triangles.
The flight of the ANAFI Ai to the top of the 368-meter active TV tower Berliner Fernsehturm, during which the confident operation of the machine is demonstrated in conditions of heavy interference.
4G piloting in a metropolis.
360-degree photo by ANAFI Ai.
Automatic flight and shooting along a planned route.
Demonstration of automatic takeoff and landing on a moving ship.