CN115758687A - Unmanned aerial vehicle autopilot simulation platform - Google Patents
Unmanned aerial vehicle autopilot simulation platform Download PDFInfo
- Publication number
- CN115758687A CN115758687A CN202211368750.5A CN202211368750A CN115758687A CN 115758687 A CN115758687 A CN 115758687A CN 202211368750 A CN202211368750 A CN 202211368750A CN 115758687 A CN115758687 A CN 115758687A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- simulation
- aerial vehicle
- sensor
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an unmanned aerial vehicle automatic driving simulation platform which comprises a scene management module, a sensor management module, a simulation module and a flight controller. The scene management module is used for preloading a plurality of simulation scenes and component models; the sensor management module is used for preloading a plurality of types of sensor models; the simulation module is embedded into a plurality of unmanned aerial vehicle models, renders a simulation scene used for displaying at present, loads an unmanned aerial vehicle model used in the simulation, binds a sensor model on the unmanned aerial vehicle model according to sensor parameters, outputs the position state of the unmanned aerial vehicle model and the acquired data of the sensor model to an automatic driving algorithm to be optimized, receives a control instruction fed back by the automatic driving algorithm and sends the control instruction to a flight controller; and the flight controller receives the control instruction and adjusts the state of the unmanned aerial vehicle model according to the control instruction. The unmanned aerial vehicle automatic driving simulation platform supports training and verification of a visual algorithm.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle simulation, and particularly relates to an unmanned aerial vehicle automatic driving simulation platform.
Background
In recent years, along with the continuous improvement of the intelligent degree of the unmanned aerial vehicle, the unmanned aerial vehicle is more and more widely used in civil activities and military activities. Based on this background, the importance of a good unmanned aerial vehicle universal simulation platform is increasingly emerging. Compared with other intelligent agents (unmanned vehicles and ground robots), the unmanned aerial vehicle is more complex in motion control, the problem of out-of-control and the like is more likely to occur, if the time and cost consumed by using a real unmanned aerial vehicle to optimize an automatic driving algorithm are too high, tests in open air are still limited by relevant regulations, and meanwhile, the problems of difficulty in reproduction of extreme weather conditions and scenes, potential hazards in test safety and the like exist, so that a reliable and efficient general simulation platform is of great importance in the unmanned aerial vehicle algorithm development and application process.
The unmanned aerial vehicle automatic driving simulation test platform has to have several core capabilities: the simulation test method comprises the steps of truly restoring a test scene, efficiently utilizing information system data to generate a simulation scene, carrying out cloud large-scale parallel acceleration and the like, so that the simulation test meets the closed loop of automatic driving perception, decision planning and control of a full stack algorithm. At present, the main bodies including science and technology companies, simulation software enterprises, colleges and universities, scientific research institutions and the like are actively invested in the construction of virtual simulation platforms.
Currently, existing simulation platforms of open-source unmanned aerial vehicles are not universally used in generality, and they support only one type of unmanned aerial vehicle, such as multiple rotor wings or fixed wings; or only support the simulation of one unmanned aerial vehicle. A general simulation platform of unmanned aerial vehicle that supports many machine polymorphic type many unmanned aerial vehicle is required in the industry.
The existing unmanned aerial vehicle simulation platform in the mainstream at present is developed based on Gazebo, has good physical and dynamic characteristics, but has poor 3D environment rendering effect and cannot support training and verification of a visual algorithm.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle automatic driving simulation platform which supports training and verification of a visual algorithm.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the utility model provides an unmanned aerial vehicle autopilot simulation platform, includes scene management module, sensor management module, simulation module and flight controller, wherein:
the scene management module is used for preloading a plurality of simulation scenes and component models and switching the simulation scenes currently used for displaying and switching the component models in the simulation scenes according to a user command;
the sensor management module is preloaded with the multi-type sensor models and used for increasing and decreasing the sensor models in the currently displayed simulation scene and adjusting sensor parameters according to user commands;
the simulation module is embedded into a plurality of unmanned aerial vehicle models, renders a simulation scene currently used for displaying, loads an unmanned aerial vehicle model used in the simulation, binds a sensor model on the unmanned aerial vehicle model according to sensor parameters, outputs the position state of the unmanned aerial vehicle model and the acquired data of the sensor model to an automatic driving algorithm to be optimized, receives a control instruction fed back by the automatic driving algorithm and sends the control instruction to the flight controller;
and the flight controller is used for receiving the control instruction sent by the simulation module and adjusting the position state of the unmanned aerial vehicle model according to the control instruction.
Several alternatives are provided below, but not as an additional limitation to the above general solution, but merely as a further addition or preference, each alternative being combinable individually for the above general solution or among several alternatives without technical or logical contradictions.
Preferably, the simulation scenario and the component model are created by the UE4 engine and sent to the scenario management module.
Preferably, the simulation scene includes the setting of weather and illumination intensity.
Preferably, the sensor management module is built based on a QT tool.
Preferably, the sensor model comprises a GPS, an IMU and a camera, and the image obtained by the drone model based on the camera comprises an RGB image, a depth map and an infrared map.
Preferably, the simulation module is implemented based on an AirSim simulator.
Preferably, multiple types of unmanned aerial vehicle dynamic models are configured in the AirSim simulator, and one or more same unmanned aerial vehicle dynamic models are arranged in one unmanned aerial vehicle model.
Preferably, the automatic driving algorithm to be optimized runs on an ROS operating system, and interacts with the AirSim simulator through the ROS operating system.
Preferably, the AirSim simulator sends the position state of the unmanned aerial vehicle model to the UE4 engine, and the UE4 engine performs rendering display of the unmanned aerial vehicle model in the simulation scene currently used for displaying.
Preferably, the simulation module interacts with the flight controller through a Mavlink communication protocol.
The unmanned aerial vehicle automatic driving simulation platform provided by the invention adopts a modular architecture, is high in reliability, is convenient to maintain and expand, has high-fidelity 3D environment rendering, multi-machine multi-type unmanned aerial vehicles, sensor models and automatic driving algorithm simulation, supports multi-rotor unmanned aerial vehicles, fixed wing unmanned aerial vehicles and composite wing unmanned aerial vehicles, contains all mainstream sensors (Camera, liDAR, radar, GPS, IMU and the like), and can support the automatic driving algorithm simulation in a visual environment.
Drawings
Fig. 1 is a schematic structural diagram of an unmanned aerial vehicle autopilot simulation platform according to the present invention;
fig. 2 is a schematic structural diagram of an unmanned aerial vehicle autopilot simulation platform according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
In order to overcome the defects of the simulation platform in the prior art, the embodiment provides an unmanned aerial vehicle automatic driving simulation platform (abbreviated as Javsim simulation platform), which adopts a modular architecture, has high reliability, is convenient to maintain and expand, supports multi-rotor unmanned aerial vehicles, fixed-wing unmanned aerial vehicles and compound-wing unmanned aerial vehicles, contains all mainstream sensors (Camera, liDAR, radar, GPS, IMU and the like), and can support the training and verification of a visual algorithm.
As shown in fig. 1, the unmanned aerial vehicle autopilot simulation platform of this embodiment includes: the system comprises a scene management module, a sensor management module, an analog simulation module and a flight controller, wherein the modules are described in detail as follows.
1) Scene management module
In this embodiment, a plurality of simulation scenes and component models are preset in the Javsim simulation platform, a plurality of simulation scenes and component models are created by using a UE4 development platform (UE 4 engine) and packaged into the Javsim simulation platform, including virtual rendering simulation scenes such as cities, forests, warehouses, caves and the like and component models such as cylinders, fences, banners and the like, a user can quickly switch and select different scenes through an interactive interface to perform algorithm training evaluation, and the component models can be increased or decreased or replaced in a specified simulation scene according to the provided component models, so as to build a high-fidelity simulation scene environment.
The UE4 engine provides a powerful 3D virtual rendering platform, can verify the detection accuracy of the visual algorithm under different Weather and illumination, and can freely set different Weather conditions and intensities in the simulation scene through the use of UE4 secondary development tools (such as a sky atmosphere component, an Infinity Weather, a sky ball and the like), including: rain, snow, fog, wind speed, fallen leaves, dust and the like, the illumination intensity of a simulation scene is freely set by calling the sky ball in the UE4 engine, the vision is continuously strengthened by collecting simulation materials under different weather and illumination, the simulation clock can be called at the same time, the simulation rate is set, and the algorithm is rapidly trained and iterated.
According to the embodiment, a plurality of commonly used simulation scenes are created on the UE4 engine and embedded into the unmanned aerial vehicle simulation platform, the use difficulty of a user on the simulation platform is reduced, the user does not need to learn and develop the scenes by himself, and the user can use the simulation scenes by one key. It should be noted that, the scene management module of this embodiment preloads the simulation scene and the component model created based on the UE4 engine, provides an interactive interface for the user to freely set the simulation environment on the basis, and invokes the UE4 secondary development tool for the user to freely set the weather and the illumination intensity in the simulation scene. The scene management module focuses on the cooperation with the UE4 engine, and the specific interface design regarding the interactive interface is not a strict limitation.
2) Sensor management module
Javsim simulation platform utilizes the QT instrument to set up a set of self-defined sensor human-computer interaction interface of unmanned aerial vehicle as sensor management module, and the user can directly increase and decrease the sensor model in the simulation scene, including GPS, IMU, camera etc. can set up sensor parameter at sensor human-computer interaction interface simultaneously.
In Javsim simulation platform vision algorithm training, images available to the drone include: RGB images, depth maps, infrared maps, etc., and segmentation maps may also be obtained based on directly acquired images. Because the depth map and the segmentation map obtained by simulation in the simulator are perfect and can not completely simulate uncertainty in a real environment, the noise of the sensor can be increased by setting sensor parameters, including camera distortion, motion blur, picture random noise and the like, which are used for data acquisition matched with a real environment, and the robustness of a visual algorithm is enhanced.
The sensor configuration of unmanned aerial vehicle among the prior art is a more complicated matter now, and this embodiment provides sensor human-computer interaction interface based on the QT instrument, presets polymorphic type sensor model, and the user can dispose according to actual need.
QT is a cross-platform C + + gui library, which currently includes parts such as QT Creator, QT embedded, QT Designer rapid development tool, QT Linguist international tool, etc., QT supports all Linux/Unix systems and also supports Windows platform, providing application developers with functions required for establishing artistic-level gui. The embodiment mainly provides a mode for realizing the sensor configuration of the unmanned aerial vehicle through the human-computer interaction interface, and the specific interface design and display of the human-computer interaction interface of the sensor are not limited.
3) Simulation module
The simulation module of the embodiment is realized based on an AirSim simulator, the AirSim is a simulator for providing unmanned aerial vehicles and other autonomous mobile devices, a JavSim simulation platform supports software-in-the-loop Simulation (SITL) with currently mainstream flight controllers (PX 4 and ArduPilot), supports hardware-in-the-loop simulation (HITL) with Pixhawk, and can realize physical and visual real simulation. Based on the simulation environment provided by the UE4 engine, the AirSim simulator can render and restore a high-fidelity virtual environment, simulate shadow, reflection and other environments which are easy to interfere in the real world, and enable the unmanned aerial vehicle to train without the risk of the real world.
In the Javsim simulation platform, firstly, various types of unmanned aerial vehicle dynamic models are configured in an AirSim simulator, wherein the dynamic models comprise a multi-rotor wing unmanned aerial vehicle dynamic model, a fixed wing unmanned aerial vehicle dynamic model, a composite wing unmanned aerial vehicle dynamic model and the like. The limitation that only a four-rotor unmanned aerial vehicle dynamic model is configured in a traditional AirSim simulator is broken through, and the degree of freedom of unmanned aerial vehicle simulation in the simulation platform is improved.
And this embodiment is provided with one or more identical drone dynamics models within one drone model. The unmanned aerial vehicle dynamic model is copied to form a plurality of unmanned aerial vehicle dynamic models to realize simultaneous simulation of a plurality of unmanned aerial vehicles on the bottom layer logic of the unmanned aerial vehicle model, so that the unmanned aerial vehicle automatic driving simulation platform of the embodiment can test a cluster and a multi-unmanned aerial vehicle cooperative algorithm.
It is easy to understand that when the Javsim simulation platform loads the unmanned aerial vehicle model, the unmanned aerial vehicle model can be directly specified according to an algorithm, and the unmanned aerial vehicle model required to be used by the user through autonomous switching of a human-computer interaction interface can also be provided.
The simulation module renders a simulation scene used for displaying at present, loads an unmanned aerial vehicle model used for the simulation, binds a sensor model on the unmanned aerial vehicle model according to sensor parameters, outputs the position state of the unmanned aerial vehicle model and the acquired data of the sensor model to an automatic driving algorithm to be optimized, receives a control instruction fed back by the automatic driving algorithm, and sends the control instruction to the flight controller.
The AirSim simulator of the Javsim simulation platform is provided with rich API interfaces for verification training of a planning control algorithm, and a user can write programs including C + +, python and the like by using various programming languages, so that the state reading and flight control of the unmanned aerial vehicle are realized. The functions of the API interface comprise position control, speed control, attitude control, motor control and the like of the unmanned aerial vehicle, and PID parameter adjustment supporting motor rotation speed control and bottom layer flight control meets different task requirements from basic control to high maneuvering control and the like; meanwhile, the API interface can directly read the state (position, velocity, attitude, etc.) of the drone, including the true state, noisy state information measured by the sensors.
The automatic driving algorithm to be optimized runs on the ROS operating system, and interacts with the AirSim simulator through the ROS operating system. The ROS operating system provides a communication platform for the autonomous navigation and obstacle avoidance algorithm, and a user can configure the ROS operating system according to the Linux system of the user.
And, in order to visually observe the tracking effect of the automatic driving algorithm in real time when performing the simulation test, in one embodiment, the AirSim simulator transmits the position state of the unmanned aerial vehicle model to the UE4 engine, and the UE4 engine performs rendering display of the unmanned aerial vehicle model in the simulation scene currently used for display. The UE4 engine displays the acquired position state and prints the position state to a graphical interface, so that the movement track (position point) of the unmanned aerial vehicle is displayed, and the flight track of the unmanned aerial vehicle can be displayed.
4) Flight controller
In the embodiment, the flight controller is embedded into the unmanned aerial vehicle automatic driving simulation platform, so that software in-loop simulation and hardware in-loop simulation are realized based on the flight controller, and the automatic driving algorithm is convenient to migrate to a real unmanned aerial vehicle.
The Javsim simulation platform is configured with a Mavlik communication protocol (Micro Air Vehicle Link) and a flight controller for transmitting signals in real time, and the flight controller (such as PX 4/Pixhawk) can transmit control instructions for the unmanned aerial Vehicle and effectively control the operation attitude of the intelligent body in real time.
The unmanned aerial vehicle automatic driving simulation platform of the embodiment can simulate real world environment, simulate the physics and the dynamic characteristics of the unmanned aerial vehicle, and simultaneously support free increase and decrease, and modify the sensor types (a visual camera, a radar, an IMU and the like) and parameters for simulating the sensing environment. And based on UE4 engine designs in advance, edits, packs multinomial simulation environment and supplies the selection to improve the environmental simulation effect, simultaneously through reconfiguring to the kinematics of unmanned aerial vehicle dynamic model in the AirSim simulator, can realize supporting the simulation of unmanned aerial vehicle models of different models such as four rotors, six rotors, solid spin an organic whole, through the duplication to unmanned aerial vehicle dynamic model in the unmanned aerial vehicle model, realize the effect of multimachine simulation.
In the aspect of planning and control simulation, the acquired position information of the unmanned aerial vehicle is transmitted to a rendering scene of a UE4 engine through protocols such as TCP (transmission control protocol), and position coordinates are printed in real time through a drawing tool carried by the UE4 engine, so that the real-time display of the motion trail and the planned route of the unmanned aerial vehicle is realized. In addition, the real value of the unmanned body pose information, the collision information, the motor motion torque and the speed can be transmitted to the rear-end efficiency evaluation interface in real time, and the efficiency evaluation is carried out by comparing the real value of the unmanned body with the sensor fusion estimated value. Through the verification of the real-time unmanned aerial vehicle, the automatic driving algorithm trained by the Javsim simulation platform can be directly transferred to the real unmanned aerial vehicle for application.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples are merely illustrative of several embodiments of the present invention, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present invention should be subject to the appended claims.
Claims (10)
1. The utility model provides an unmanned aerial vehicle autopilot simulation platform which characterized in that, unmanned aerial vehicle autopilot simulation platform, including scene management module, sensor management module, simulation module and flight control ware, wherein:
the scene management module is used for preloading a plurality of simulation scenes and component models and switching the simulation scenes currently used for displaying and switching the component models in the simulation scenes according to a user command;
the sensor management module is preloaded with multiple types of sensor models and used for increasing and decreasing the sensor models in the currently displayed simulation scene and adjusting sensor parameters according to user commands;
the simulation module is embedded into a plurality of unmanned aerial vehicle models, renders a simulation scene used for displaying at present, loads an unmanned aerial vehicle model used in the simulation, binds a sensor model on the unmanned aerial vehicle model according to sensor parameters, outputs the position state of the unmanned aerial vehicle model and the acquired data of the sensor model to an automatic driving algorithm to be optimized, receives a control instruction fed back by the automatic driving algorithm and sends the control instruction to a flight controller;
and the flight controller is used for receiving the control instruction sent by the simulation module and adjusting the position state of the unmanned aerial vehicle model according to the control instruction.
2. The drone autopilot simulation platform of claim 1 wherein the simulation scenarios and component models are created by a UE4 engine and sent to the scenario management module.
3. The unmanned aerial vehicle autopilot simulation platform of claim 1 wherein the simulation scenario includes settings for weather and light intensity.
4. The unmanned aerial vehicle autopilot simulation platform of claim 1 wherein the sensor management module is built based on QT tools.
5. The drone autopilot simulation platform of claim 1 wherein the sensor model includes a GPS, an IMU and a camera, the camera-based images obtained by the drone model including an RGB image, a depth map and an infrared map.
6. The unmanned aerial vehicle autopilot simulation platform of claim 1 wherein the simulation module is implemented based on an AirSim simulator.
7. An unmanned aerial vehicle autopilot simulation platform as claimed in claim 6 wherein the AirSim simulator has disposed therein a plurality of types of unmanned aerial vehicle dynamics models, one unmanned aerial vehicle model having disposed therein one or more of the same unmanned aerial vehicle dynamics models.
8. An unmanned aerial vehicle autopilot simulation platform of claim 6 wherein the autopilot algorithm to be optimized runs on an ROS operating system through which it interacts with an AirSim simulator.
9. The drone autopilot simulation platform of claim 6 wherein the AirSim simulator sends the position status of the drone model to the UE4 engine, the UE4 engine rendering the drone model for display in the simulation scene currently being used for display.
10. The unmanned aerial vehicle autopilot simulation platform of claim 1 wherein the simulation module interacts with the flight controller via a Mavlink communication protocol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211368750.5A CN115758687A (en) | 2022-11-03 | 2022-11-03 | Unmanned aerial vehicle autopilot simulation platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211368750.5A CN115758687A (en) | 2022-11-03 | 2022-11-03 | Unmanned aerial vehicle autopilot simulation platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115758687A true CN115758687A (en) | 2023-03-07 |
Family
ID=85357567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211368750.5A Pending CN115758687A (en) | 2022-11-03 | 2022-11-03 | Unmanned aerial vehicle autopilot simulation platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115758687A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117313439A (en) * | 2023-11-30 | 2023-12-29 | 西安辰航卓越科技有限公司 | Multi-scene multi-machine type unmanned aerial vehicle simulation system |
-
2022
- 2022-11-03 CN CN202211368750.5A patent/CN115758687A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117313439A (en) * | 2023-11-30 | 2023-12-29 | 西安辰航卓越科技有限公司 | Multi-scene multi-machine type unmanned aerial vehicle simulation system |
| CN117313439B (en) * | 2023-11-30 | 2024-03-01 | 西安辰航卓越科技有限公司 | Multi-scene multi-machine type unmanned aerial vehicle simulation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Giernacki et al. | Crazyflie 2.0 quadrotor as a platform for research and education in robotics and control engineering | |
| US11276325B2 (en) | Systems and methods for flight simulation | |
| O'Kelly et al. | F1/10: An open-source autonomous cyber-physical platform | |
| CN110187700B (en) | Bionic flapping wing flying robot remote control system and method based on virtual reality | |
| CN102789171A (en) | Method and system for semi-physical simulation test of visual unmanned aerial vehicle flight control | |
| CN105006187A (en) | Civil unmanned aerial vehicle simulation training system | |
| CN109461342A (en) | A kind of tutoring system and its teaching method for unmanned motor vehicle | |
| WO2020053573A1 (en) | Control and navigation systems, pose optimisation, mapping, and localisation techniques | |
| CN113419518B (en) | VIL test platform based on VTS | |
| CN114488848A (en) | Unmanned aerial vehicle autonomous flight system and simulation experiment platform for indoor building space | |
| CN105632271B (en) | A kind of low-speed wind tunnel model flight tests ground simulation training system | |
| Bu et al. | General simulation platform for vision based UAV testing | |
| CN115758687A (en) | Unmanned aerial vehicle autopilot simulation platform | |
| CN110930811B (en) | System suitable for unmanned decision learning and training | |
| Doukhi et al. | Deep reinforcement learning for autonomous map-less navigation of a flying robot | |
| CN106828860B (en) | A kind of remote control system and its control method of stratospheric airship | |
| Mancini et al. | A framework for simulation and testing of uavs in cooperative scenarios | |
| CN114707304A (en) | Virtual-real combined multi-unmanned aerial vehicle perception avoidance verification system and method | |
| GB2581403A (en) | Pose optimisation, mapping, and localisation techniques | |
| CN117252011A (en) | Heterogeneous ground-air unmanned cluster simulation system construction method based on distributed architecture | |
| CN114936455A (en) | Unmanned aerial vehicle digital twin model construction method | |
| CN114397909A (en) | Automatic inspection method for small unmanned aerial vehicle of large airplane | |
| CN114741778A (en) | Unmanned ship autonomous capability testing system and method based on man-machine game | |
| Archdeacon et al. | Aerospace Cognitive Engineering Laboratory (ACELAB) Simulator for Electric Vertical Takeoff and Landing (eVOTL) Research and Development | |
| Zou et al. | Visual track system applied in quadrotor aerial robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |