Cluster unmanned aerial vehicle obstacle avoidance device

Abstract

The utility model provides a cluster unmanned aerial vehicle obstacle avoidance device, and relates to the technical field of three-dimensional position control. The device comprises a base, a binocular vision sensor is arranged on the base, a millimeter-wave radar is arranged on the base, a support is arranged on the base, the millimeter-wave radar is hinged to the support, and a driving source for driving the millimeter-wave radar to swing is arranged on the support. According to the utility model, the advantages of two different sensors, namely the millimeter-wave radar and the binocular vision sensor, are integrated, so that the environmental adaptability and the recognition precision are improved.

Description

Technical Field

[0001] The utility model relates to the technical field of three-dimensional position control, and in particular to an obstacle avoidance device for a cluster of unmanned aerial vehicles. Background Art

[0002] In the context of the rapid development of UAV technology, swarm UAV systems have attracted widespread attention due to their efficient collaborative operation capabilities. However, the obstacle avoidance problem of swarm UAVs in complex environments has always been a key technical bottleneck restricting their widespread application. At present, although the obstacle avoidance technology of UAVs has improved the autonomous flight capability of UAVs to a certain extent, there are still many defects and deficiencies in practical applications.

[0003] In the prior art, the sensors used for obstacle avoidance are single, generally infrared sensors, ultrasonic sensors or laser radars. Infrared sensors are easily disturbed by ambient light, especially in strong sunlight or dark environments, where the detection accuracy is significantly reduced. In addition, the detection effect on black or dark objects is poor, which is easy to cause missed detection; ultrasonic sensors have a limited range and are usually only suitable for short-range obstacle avoidance. In severe weather conditions (such as strong winds, rain and snow), their performance will be greatly reduced, affecting the obstacle avoidance effect; although laser radars are highly accurate, they are expensive and are not suitable for large-scale cluster drone systems. At the same time, laser radars are easily disturbed in severe weather such as rain, snow, and smoke, which affects the detection results. Therefore, the current single sensor has limitations, is difficult to adapt to complex and changing environmental conditions, and has the problem of poor environmental adaptability. Utility Model Content

[0004] The purpose of the utility model is to develop a cluster UAV obstacle avoidance device which improves environmental adaptability and recognition accuracy by integrating the advantages of two different sensors, a millimeter-wave radar and a binocular vision sensor.

[0005] The utility model is achieved through the following technical solutions:

[0006] A cluster UAV obstacle avoidance device, comprising:

[0007] Pedestal;

[0008] A binocular vision sensor is arranged on the base;

[0009] A millimeter wave radar is mounted on a base;

[0010] Wherein, a support is provided on the base, the millimeter-wave radar is hinged on the support, and a driving source for driving the millimeter-wave radar to swing is provided on the support.

[0011] Optionally, the binocular vision sensor includes a left camera and a right camera arranged on the same side wall of a base, and the millimeter wave radar is arranged between the left camera and the right camera.

[0012] Optionally, the support includes two triangular support plates arranged perpendicular to the base and parallel to each other, a swivel seat is rotatably connected between the two support plates, the millimeter wave radar is arranged on the swivel seat, and a driving motor is provided on the support plate as a driving source to drive the swivel seat to rotate.

[0013] Optionally, the support is arranged on a side wall of the base above the middle of the left-eye camera and the right-eye camera, and the support plate is parallel to the arrangement trajectory of the left-eye camera and the right-eye camera.

[0014] Optionally, the millimeter wave radar includes a millimeter wave radar base plate arranged on the swivel seat, and the millimeter wave radar base plate is provided with a transceiver antenna and a radome.

[0015] Optionally, a posture sensor array is provided on a base at the lower part between the left-eye camera and the right-eye camera, and the posture sensor array includes three IMU measurement units.

[0016] Optionally, the base is in the shape of a rectangular plate, and the four corners of the base are rounded.

[0017] Optionally, the left camera and the right camera are arranged in the length direction of the base.

[0018] Optionally, the left camera and the right camera are high-precision cameras.

[0019] The beneficial effects of the utility model are:

[0020] The millimeter-wave radar of the utility model is responsible for providing rough obstacle information over a wide range, while the binocular vision sensor is responsible for fine identification of potential obstacle areas indicated by the radar. The two exchange data in real time through a high-speed data bus to ensure the synchronization and accuracy of information.

[0021] The utility model integrates a millimeter-wave radar and a binocular vision sensor. The millimeter-wave radar has strong penetration and is not affected by light, so it can work stably in adverse weather (such as rain, snow, fog and haze) and low-light conditions, and provide accurate obstacle distance information. The binocular vision sensor simulates the stereoscopic vision principle of the human eye and uses two cameras to obtain images of the scene from different perspectives. The binocular vision sensor calculates the parallax between the images obtained by the two cameras to generate a three-dimensional depth map of the scene, thereby accurately judging the shape, size and distance of the obstacle, achieving fine recognition and positioning of the obstacle, enhancing recognition accuracy, and avoiding missed detection or false detection caused by a single sensor. The transceiver antenna of the millimeter-wave radar is driven by a driving motor to perform a large-scale scan. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a structural diagram of the utility model;

[0024] Figure 2 This is a structural diagram of the utility model from another perspective.

[0025] Figure numerals: 1. base; 2. right camera; 3. left camera; 4. support plate; 5. drive motor; 6. millimeter wave radar bottom plate; 7. transceiver antenna; 8. IMU measurement unit; 9. swivel base. DETAILED DESCRIPTION

[0026] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0027] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0028] The embodiments of the present utility model are described in detail below with reference to the accompanying drawings.

[0029] like Figure 1 and Figure 2 As shown, the utility model discloses a cluster UAV obstacle avoidance device, including a base 1, the base 1 is in the shape of a rectangular plate, the four corners of the base 1 are rounded, and a binocular vision sensor and a millimeter wave radar are provided on the base 1.

[0030] The binocular vision sensor includes a left camera 3 and a right camera 2 arranged on the same side wall of the base 1. The left camera 3 and the right camera 2 are high-precision cameras, and the left camera 3 and the right camera 2 are arranged in the length direction of the base 1. The binocular vision sensor also includes an image processing system, which is responsible for converting raw image data into a three-dimensional depth map to provide accurate obstacle information for the obstacle avoidance algorithm.

[0031] A support is provided on the side wall of the base 1 above the middle of the left-eye camera 3 and the right-eye camera 2, a millimeter-wave radar is hinged on the support, and a driving source for driving the millimeter-wave radar to rotate is provided on the support.

[0032] The support comprises two triangular support plates 4 arranged perpendicular to the base 1 and parallel to each other, and the support plates 4 are arranged parallel to the length direction of the base 1. A rotating seat 9 is rotatably arranged between the two support plates 4, and a driving motor 5 is also arranged on one of the support plates 4 as a driving source to drive the rotating seat 9 to rotate.

[0033] The millimeter wave radar includes a millimeter wave radar base plate 6 disposed on a rotating seat 9, and a transceiver antenna 7 and a radome (not shown) are disposed on the millimeter wave radar base plate 6. The millimeter wave radar base plate 6 rotates with the rotating seat 9, so that the scanning range of the transceiver antenna 7 is increased.

[0034] A posture sensor array is provided on the base 1 at the lower part between the left camera 3 and the right camera 2, which includes three IMU measurement units 8 to provide high-precision posture measurement. The binocular vision sensor and the millimeter-wave radar share the posture sensor array.

[0035] When the drone is in flight, the millimeter-wave radar first performs a large-scale scan to quickly lock onto the location of potential obstacles. Then, the binocular vision sensor uses the information provided by the radar to collect and process high-resolution images of specific areas to accurately identify and locate obstacles. This "coarse-fine" combination of obstacle avoidance strategies greatly improves the drone's obstacle avoidance capabilities under different lighting and weather conditions.

[0036] Binocular vision sensors and millimeter-wave radars form a detection array, continuously collecting image data of the surrounding environment, and generating radar vision-enhanced depth maps in real time through the data processing system. This obstacle avoidance method based on three-dimensional depth maps effectively avoids missed detection or false detection problems caused by a single sensor. The data fusion algorithm receives and processes data from millimeter-wave radar and binocular vision sensors in real time. It first uses radar data for rapid scanning to lock potential obstacle areas, and then uses visual data for fine identification in the area to extract the precise location and shape information of obstacles. Finally, the algorithm generates obstacle avoidance instructions based on this information to control the flight path of the drone. This data fusion method greatly improves the efficiency and accuracy of information processing and ensures the real-time performance of the obstacle avoidance system.

[0037] The above embodiments are only preferred embodiments of the present utility model and are not limitations on the technical solutions of the present utility model. Any technical solution that can be implemented on the basis of the above embodiments without creative work should be deemed to fall within the scope of protection of the patent of the present utility model.

Claims

1. A cluster drone obstacle avoidance device, characterized in that: include: Pedestal; A binocular vision sensor is arranged on the base; A millimeter wave radar is mounted on a base; Wherein, a support is provided on the base, the millimeter-wave radar is hinged on the support, and a driving source for driving the millimeter-wave radar to swing is provided on the support.

2. The swarm drone obstacle avoidance device according to claim 1, characterized in that: The binocular vision sensor comprises a left camera and a right camera which are arranged on the same side wall of a base, and the millimeter wave radar is arranged between the left camera and the right camera.

3. The swarm drone obstacle avoidance device according to claim 2, characterized in that: The support includes two triangular support plates which are arranged perpendicular to the base and parallel to each other. A swivel seat is rotatably connected between the two support plates. The millimeter wave radar is arranged on the swivel seat. A driving motor is arranged on the support plate as a driving source to drive the swivel seat to rotate.

4. The swarm drone obstacle avoidance device according to claim 3, characterized in that: The support is arranged on the side wall of the base above the middle of the left-eye camera and the right-eye camera, and the support plate is parallel to the arrangement track of the left-eye camera and the right-eye camera.

5. The swarm drone obstacle avoidance device according to claim 3, characterized in that: The millimeter wave radar comprises a millimeter wave radar bottom plate arranged on the rotating seat, and a transceiver antenna and a radome are arranged on the millimeter wave radar bottom plate.

6. The swarm drone obstacle avoidance device according to claim 2, characterized in that: A posture sensor array is provided on a base at the lower part between the left-eye camera and the right-eye camera, and the posture sensor array includes three IMU measurement units.

7. The swarm drone obstacle avoidance device according to claim 2, characterized in that: The base is in the shape of a rectangular plate, and the four corners of the base are rounded.

8. The swarm drone obstacle avoidance device according to claim 7, characterized in that: The left camera and the right camera are arranged in the length direction of the base.

9. The swarm drone obstacle avoidance device according to claim 2, characterized in that: The left camera and the right camera are high-precision cameras.

Images