Collision detection method, device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a collision detection method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring to-be-detected track information of a first mobile device; constructing a first time-space aggregate corresponding to the corresponding timestamp based on the position information of the first mobile device at each timestamp and the physical size information of the first mobile device; obtaining the existing track information of the second mobile device; performing collision detection processing on the first time-space aggregate and the second time-space aggregate corresponding to the same timestamp by adopting a collision detection strategy to obtain a collision detection result corresponding to the same timestamp; and generating a collision feedback result of the first mobile device according to the collision detection result corresponding to each timestamp in the plurality of timestamps. The embodiment of the invention can be applied to the traffic field, the automatic driving field and the like, and can effectively improve the accuracy of collision detection for the mobile equipment.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular, to a collision detection method, a collision detection device, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the rapid rise of intelligent transportation, various movable devices have been rapidly developed, and movable devices are applied to different application fields due to their advantages such as fearlessness of danger and flexibility.

[0003] It has been found through practice that movable devices are prone to collisions during operation; for example, when two movable devices are close to each other during operation, the movement of one movable device may have a negative impact on the other movable device. Therefore, how to accurately detect collision problems during the operation of movable platforms has become a research hotspot. Summary of the Invention

[0004] Embodiments of the present application provide a collision detection method, device, equipment, medium, and program product, which can effectively improve the accuracy of collision detection for movable devices.

[0005] On the one hand, embodiments of the present application provide a collision detection method, which includes:

[0006] Obtain the to-be-detected track information of the first movable device, where the to-be-detected track information includes: multiple timestamps of the track period corresponding to the first movable device, the position information of the first movable device at each timestamp, and the physical size information of the first movable device;

[0007] Based on the position information of the first movable device at each timestamp and the physical size information of the first movable device, construct a first spatio-temporal aggregate corresponding to the corresponding timestamp; the first spatio-temporal aggregate is a cubic space structure constructed based on the physical size information of the first movable device, the interference distance and the running range of the first movable device at the corresponding timestamp;

[0008] Obtain the existing track information of the second movable device; the existing track information includes: multiple timestamps of the track period corresponding to the second movable device and the second spatio-temporal aggregate corresponding to each timestamp;

[0009] Adopt a collision detection strategy to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp, and obtain a collision detection result corresponding to the same timestamp;

[0010] Generate a collision feedback result of the first movable device according to the collision detection result corresponding to each timestamp among multiple timestamps.

[0011] On the other hand, an embodiment of the present application provides a collision detection device, which includes:

[0012] An acquisition unit, configured to acquire the to-be-detected track information of a first movable device, where the to-be-detected track information includes: multiple timestamps of the track period corresponding to the first movable device, the position information of the first movable device at each timestamp, and the physical size information of the first movable device;

[0013] A processing unit, configured to construct a first spatio-temporal aggregate corresponding to the corresponding timestamp based on the position information of the first movable device at each timestamp and the physical size information of the first movable device; the first spatio-temporal aggregate is a cubic space structure constructed based on the physical size information of the first movable device, the interference distance and the operating range of the first movable device at the corresponding timestamp;

[0014] The processing unit is further configured to acquire the existing track information of a second movable device; the existing track information includes: multiple timestamps of the track period corresponding to the second movable device and the second spatio-temporal aggregate corresponding to each timestamp;

[0015] The processing unit is further configured to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp by using a collision detection strategy, and obtain a collision detection result corresponding to the same timestamp;

[0016] The processing unit is further configured to generate a collision feedback result of the first movable device according to the collision detection result corresponding to each timestamp among multiple timestamps.

[0017] In one implementation, the to-be-detected track information further includes the speed information and the attitude information of the first movable device at each timestamp; any timestamp among the multiple timestamps of the track period corresponding to the first movable device is represented as the T-th timestamp; T is an integer greater than zero;

[0018] When the processing unit constructs the first spatio-temporal aggregate corresponding to the corresponding timestamp based on the position information of the first movable device at each of the timestamps and the physical size information of the first movable device, specifically:

[0019] Regarding the first movable device as a particle, and constructing a core layer corresponding to the T-th timestamp according to the position information and the speed information of the particle at the T-th timestamp, and the first time period and the second time period adjacent to the T-th timestamp of the particle;

[0020] Based on the core layer corresponding to the T-th timestamp, the attitude information of the first movable device at the T-th timestamp, and the physical size information of the first movable device, constructing a physical layer corresponding to the T-th timestamp;

[0021] Based on the interference distance of the physical layer and the first movable device to the surrounding environment, construct an interference layer corresponding to the T-th timestamp; the interference layer corresponding to the T-th timestamp is the first spatio-temporal aggregate of the first movable device at the T-th timestamp.

[0022] In one implementation, the interference layer includes a physical layer, and the physical layer includes a core layer; where:

[0023] The core layer is a cubic space structure composed of all spatial positions that the first movable device can reach at the T-th timestamp when the first movable device is used as a particle for trajectory planning;

[0024] The physical layer is a cubic space structure that can enclose the outer contour of the first movable device when the first movable device moves to the edge of the core layer;

[0025] The interference layer is a cubic space structure that can enclose the interference distance generated by the first movable device to the surrounding environment when the first movable device moves to the edge of the core layer.

[0026] In one implementation, any timestamp among multiple timestamps of the trajectory period corresponding to the first movable device is represented as the T-th timestamp; the processing unit is used to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp by using a collision detection strategy, and when obtaining the collision detection result corresponding to the same timestamp, it is specifically used for:

[0027] Adopt a collision detection strategy to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp to obtain a particle detection result;

[0028] If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is less than or equal to a preset distance threshold, then perform vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp;

[0029] Among them, the collision detection result corresponding to the T-th timestamp is used to indicate: the first movable device and the second movable device collide at the T-th timestamp, or do not collide at the T-th timestamp.

[0030] In one implementation, the representation form of the position information is in the form of spatial coordinates, and the spatial coordinates include a first coordinate value, a second coordinate value, and a third coordinate value; the processing unit is used to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp by using a collision detection strategy, and when obtaining a particle detection result, it is specifically used for:

[0031] Adopt a collision detection strategy to compare the first coordinate value of the first movable device at the T-th timestamp with the first coordinate value of the second movable device at the T-th timestamp to obtain a first comparison sub-result;

[0032] Adopt a collision detection strategy to compare the second coordinate value of the first movable device at the T-th timestamp with the second coordinate value of the second movable device at the T-th timestamp to obtain a second comparison sub-result;

[0033] Adopt a collision detection strategy to compare the third coordinate value of the first movable device at the T-th timestamp with the third coordinate value of the second movable device at the T-th timestamp to obtain a third comparison sub-result;

[0034] Generate a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result.

[0035] In one implementation, each coordinate value in the spatial position corresponds to a preset distance threshold; when the processing unit generates a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result, it is specifically used for:

[0036] If any one of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is less than the corresponding preset distance threshold, then generate a particle detection result; the particle detection result indicates that the first movable device and the second movable device collide at the T-th timestamp; or,

[0037] If each of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is greater than or equal to the corresponding preset distance threshold, then generate a particle detection result; the particle detection result indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0038] In one implementation, the track information to be detected of the first movable device further includes the attitude information of the first movable device at the T-th timestamp; when the processing unit performs vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp, it is specifically used for:

[0039] According to the position information of the first movable device at the T-th timestamp, the physical size information of the first movable device, and the attitude information of the first movable device at the T-th timestamp, calculate the vertex coordinates of the extreme vertices in the first spatio-temporal aggregate corresponding to the T-th timestamp;

[0040] Obtain the vertex coordinates of the extreme vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp;

[0041] The vertex coordinates of the extreme value vertices in the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the vertex coordinates of the extreme value vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp are calculated using the extreme value check rule, and the collision detection result corresponding to the T-th timestamp is obtained.

[0042] In one implementation, the extreme value vertex of the spatio-temporal aggregate refers to the vertex with extreme spatial coordinates among the multiple vertices included in the spatio-temporal aggregate;

[0043] The extreme value check rule includes multiple judgment expressions; when each judgment expression in the multiple judgment expressions is true, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device collide at the T-th timestamp; when at least one judgment expression in the multiple judgment expressions is false, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0044] In one implementation, the processing unit is further configured to:

[0045] If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is greater than the preset distance threshold, the collision detection result corresponding to the T-th timestamp is obtained; the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0046] In one implementation, when the processing unit generates the collision feedback result of the first movable device according to the collision detection results corresponding to each timestamp among multiple timestamps, it is specifically configured to:

[0047] If there is a collision detection result corresponding to a timestamp among the multiple timestamps indicating that the first movable device and the second movable device collide at the corresponding timestamp, the collision feedback result of the first movable device is generated; the collision feedback result indicates that the first movable device and the second movable device will collide;

[0048] The processing unit is further configured to:

[0049] Filter out the target timestamps corresponding to the collision detection results indicating collisions from the multiple timestamps, and generate a correction prompt message based on the target timestamps; output the correction prompt message to the first movable device.

[0050] In one implementation, the first movable device or the second movable device includes any one of the following: an aircraft, an intelligent robot, a vehicle, or a ship.

[0051] On the other hand, an embodiment of the present application provides a computer device, and the device includes:

[0052] A processor, adapted to execute a computer program;

[0053] A computer-readable storage medium storing a computer program, which when executed by the processor, implements the collision detection method as described above.

[0054] On the other hand, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which is adapted to be loaded and executed by a processor to implement the collision detection method as described above.

[0055] On the other hand, an embodiment of the present application provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to enable the computer device to execute the collision detection method as described above.

[0056] In an embodiment of the present application, if there is a first movable device with a track to be detected, then the track information to be detected of the first movable device can be obtained. The track information to be detected includes multiple timestamps corresponding to the track period of the first movable device, the position information of the first movable device at each timestamp, and the physical size information of the first movable device. Then, it is supported to construct a first spatio-temporal aggregate corresponding to each timestamp for the first movable device according to the position information and physical size information of the first movable device at each timestamp. Finally, the existing track information of the second movable device is obtained, the existing track information includes a second spatio-temporal aggregate corresponding to each timestamp, and a collision detection strategy is used to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp to generate a collision feedback result of the first movable device. It can be seen that an embodiment of the present application provides a brand-new collision detection scheme for movable devices; on the one hand, fully considering the physical size of the movable device itself and the interference around the movable device during movement, corresponding first spatio-temporal aggregates are constructed for the movable device at different timestamps. Compared with performing collision detection by regarding the first movable device as a mass point, the accuracy of collision detection can be improved based on the first spatio-temporal aggregate including physical size and interference distance. On the other hand, a new collision detection strategy is designed to perform collision detection on the first spatio-temporal aggregate corresponding to the first movable device and the second spatio-temporal aggregate corresponding to the second movable device, effectively reducing the number of detections compared with traditional detection methods, thereby improving the efficiency of collision detection. Description of the Drawings

[0057] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0058] Figure 1 It is a schematic structural diagram of a collision detection system provided by an exemplary embodiment of the present application;

[0059] Figure 2 It is a schematic flowchart of a collision detection method provided by an exemplary embodiment of the present application;

[0060] Figure 3 It is a schematic diagram of a spatio-temporal aggregate provided by an exemplary embodiment of the present application;

[0061] Figure 4 It is a schematic diagram of a core layer provided by an exemplary embodiment of the present application;

[0062] Figure 5a It is a schematic diagram of a physical layer provided by an exemplary embodiment of the present application;

[0063] Figure 5b It is a schematic diagram of another physical layer provided by an exemplary embodiment of the present application;

[0064] Figure 6 It is a schematic diagram of an interference layer provided by an exemplary embodiment of the present application;

[0065] Figure 7 It is a schematic flowchart of another collision detection method provided by an exemplary embodiment of the present application;

[0066] Figure 8 It is a schematic background flowchart of a collision detection provided by an exemplary embodiment of the present application;

[0067] Figure 9 It is a schematic diagram of a track provided by an exemplary embodiment of the present application;

[0068] Figure 10 It is a schematic diagram of a particle detection provided by an exemplary embodiment of the present application;

[0069] Figure 11 It is a schematic structural diagram of a collision detection device provided by an exemplary embodiment of the present application;

[0070] Figure 12 It is a schematic structural diagram of a computer device provided by an exemplary embodiment of the present application. Detailed implementation manners

[0071] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0072] In the embodiments of the present application, a collision detection solution based on a movable device is proposed. Among them, the movable device, also known as a movable platform, etc., is a device with the ability to move or travel, specifically a device that can move along a planned path according to a control instruction. Here, the control instruction can be directly or indirectly sent by an object (i.e., a user who holds or controls the movable device) to the movable device, or it can be a preset program, so that the movable device can move automatically based on the preset program. The movable device can include but is not limited to: aircraft, intelligent robots, vehicles, ships, etc. Among them: an aircraft is a device with the ability to operate in the air, and common aircraft include drones, airplanes, airships, etc.; an intelligent robot can refer to a device with the ability to move, such as a robot that can move along a predetermined path in a hotel or shopping mall to provide services to an object; a vehicle can refer to an autonomous vehicle (i.e., realizing autonomous driving according to an object preset program), and such an autonomous vehicle does not require the object to directly control the movement of the vehicle, so it can also be called a driverless vehicle, etc.; a ship can refer to an autonomous ship, or be called a driverless ship, etc.

[0073] Furthermore, collision detection, also known as anti-collision detection, refers to a mechanism for detecting whether a movable device collides with an obstacle during movement; the obstacle here can include but is not limited to other movable devices, animals, static objects, etc. For a movable device, accurately identifying or detecting various collision situations on its working movement path is an important factor to ensure the safe movement of the movable device. For example, during the operation of a drone in the air, if it cannot effectively avoid obstacles in the operation path, it will lead to problems such as the drone crashing due to collision with an obstacle.

[0074] It should be noted that considering the wide application of drones in various fields, it has become a research hotspot globally; therefore, in the subsequent embodiments of the present application, the movable device is taken as a drone as an example to introduce the collision detection solution proposed in the embodiments of the present application. The collision detection solution provided by the embodiments of the present application can be extended to the collision detection of other movable devices except aircraft.

[0075] To improve the accuracy of collision detection during the operation of a mobile device and reduce the computational overhead of collision detection; the collision detection scheme proposed in the embodiments of this application, on the one hand, proposes the concept of a three-layer spatio-temporal capsule, aiming to expand the trajectory planning (or plan) of the mobile platform into a spatio-temporal aggregate that takes into account the physical size of the mobile device and surrounding interference. On the other hand, a collision detection strategy is introduced. This strategy can check whether there is a collision conflict between the trajectory to be inspected of the mobile device to be inspected and the existing trajectory of the inspected mobile device by means of particle rapid inspection and extreme value inspection. It can greatly reduce the number of detections on the premise of ensuring the detection of potential trajectory planning conflicts, thereby greatly improving the detection efficiency. Among them, the trajectory planning of the mobile device refers to the optimal flight trajectory from the starting point to the target point planned for the mobile platform under specific constraint conditions and meeting certain performance indicators. Briefly speaking, the trajectory planning of the mobile device can be the object that controls the mobile device and sets the optimal flight path for the mobile device under specific constraint conditions. When planning the trajectory, information such as the heading angle, speed, and three-dimensional position of the mobile device in the time dimension is mainly considered. The output result of the trajectory planning is the position information (this position information can be regarded as a position point) of each timestamp (or called time step, such as every second) in the trajectory period of the mobile device (or called the takeoff and landing time, that is, the flight period between the moment when the mobile device starts flying from the starting point and the moment when it ends flying at the target point).

[0076] Specifically, the general process of the collision detection solution provided by the embodiments of the present application may include: Assuming that the first movable device has a need for collision detection, the track information to be detected of the first movable device can be obtained. The track information to be detected includes multiple timestamps corresponding to the track period of the first movable device, the position information of the first movable device at each timestamp, and the physical size information of the first movable device. After obtaining the track information to be detected of the first movable device, based on the position information and physical size information at each timestamp included in the track to be detected, a first spatio-temporal aggregate corresponding to each timestamp (i.e., the three-layer spatio-temporal capsule mentioned above) can be constructed for the first movable device; the first spatio-temporal aggregate is a cubic space structure (such as a cuboid) that covers all the spatial positions that the first movable device can reach at the corresponding timestamp considering the physical size information of the first movable device and the interference distance of the surrounding environment. Then, the existing track information of the second movable device that has been detected (i.e., the track planning during the operation of the second movable device has been subjected to collision detection, and the collision detection result is that no collision will occur) is obtained. The existing track information at least includes the second spatio-temporal aggregate corresponding to each timestamp of the second movable device. Finally, using the collision detection strategy designed by the embodiments of the present application, collision detection processing is performed on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp to obtain the collision detection result corresponding to the same timestamp; thus, according to the collision detection results corresponding to each timestamp of the first movable device during the track period, a collision feedback result is generated for the first movable device.

[0077] It can be seen that when performing track planning for the first movable device, the embodiments of the present application also introduce the physical size information of the first movable device and the possible interference distance around the first movable device during operation; in this way, fully considering the complex factors during the operation of the first movable device in the real world, a more realistic first spatio-temporal aggregate can be constructed for the first movable device, completely surrounding the first movable device within the aggregate, thereby improving the accuracy of detection when performing collision detection based on the first spatio-temporal aggregate. In addition, after constructing the first spatio-temporal aggregate, based on the characteristics of the cubic space structure of the first spatio-temporal aggregate, a relatively simple collision detection strategy (i.e., particle and extreme value detection) can be used to quickly detect the first spatio-temporal aggregate of the first movable device and the second spatio-temporal aggregate of the second movable device, thereby improving the detection efficiency of collision detection.

[0078] In practical applications, taking the first movable device as an unmanned aerial vehicle (UAV) as an example, before allowing the UAV to officially operate (such as performing a flight mission), the operator corresponding to the UAV needs to declare or apply to the relevant air traffic control platform for the airspace geographical information and flight track information of the UAV operation (the declared content includes, but is not limited to, information such as the time, altitude, speed, and loitering time of the airspace occupied by the UAV, etc.). In this way, within a period of time before the UAV takes off (such as several minutes or even several seconds), after the operator submits the to-be-inspected track information obtained from the track planning of the UAV to the air traffic control platform, the air traffic control platform needs to quickly analyze based on the existing track information and the to-be-inspected track information submitted by the same operator or multiple operators to ensure that the UAV is not in a restricted airspace and there are no time and space conflicts with other aircraft, so as to ensure that there is no collision risk between multiple aircraft and thus ensure the safety of the flight mission.

[0079] Based on this, it can be seen that the air traffic control platform plays an important role in coordinating multiple UAV flight missions during the UAV operation process; therefore, the collision detection solution provided in the embodiments of the present application can be embedded in the air traffic control platform in the form of an algorithm or the like. Among them, the air traffic control platform, also known as the air traffic control equipment, refers to the equipment used by the air traffic control department with management authority over a piece of airspace. The air traffic control software can be deployed in this equipment, and the collision detection solution provided in the embodiments of the present application is embedded in the air traffic control software; in this way, the air traffic control platform can be used to perform collision detection on the to-be-inspected track information submitted by the operator to the air traffic control department. Of course, when the first movable device is other equipment except for aircraft, the collision detection solution provided in the embodiments of the present application can be deployed to the corresponding control platform or equipment; the embodiments of the present application do not limit the specific platform or equipment for deploying the collision detection solution.

[0080] A schematic diagram of the architecture of an exemplary collision detection system with a movable device as an aircraft can be as Figure 1 shown. This collision detection system can be understood as an Intelligent Traffic System (ITS), also known as an Intelligent Transportation System. It effectively integrates advanced scientific and technological means (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, and artificial intelligence, etc.) into transportation, service control, and vehicle manufacturing, strengthening the connection between aircraft, airspace, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, improves the environment, and saves energy.

[0081] As Figure 1As shown in the figure, the collision detection system at least includes a first movable device 101, an operator device 102 corresponding to the first movable device 101, an air traffic control device 103 corresponding to the air traffic control department, and a second movable device 104 that has been approved by the air traffic control department (i.e., the collision detection is passed, that is, the collision detection result indicates that no collision will occur during the operation process). Among them: ① In the embodiments of the present application, the number of the first movable device that needs collision detection and the second movable device that has been detected is not limited, nor is the number of the air traffic control devices and the number of the operator devices limited. ② The operator device 102 and the air traffic control device 103 can be servers. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. It should be noted that the above-mentioned movable devices (such as the first movable device 101 and the second movable device 104) and the server can be directly or indirectly connected through a wireless communication method, and the present application does not limit this here.

[0082] In a specific implementation, first, when an object holding the first movable device 101 has a need to operate in the airspace using the first movable device 101, the object can send an operation plan or a flight plan to the operator device 102 corresponding to the first movable device 101 through the first movable device 101 (specifically, the remote control device corresponding to the first movable device 101). Then, based on the flight plan of the first movable device 101, the operator device 102 performs flight path planning for it and generates the to-be-inspected flight path information of the first movable device 101; the operator device 102 sends the to-be-inspected flight path information of the first movable device 101 to the air traffic control device 103 corresponding to the airspace where the first movable device 101 wants to operate. Finally, after receiving the to-be-inspected flight path information of the first movable device 101, the air traffic control device 103 can construct a first spatio-temporal aggregate corresponding to each time stamp in a plurality of time stamps during the flight path period for the first movable device 101 based on the to-be-inspected flight path information; and, the control device 103 also obtains from the database the existing flight path information of the second movable device 104 with the same airspace where the first movable device 101 wants to operate, and the second spatio-temporal aggregate corresponding to each time stamp in the flight path period corresponding to the second movable device itself in the existing flight path information; in this way, the air traffic control device 103 can perform collision detection on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same time stamp by using the collision detection strategy designed in the embodiment of the present application, and generate a collision feedback result of the first movable device 101 according to the collision detection results corresponding to each time stamp of the first movable device during the entire flight path period.

[0083] Further, the air traffic control device 103 returns the collision feedback result of the first movable device 101 to the operator device 102, so that the operator device 102 can send flight instruction information to the first movable device 101 based on the collision feedback result. For example, when the collision feedback result indicates that there will be no collision when the first movable device 101 operates according to the to-be-inspected flight path information, the flight instruction information returned by the operator device 102 can instruct the first movable device 101 to operate according to the flight path trajectory; again, for example, when the collision feedback result indicates that there will be a collision when the first movable device 101 operates according to the to-be-inspected flight path information, the operator device 102 can generate flight instruction information according to the correction prompt information carried in the collision feedback result. At this time, the flight instruction information includes correction prompt information to instruct the first movable device 101 to adjust the flight path, otherwise there will be a collision.

[0084] Based on the above-described collision detection scheme and system architecture, the following two points need to be further explained:

[0085] ① As mentioned above in the embodiment of the present application Figure 1The system shown is for a clearer illustration of the technical solution of the embodiments of the present application and does not constitute a limitation on the technical solution provided by the embodiments of the present application. Those of ordinary skill in the art will know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiments of the present application is equally applicable to similar technical problems. For example, the above takes a movable device as a drone as an example to introduce an application scenario of the collision detection solution; it should be understood that in actual applications, the movable device can also be other devices. For example, the first movable device is a drone, and the second movable device is an unmanned vehicle, an unmanned ship, or an intelligent robot, etc. In this scenario, the air traffic control device corresponding to the first movable device may need to interact with the control device corresponding to the second movable device (such as a ship control device or a vehicle control device) to achieve collision detection between the two fields.

[0086] ② The first movable device or the second movable device involved in the embodiments of the present application includes any of the movable devices described above; for example, the first movable device or the second movable device can include any of the following: an aircraft, an intelligent robot, a vehicle, or a ship. Optionally, the device types of the first movable device and the second movable device are the same. For example, both the first movable device and the second movable device are aircraft; optionally, the device types of the first movable device and the second movable device are different. For example, the first movable device is an aircraft, and the second movable device is a ship (such as a ship with a large flight deck or related equipment for berthing aircraft). The embodiments of the present application do not limit the specific device types of the first movable device and the second movable device, and this is hereby specifically stated.

[0087] ③ In the embodiments of the present application, the collection and processing of relevant data should be strictly in accordance with the requirements of relevant laws and regulations. Obtaining personal information requires the informed consent of the individual subject (or having a legal basis for information acquisition), and subsequent data use and processing behaviors should be carried out within the scope authorized by laws and regulations and the individual information subject. For example, when the embodiments of the present application are applied to specific products or technologies, such as obtaining the track information to be inspected of the first movable device, the permission or consent of the object holding the first movable device is required, and the collection, use, and processing of relevant data (such as the collection and release of bullet screens published by the object) need to comply with the relevant laws, regulations, and standards of the relevant region.

[0088] Based on the collision detection solution described above, the embodiments of the present application propose a more detailed collision detection method. The following will introduce the collision detection method proposed by the embodiments of the present application in detail with reference to the accompanying drawings.

[0089] Please refer to Figure 2 , Figure 2The figure shows a schematic flowchart of a collision detection method provided by an exemplary embodiment of the present application; this collision detection method can be executed by a computer device (such as an air traffic control device that deploys the collision detection method provided by the present application), and this collision detection method includes but is not limited to steps S201 - S205:

[0090] S201: Obtain the track information to be detected of the first movable device.

[0091] The first movable device is a movable device with a track detection requirement. For example, the first movable device is a drone with a flight plan, etc.; further, the track information to be detected of the first movable device is track information generated based on the track plan of the first movable device and that needs to be detected by a control device (such as an air traffic control device). The track information to be detected of the first movable device at least includes: multiple timestamps corresponding to the track period of the first movable device, the position information of the first movable device at each timestamp, and the physical size information of the first movable device. Among them: ① The track period corresponding to the first movable device can be understood as the takeoff and landing period during which the first movable device plans to fly. For example, if it takes off at 9:00 and lands at 10:00, then the takeoff period is the period from 9:00:00 to 9:10:00; multiple timestamps of the track period can be understood as time points at fixed intervals within this track period. For example, if the timestamp is 1 second, then the timestamps of the track period from 9:00 to 9:10 at least include: 9:00:00, 9:00:01, 9:00:02,..., 9:10:00, etc. ② The position information of the first movable device at each timestamp can refer to the coordinates of the first movable device in the space coordinate system at the corresponding timestamp, that is, the form of this position information can be in the form of the space coordinates of the first movable device in the space coordinate system. ③ The physical size information of the first movable device can be used to reflect information such as the volume, shape, and size of the first movable device; for example, the physical size information of the first movable device is expressed as information such as the length, width, and height of the first movable device.

[0092] In a specific implementation, if the object holding the first movable device wants to fly the first movable device in the airspace, then the object can configure the track information to be detected of the first movable device in the remote controller corresponding to the first movable device, such as setting the track period, selecting the timestamps in the track period, customizing the position information corresponding to each timestamp, correcting the physical size information of the first movable device, and so on. Then, after the object finishes the configuration, the track information to be detected of the first movable device is sent to the operator device corresponding to the first movable device through the remote controller. Then, the operator device can send the track information to be detected of the first movable device to the air traffic control device. At this time, the air traffic control device determines that it has obtained the track information to be detected of the first movable device.

[0093] It should be noted that the method for determining the track information to be inspected of the first movable device described above is not fixed. For example, the object can only perform basic configuration operations in the remote controller, such as setting the track time period, without selecting the time stamp, such as setting the flight altitude range corresponding to the track time period, without setting the position information corresponding to each time stamp, etc.; after the remote controller sends this basic information to the operator device, the operator device automatically generates the track information to be inspected of the first movable device based on the basic information combined with some preset and predicted information, etc. In this way, for the object, it does not need to master complicated information configuration rules, and only needs to simply configure the information according to its will, effectively reducing the workload of the object, and the generation of the track information to be inspected by the operator device can ensure the accuracy of the track information to be inspected to a certain extent.

[0094] S202: Based on the position information of the first movable device at each time stamp and the physical size information of the first movable device, construct the first spatio-temporal aggregate corresponding to the corresponding time stamp.

[0095] The first spatio-temporal aggregate corresponding to any time stamp in the track time period of the first movable device is a cubic space structure that includes the operation range indicated by the position information of the first movable device at the any time stamp under the condition of considering the interference distance of the first movable device at the any time stamp and the physical size information of the first movable device. That is to say, the first spatio-temporal aggregate involved in the embodiments of the present application is a cubic space structure constructed based on the physical size of the first movable device, the interference distance and the operation range of the first movable device at the corresponding time stamp. Among them, the interference distance of the first movable device at the corresponding time stamp refers to: the interference and danger caused by the interference of the surrounding air flow or magnetic field, etc. generated by the movement of the first movable device at the time stamp to the surrounding adjacent movable devices; by introducing the interference distance for each time stamp in the track time period of the first movable device, it can be ensured that different movable devices move at a certain distance (such as flying), so as to ensure the safe movement between different movable devices. Similarly, the operation range of the first movable device at the corresponding time stamp can refer to: the space range composed of one or more spatial positions that the first movable device may reach at the time stamp.

[0096] Furthermore, the first spatio-temporal aggregate corresponding to the first movable device at the time stamp can be referred to Figure 3 , and the first spatio-temporal aggregate can be divided into three layers, from the inside to the outside, including: the core layer (such as Figure 3 denoted as C1), the physical layer (such as Figure 3 denoted as C2) and the interference layer (such as Figure 3Denoted as C3); that is to say, the first spatio-temporal aggregate can be considered as the outermost "interference layer", which includes the physical layer, and the physical layer includes the core layer. Taking any timestamp among multiple timestamps of the track period corresponding to the first movable device as the T-th timestamp as an example, where T is an integer greater than zero, the specific implementation process of constructing the first spatio-temporal aggregate corresponding to the T-th timestamp will be introduced; this specific implementation process may include but is not limited to steps s11-s13, where:

[0097] s11: Construct the core layer. The core layer is a cubic space structure (such as the smallest cuboid) composed of all spatial positions that the first movable device can reach at the T-th timestamp when the first movable device is used as a particle for track planning; the cubic space structure includes the set of positions that the first movable device may reach at the T-th timestamp.

[0098] In practical applications, considering that the actual position information of the first movable device at the timestamp may have a certain degree of uncertainty due to certain reasons (such as weather factors or sudden obstacle avoidance factors, etc.) during movement; for example, if the first movable device is a drone, its actual position during flight may not coincide with the planned position. In order to accurately determine the possible position of the first movable device at the T-th timestamp, the embodiments of the present application support using the concept of the core layer to describe the possible track of the first movable device at the T-th timestamp when performing specific track planning for the first movable device, so as to facilitate airspace spatio-temporal dynamic management, that is, to facilitate mastering the possible position of the first movable device at the first T-th timestamp.

[0099] In specific implementation, during track planning, it is supported to consider the first movable device as a particle. For example, the geometric center or the center of gravity of the outer envelope line of the first movable device is selected as the particle of the first movable device. In this way, taking the first movable device as a particle, and based on the position information and speed information of the particle at the T-th timestamp, as well as the first time period and the second time period adjacent to the T-th timestamp of the particle, the core layer corresponding to the first movable device at the T-th timestamp is constructed; where the speed information of the first movable device at the T-th timestamp is carried in the track information to be inspected of the first movable device, that is, the track information to be inspected of the first movable device also includes the speed information of the first movable device at each timestamp.

[0100] An exemplary schematic diagram of a core layer can be seen Figure 4 ; as Figure 4 shown, assuming that the speed of the first movable device at the T-th timestamp is V(T), the first time period adjacent to the T-th timestamp of the first movable device is T 1 and the second time period is T 2 , and the T 1is T after the T-th timestamp 1 time period, T 2 is T before the T-th timestamp 2 time period; T here 1 time period and T 2 The specific duration of the time period is not limited. For example, 0.5 seconds is the error time for the first movable device to reach the position information corresponding to the T-th timestamp. Then, it is determined that the core layer includes both the position of the first movable device at the T-th timestamp and also includes the possible positions of the first movable device in the T 2 time period before and T 1 time period after.

[0101] That is to say, the core layer contains the set of possible positions of the first movable device within the time interval [T - T2, T + T1]. All the spatial positions included in this position set are located within the core layer, and this core layer is a cubic space structure as shown in Figure 3 ——the smallest cuboid; the length * width * height of this smallest cuboid = L 1 ·W 1 ·H 1 . Among them: ① The length L of the smallest cuboid 1 = L 11 + L 12 ; where, L 1i = T i ·V(T), i = 1 or 2; when i = 1, L 11 = T 1 ·V(T) represents the movement distance of the first movable device in the T 1 time period after the T-th timestamp. Conversely, when i = 2, L 12 = T 2 ·V(T) represents the movement distance of the first movable device in the T 2 time period before the T-th timestamp. ② The width W 1 and height H 1 of the smallest cuboid can be determined according to preset conditions; among them, the preset conditions can include but are not limited to at least one of the following: the attitude information of the first movable device at the T-th timestamp, the general environmental factors of the position information corresponding to the T-th timestamp of the first movable device, and fixed values set in advance according to experience, etc. The embodiments of the present application do not limit the specific calculation method of the width W 1 and height H 1 of the smallest cuboid, as long as all the spatial positions that the first movable device may reach as a particle at the T-th timestamp are included in the core layer composed of the width and height ranges.

[0102] It can be seen that when constructing the first spatio-temporal aggregate corresponding to the timestamp for the first movable device in the embodiments of the present application, the error between the actual position and the planned position of the first movable device during movement is fully considered, and a core layer corresponding to the T-th timestamp is constructed for the first movable device, so that the core layer can include the set of all spatial positions that may be reached at the T-th timestamp, thereby avoiding the negative impact brought by the position deviation during the movement of the first movable device, such as the decrease in the accuracy of subsequent collision detection caused by the position deviation, which may further lead to a collision crisis of the first movable device.

[0103] s12: Construct a physical layer surrounding the core layer. The physical layer is a cubic space structure (such as a minimum cuboid) that can enclose the outer contour of the first movable device when the first movable device moves to the edge of the core layer.

[0104] In practical applications, if only the spatial positions that the first movable device may reach at the T-th timestamp as a particle are considered to construct the core layer, then when the particle of the first movable device moves to the edge of the core layer, due to the physical entity size of the first movable device itself, some of its physical entity components will necessarily be outside the core layer. Therefore, if only based on the core layer corresponding to the first movable device at the T-th timestamp to determine whether a collision or overlap occurs, it is not sufficient to ensure that all physical entity parts of the first movable device do not collide. For this reason, the embodiments of the present application also support introducing the physical size information of the first movable device, and introducing a physical layer outside the core layer (i.e., the second layer of the first spatio-temporal aggregate), so that the physical layer completely wraps the core layer. In this way, even when the first movable device is at the edge of the core layer, the physical envelope of the first movable device is still surrounded by the physical layer. That is, if there is a particle of the first movable device at all positions within the core layer, the physical layer is a minimum cubic space structure that can enclose the outer contours of all physical entity components of the first movable device, specifically a minimum cuboid.

[0105] In a specific implementation, the air traffic control device supports constructing a physical layer corresponding to the first movable device at the T-th timestamp based on the core layer corresponding to the first movable device at the T-th timestamp, the attitude information of the first movable device at the T-th timestamp, and the physical size information of the first movable device. Among them, the attitude information of the first movable device at the T-th timestamp is carried in the track information to be inspected of the first movable device, that is, the track information to be inspected of the first movable device includes the attitude information of each timestamp in the track period corresponding to the first movable device. Further, the attitude information of the first movable device at the T-th timestamp can be used to characterize the motion attitude of the first movable device at the T-th timestamp. For example: when the first movable device is a drone, the attitude information of the drone may include but is not limited to: yaw angle (or called heading angle), pitch angle, roll angle, etc.; among them, the yaw angle of the drone refers to the angle of rotation of a fixed-wing or rotary-wing aircraft around its own longitudinal axis during vertical flight, or the angle between the actual heading of the drone and the planned heading; the pitch angle of the drone refers to the angle between the body axis (along the nose direction) of the drone and the ground plane (horizontal plane) with the nose of the drone horizontal as the reference; the roll angle of the drone refers to the angle of the drone rolling around the front and rear axes.

[0106] An exemplary schematic diagram of a physical layer can be seen in Figure 5a ; as Figure 5a shown, assuming the first movable device is a drone, when the drone moves to the edge of the core layer, some physical components of the drone (such as some wings) exceed the core layer. Therefore, in the embodiment of the present application, a physical layer is constructed outside the core layer corresponding to the drone at the T-th timestamp based on the physical size information of the drone, and the shape of the physical layer is a cuboid that completely wraps the core layer. Taking the shape of the drone as centrosymmetric as an example, in this case, the minimum size of the physical layer wrapping the core layer is length * width * height = (L 1 +2ΔL 2 )·(W 1 +2ΔW 2 )·(H 1 +2ΔH 2 ); among them, as can be seen from the side view shown in Figure 5a , ΔL 2 is the length by which the wing of the drone exceeds the core layer in the length direction when the drone is at the edge of the core layer. Similarly, ΔH 2 is the height by which the wing of the drone exceeds the core layer in the height direction when the drone is at the edge of the core layer; as can be seen from the top view shown in Figure 5a , ΔW 2 is the width by which the wing of the drone exceeds the core layer in the width direction when the drone is at the edge of the core layer.

[0107] It should be noted thatFigure 5a This is described by taking the shape of the unmanned aerial vehicle (UAV) as centrosymmetric and the attitude information of the UAV indicating that both the pitch angle and the roll angle of the UAV are zero degrees as an example. However, in practical applications, the shape of the UAV itself may not be centrosymmetric, or the attitude information of the UAV indicates that the UAV has a certain pitch angle and / or roll angle and / or heading angle, etc. In this implementation manner, when constructing the physical layer for the UAV, it is necessary to construct the physical layer according to the specific shape and pose information of the UAV. A schematic diagram of constructing the physical layer for a UAV with a certain roll angle can be seen in Figure 5b ; as Figure 5b shown, when the UAV has a roll angle, when the UAV is at the edge of the core layer, the length exceeding the core layer in the length direction is less than ΔL 2 , which is denoted as ΔL′ 2 . Similarly, when the UAV is at the edge of the core layer, the length exceeding the core layer in the height direction is greater than ΔH 2 , which is denoted as ΔH′ 2 ; at this time, the minimum size of the physical layer wrapping the core layer, length * width * height = (L 1 + 2ΔL′ 2 )·(W 1 + 2ΔW 2 )·(H 1 + 2ΔH′ 2 ).

[0108] It can be seen that the embodiment of the present application supports constructing a larger range of physical layer for the first movable device according to the actual physical size of the first movable device when the first movable device is at the edge of the core layer, so that the physical layer can completely surround the outer contour of the first movable device when the first movable device is at the edge of the core layer, thereby avoiding the collision between the outer contour of the first movable device and surrounding objects when the first movable device is at the edge of the core layer, and significantly improving the anti-collision mechanism of the first movable device.

[0109] s13: Construct an interference layer surrounding the physical layer, that is, the first spatio-temporal aggregate corresponding to the first movable device at the T-th time stamp. Among them, the interference layer is a cubic space structure that can surround the interference distance generated by the first movable device on the surrounding environment when the first movable device moves to the edge of the core layer.

[0110] Based on the foregoing steps, the core layer and the physical layer constructed for the first movable device at the T-th timestamp can include the possible positions of the first movable device at the T-th timestamp and the corresponding physical entity components. Further, considering that there are interference factors around the first movable device during flight that can interfere with other surrounding aircraft or objects, this ensures that there is no collision or overlap between the physical entity components of the first movable device and the surrounding aircraft or objects. However, it still cannot guarantee the safety of the flight path of the first movable device because the airflow, magnetic field, etc. generated when the first movable device moves may also have a negative impact on the surroundings. Based on this, the embodiments of the present application consider the interference caused by the movement of the first movable device and introduce an interference layer (i.e., the third layer of the first spatio-temporal aggregate); that is, if there is a first movable device existing as a mass point at all positions within the core layer, the interference layer is a cuboid (or the smallest cuboid) that can enclose the outer contour of all its interference distances.

[0111] In a specific implementation, after the air traffic control device constructs the core layer and the physical layer for the first movable device at the T-th timestamp, it can continue to construct the interference layer corresponding to the first movable device at the T-th timestamp based on the physical layer and the interference distance of the first movable device to the surrounding environment; at this time, the interference layer corresponding to the T-th timestamp can be considered as the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp. Among them, the specific value of the interference distance of the first movable device to the surrounding environment at the T-th timestamp is determined according to the interference factors of the first movable device at the T-th timestamp, such as airflow, magnetic field, wind force, etc., and there is no limitation on this.

[0112] An exemplary schematic diagram of an interference layer can be seen in Figure 6 ; as Figure 6 shown, assuming that the first movable device is a drone, when the drone is at the edge of the core layer, the drone will cause a certain interference to the surrounding environment, such as generating an airflow (the magnitude of the airflow can be determined according to factors such as the wing rotation rate of the drone). Therefore, the embodiments of the present application construct an interference layer outside the physical layer based on the interference distance generated when the drone is at the edge of the core layer, and the shape of the interference layer is a cuboid (or the smallest cuboid) that completely wraps the physical layer. Taking the shape of the drone as centrosymmetric and the interference generated by the drone to the surrounding environment as symmetric as an example, in this case, the minimum size of the length * width * height of the interference layer wrapping the physical layer = (L 1 + 2ΔL 2 + 2ΔL 3 ) · (W 1 + 2ΔW 2 + 2ΔW 3 ) · (H 1 + 2ΔH 2 + 2ΔH3 )。Among them, ΔL 3 is the interference distance of the interference signal generated by the UAV on the surrounding environment in the length direction when the UAV is at the edge of the core layer; ΔW 3 is the interference distance of the interference signal generated by the UAV on the surrounding environment in the width direction when the UAV is at the edge of the core layer; ΔH 3 is the interference distance of the interference signal generated by the UAV on the surrounding environment in the height direction when the UAV is at the edge of the core layer.

[0113] It should be noted that the embodiments of the present application do not limit the specific values of the interference distances of the interference signals generated by the first movable device on the surrounding environment (such as the length direction, width direction, and height direction). For example, it can be determined according to empirical values; or, according to the attitude information and speed information of the first movable device corresponding to the T time stamp; or, a model is used to estimate the interference distance of the interference signal generated by the first movable device on the surrounding environment, and so on.

[0114] It can be seen that the embodiments of the present application fully consider the interference generated by the first movable device on the surrounding environment during movement, and construct an interference layer for the first movable device to completely wrap the physical layer. The interference here can include, but is not limited to, the interference and danger caused by the surrounding air flow or magnetic field, etc. of the first movable device during movement to the surrounding adjacent objects; thereby ensuring that a safe distance is maintained between the first movable device and surrounding objects (such as other movable devices) during movement, and greatly improving the operating safety of the first movable device.

[0115] In summary, compared with the first spatio-temporal aggregate constructed for the first movable device based on the above steps s11-s13 in the embodiments of the present application and the elliptical cylinder constructed in the traditional technology only considering the first movable device as a mass point, the first spatio-temporal aggregate constructed in the embodiments of the present application can not only completely wrap the physical components of the first movable device, but also completely wrap the interference distances of the interference signals generated by the first movable device on the surrounding environment. Therefore, performing subsequent collision detection based on the first spatio-temporal aggregate can effectively ensure that the collision detection result is accurate and reliable.

[0116] S203: Obtain the existing track information of the second movable device.

[0117] The second movable device refers to a movable device for which the air traffic control device has performed collision detection and the collision feedback result indicates that no collision will occur. To save the workload of collision detection by the air traffic control device and improve the efficiency of collision detection, the embodiments of the present application also support setting movable devices whose obtained second movable device and the first movable device to be detected have the same track airspace and there is an overlapping timestamp in the track time period. For example, assume that before the air traffic control device receives the track information to be detected of the first movable device sent by the operator device, collision detection processing is performed on the second movable device 1 and the second movable device 2, and both the second movable device 1 and the second movable device 2 pass the detection. Then, after the air traffic control device obtains the track information to be detected of the first movable device, it can compare the timestamp and airspace information included in the track information to be detected of the first movable device (such as indicating the moving airspace corresponding to the track of the first movable device) with the second movable device 1 and the second movable device 2 respectively; if the air traffic control device detects that the airspace corresponding to the track of the first movable device is the same as or overlaps with the airspace corresponding to the track of the second movable device, while the airspace corresponding to the track of the first movable device and the airspace corresponding to the track of the second movable device are completely different or do not overlap, then the air traffic control device determines the second movable device 1 as the movable device that needs to perform collision detection with the first movable device, and the second movable device 2 does not need to perform collision detection with the first movable device. It is not difficult to see that the screening mechanism for the second movable device provided by the embodiments of the present application can prevent the air traffic control device from detecting all the second movable devices that have passed the collision detection with the first movable device, reducing the workload of collision detection by the air traffic control device while improving the efficiency of collision detection.

[0118] Among them, the existing track information of the second movable device selected for collision detection with the first movable device at least includes: multiple timestamps of the track period corresponding to the second movable device and the second spatio-temporal aggregate corresponding to each timestamp. It should be noted that the second spatio-temporal aggregate corresponding to the second movable device at each timestamp can be preprocessed by the air traffic control device, that is, the air traffic control device does not have to wait until it receives the track information to be detected of the first movable device to execute the construction process of the second spatio-temporal aggregate corresponding to the second movable device at different timestamps, but can execute the construction of the second spatio-temporal aggregates corresponding to different timestamps of all second movable devices when the air traffic control device is idle. Of course, the second spatio-temporal aggregate corresponding to the second movable device at the timestamp may also be constructed and pre-stored by the air traffic control device during the collision detection process of the second movable device; when the air traffic control device performs collision detection on the first movable device, it can directly obtain the pre-stored second spatio-temporal aggregates corresponding to different timestamps of the second movable device; the embodiment of the present application does not limit the construction time of the second spatio-temporal aggregates of the second movable device at different timestamps, and the construction method of the second spatio-temporal aggregate is similar to the construction method of the first spatio-temporal aggregate corresponding to the first movable device at the timestamp described above, which will not be elaborated here.

[0119] It is also worth noting that the number of second movable devices used for collision detection with the first movable device can be one or more; when the number of second movable devices is multiple, the specific implementation process of collision detection between each second movable device and the first movable device is the same. Subsequently, only a single second movable device will be used as an example to introduce the collision detection process between the second movable device and the first movable device in detail.

[0120] S204: Use the collision detection strategy to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp, and obtain the collision detection result corresponding to the same timestamp.

[0121] S205: Generate the collision feedback result of the first movable device according to the collision detection results corresponding to each timestamp among multiple timestamps.

[0122] In steps S204 - S205, considering that the condition for the first movable device and the second movable device to collide is that the first movable device and the second movable device are at the same or similar positions at the same timestamp; based on this, after the air traffic control device constructs a corresponding first spatio - temporal aggregate for the first movable device at each of multiple timestamps based on the foregoing steps, and obtains the second spatio - temporal aggregate corresponding to the second movable device at each of multiple timestamps, it can use the collision detection strategy designed in the embodiments of the present application to perform collision detection processing on the first spatio - temporal aggregate and the second spatio - temporal aggregate corresponding to the same timestamp, and obtain the collision detection result corresponding to the same timestamp. Further, the air traffic control device can generate a collision feedback result for the first movable device based on the collision detection results corresponding to each of multiple timestamps included in the track corresponding to the first movable device. Among them: if the collision detection results corresponding to each of multiple timestamps in the track period corresponding to the first movable device all indicate that no collision will occur, the collision feedback result indicates that no collision will occur when the first movable device moves according to the track plan; on the contrary, if the collision detection results corresponding to at least one timestamp among multiple timestamps indicate that a collision will occur, the collision feedback result indicates that the first movable device will collide.

[0123] In summary, the embodiments of the present application combine the physical size of the first movable device and the interference in the surrounding environment, and creatively give a construction logic of a three - layer spatio - temporal aggregate; by constructing a corresponding first spatio - temporal aggregate for the first movable device at each timestamp, it is ensured that the spatio - temporal aggregate used for subsequent collision detection processing can not only completely wrap the physical components of the entire first movable device, but also wrap the interference range of the interference signal generated by the first movable device on the surrounding environment during operation, thus greatly improving the safety of the first movable device during operation.

[0124] Please refer to Figure 7 , Figure 7 which shows a schematic flowchart of another collision detection method provided by an exemplary embodiment of the present application; this collision detection method can be executed by a computer device (such as an air traffic control device deploying the collision detection method provided by the present application), and this collision detection method includes but is not limited to steps S701 - S707:

[0125] S701: Obtain the track information to be inspected of the first movable device.

[0126] S702: Based on the position information of the first movable device at each timestamp and the physical size information of the first movable device, construct a corresponding first spatio - temporal aggregate for the corresponding timestamp.

[0127] S703: Obtain the existing track information of the second movable device.

[0128] It should be noted that for the specific implementation processes shown in steps S701 - S703, reference can be made to the relevant descriptions of the specific implementation processes shown in steps S201 - S202 in the foregoing Figure 2 illustrated embodiments, which will not be elaborated herein.

[0129] In addition, when the second movable device is one or more, the specific implementation logic of the collision detection process between the first movable device and one or more second movable devices can be referred to Figure 8 , such as Figure 8 shown:

[0130] First, the air traffic control device constructs a second spatio - temporal aggregate for each second movable device among one or more second movable devices at the corresponding time stamp, and determines the extreme vertices for each second spatio - temporal aggregate. Similarly, the air traffic control device also constructs a first spatio - temporal aggregate corresponding to each time stamp for the first movable device to be detected, and determines the corresponding extreme vertices for each first spatio - temporal aggregate. Among them, the extreme vertices can be understood as the largest and smallest vertices among the 8 vertices of a cuboid when the spatio - temporal aggregate (such as the first spatio - temporal aggregate or the second spatio - temporal aggregate) is a cuboid, and the extreme vertices will be further described later.

[0131] Then, in the order of the time stamps, the first spatio - temporal aggregate corresponding to the initial time stamp (i.e., the time stamp indicating the earliest time point) is determined from the multiple time stamps corresponding to the first movable device, and it is detected whether each second movable device among one or more second movable devices collides with the first movable device in the first spatio - temporal aggregate corresponding to the initial time stamp in the second spatio - temporal aggregate corresponding to the initial time stamp. If each second movable device in the second spatio - temporal aggregate corresponding to the initial time stamp collides with the first movable device in the first spatio - temporal aggregate corresponding to the initial time stamp, it indicates that at the initial time stamp, the first movable device will not collide with any of the second movable devices that have applied for flight. Then, it is detected whether there is still a first spatio - temporal aggregate corresponding to the time stamp to be detected for the first movable device. If so, the collision detection continues for the first spatio - temporal aggregate corresponding to the time stamp to be detected. On the contrary, if there is at least one second movable device among one or more second movable devices whose second spatio - temporal aggregate corresponding to the corresponding initial time stamp does not collide with the first movable device in the first spatio - temporal aggregate corresponding to the initial time stamp, then an undetected second movable device is selected from at least one second movable device, and a particle detection process is performed on the second spatio - temporal aggregate corresponding to the initial time stamp of the second movable device and the first spatio - temporal aggregate corresponding to the initial time stamp of the first movable device.

[0132] Secondly, if the particle detection result obtained by performing particle detection processing on the second spatio-temporal aggregate corresponding to the second movable device at the initial timestamp and the first spatio-temporal aggregate corresponding to the first movable device at the initial timestamp indicates that the particle detection passes; it means that when the second movable device moves to the second spatio-temporal aggregate corresponding to the initial timestamp and the first movable device moves to the first spatio-temporal aggregate corresponding to the initial timestamp, no collision will occur, then continue to select the second movable device to be detected from at least one second movable device to perform the above particle detection processing. On the contrary, if the particle detection result obtained by performing particle detection processing on the second spatio-temporal aggregate corresponding to the second movable device at the initial timestamp and the first spatio-temporal aggregate corresponding to the first movable device at the initial timestamp indicates that the particle detection fails, it means that when the second movable device moves to the second spatio-temporal aggregate corresponding to the initial timestamp and the first movable device moves to the first spatio-temporal aggregate corresponding to the initial timestamp, a collision may occur, then continue to perform vertex collision detection (or called extreme value detection) on the second spatio-temporal aggregate corresponding to the second movable device at the initial timestamp and the first spatio-temporal aggregate corresponding to the first movable device at the initial timestamp, to obtain the collision detection result corresponding to the initial timestamp.

[0133] Finally, if the collision detection result corresponding to the initial timestamp indicates that when the second movable device moves to the second spatio-temporal aggregate corresponding to the initial timestamp and the first movable device moves to the first spatio-temporal aggregate corresponding to the initial timestamp, a collision may occur, the air traffic control device records the relevant information of the initial timestamp when the collision will occur, so as to report to the object holding the first movable device, and the air traffic control device can also continue to detect whether a collision occurs in the first spatio-temporal aggregate corresponding to the next timestamp corresponding to the initial timestamp. On the contrary, if the collision detection result corresponding to the initial timestamp indicates that when the second movable device moves to the second spatio-temporal aggregate corresponding to the initial timestamp and the first movable device moves to the first spatio-temporal aggregate corresponding to the initial timestamp, no collision will occur, the air traffic control device can also continue to detect whether a collision occurs in the first spatio-temporal aggregate corresponding to the next timestamp corresponding to the initial timestamp, until collision detection is performed between the first spatio-temporal aggregate corresponding to each timestamp in the track period corresponding to the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to each second movable device in at least one second movable device at the corresponding timestamp.

[0134] It should be noted that: ① The above Figure 8It is a general process for implementing collision detection in the order of timestamps. In practical applications, considering that the first movable device and the second movable device are likely to collide only when they are at the same or similar positions at the same timestamp. Therefore, before the embodiments of this application implement the collision detection between the first movable device and the second movable device for a certain timestamp by using mass points and extreme values, it also supports first determining at which timestamps the first movable device and the second movable device need to perform collision detection, that is, which time points indicated by the timestamps are the same; and collision detection does not need to be performed for different timestamps, which can avoid the overhead caused by performing collision detection for all timestamps to a certain extent and improve the efficiency of collision detection.

[0135] For example, as Figure 9 shown, assume that the air traffic control device has performed collision detection on the second movable device 901 and the second movable device 902, and the detection result indicates that the second movable device 901 and the second movable device 902 will not collide with surrounding objects when moving; and the track period corresponding to the second movable device 901 includes the timestamps T, T + 1, and T + 2, and the track period corresponding to the second movable device 902 includes the timestamps T - 1, T, and T + 1; and the air traffic control device obtains that the track period corresponding to the first movable device 903 to be detected includes the timestamps T, T + 1, and T + 2. Then, it is determined that only the second movable device 902 has a flight plan at the timestamp T - 1, so there is no need to perform collision detection between the first movable device 903 and the second movable device 902 at the timestamp T - 1; similarly, at the timestamp T, the second movable device 901, the second movable device 902, and the first movable device 903 all have flight plans, so it is necessary to perform collision detection between the first movable device 903 and the second movable device 901, and between the first movable device 903 and the second movable device 902 at the timestamp T; similarly, at the timestamp T + 1, the second movable device 901, the second movable device 902, and the first movable device 903 all have flight plans, so it is necessary to perform collision detection between the first movable device 903 and the second movable device 901, and between the first movable device 903 and the second movable device 902 at the timestamp T + 1; similarly, at the timestamp T + 2, only the second movable device 901 and the first movable device 903 have flight plans, so it is necessary to perform collision detection between the first movable device 903 and the second movable device 901 at the timestamp T + 2.

[0136] ② The above Figure 8 and Figure 9It introduces the collision detection process between the first movable device and one or more second movable devices from an overall perspective. For the specific implementation process of the collision detection process for the first spatio-temporal aggregate corresponding to the first movable device at any time stamp (such as the T-th time stamp) and the second spatio-temporal aggregate corresponding to the second movable device at the same time stamp using the collision detection strategy, refer to the following steps S704 - S706.

[0137] S704: Adopt the collision detection strategy to perform particle collision detection on the position information of the first movable device at the T-th time stamp and the position information of the second movable device at the T-th time stamp, and obtain the particle detection result.

[0138] Among them, the position information of the first movable device at the T-th time stamp can be the position of the first movable device when it is regarded as a particle at the T-th time stamp; specifically, it is the central position of the first movable device in the first spatio-temporal aggregate corresponding to the T-th time stamp. The form of the position information is in the form of spatial coordinates, and this spatial position is calculated based on a three-dimensional space coordinate system, and the space coordinate system includes the first coordinate value X, the second coordinate value Y, and the third coordinate value Z. Then, after obtaining the position information of the first movable device at the T-th time stamp and the position information of the second movable device at the T-th time stamp, the position information of the two can be directly detected; if the distance between the two particles is far, it indicates that there must be no overlapping area between the two spatio-temporal aggregates (i.e., the first spatio-temporal aggregate and the second spatio-temporal aggregate) corresponding to the two particles at the T-th time stamp, so it is judged that the first movable device and the second movable device will not collide at the T-th time stamp; if the distance between the two particles is close, it indicates that there may be an overlapping area between the two spatio-temporal aggregates (i.e., the first spatio-temporal aggregate and the second spatio-temporal aggregate) corresponding to the two particles at the T-th time stamp, so it is judged that the first movable device and the second movable device may collide at the T-th time stamp, and the next extreme value detection is required.

[0139] Among them, the specific implementation process of particle collision detection may include: adopting a collision detection strategy to compare the first coordinate value of the first movable device at the T-th timestamp with the first coordinate value of the second movable device at the T-th timestamp to obtain a first comparison sub-result; the first comparison sub-result indicates the distance information between the first movable device and the second movable device in the X direction at the T-th timestamp. Similarly, adopting a collision detection strategy to compare the second coordinate value of the first movable device at the T-th timestamp with the second coordinate value of the second movable device at the T-th timestamp to obtain a second comparison sub-result; the second comparison sub-result indicates the distance information between the first movable device and the second movable device in the Y direction at the T-th timestamp. Similarly, adopting a collision detection strategy to compare the third coordinate value of the first movable device at the T-th timestamp with the third coordinate value of the second movable device at the T-th timestamp to obtain a third comparison sub-result; the third comparison sub-result indicates the distance information between the first movable device and the second movable device in the Z direction at the T-th timestamp. In this way, a particle detection result can be generated based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result. Among them, when the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is less than or equal to a preset distance threshold, it indicates that the first movable device and the second movable device may collide at the T-th timestamp, and then trigger the execution of the following step S705; or, when the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is greater than the preset distance threshold, it indicates that the first movable device and the second movable device may not collide at the T-th timestamp, and then trigger the execution of the following step S706.

[0140] Further, considering that the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp may be a cuboid, the center point of the cuboid (i.e., the position of the first movable device when regarded as a particle) and the position of the second movable device at the T-th timestamp may have different preset distance thresholds for non-collision in the X, Y, and Z directions; that is to say, each coordinate value in the spatial position corresponds to a preset distance threshold, that is, each coordinate direction corresponds to a preset distance threshold. Based on this, after the air traffic control device obtains the comparison sub-results in the X, Y, and Z directions, namely the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result, based on the foregoing steps, the logic for generating the particle detection result may include: If any one of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is less than the corresponding preset distance threshold, then generate a particle detection result; at this time, the particle detection result indicates that the first movable device and the second movable device collide at the T-th timestamp. Or, if each of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is greater than or equal to the corresponding preset distance threshold, then generate a particle detection result; at this time, the particle detection result indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0141] Among them, the specific values of the preset distance thresholds in the X, Y, and Z directions are related to the lengths, widths, and heights of the spatio-temporal aggregates corresponding to the first movable device and the second movable device at the T-th timestamp respectively. For example, the Y direction is the length of the spatio-temporal aggregate, the length of the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp is 3, and the length of the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp is 5. Then, considering that the particle is located at the center point of the spatio-temporal aggregate, the preset distance threshold for the particle in the first spatio-temporal aggregate and the particle in the second spatio-temporal aggregate in the Y direction is determined to be 3 / 2 + 5 / 2 = 4. Another example: The Z direction is the height of the spatio-temporal aggregate, the height of the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp is 8, and the length of the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp is 6. Then, considering that the particle is located at the center point of the spatio-temporal aggregate, the preset distance threshold for the particle in the first spatio-temporal aggregate and the particle in the second spatio-temporal aggregate in the Z direction is determined to be 8 / 2 + 6 / 2 = 7.

[0142] For example, Figure 10As shown, assume that the spatial position of the first movable device when regarded as a particle at the T-th timestamp is (7, 8, 14), and the spatial position of the second movable device when regarded as a particle at the T-th timestamp is (10, 15, 4). Also, the preset distance threshold in the X direction, Y direction, and Z direction for the first movable device and the second movable device at the T-th timestamp is 2, 8, and 2 respectively. Then, the distance information in the X direction (i.e., the first comparison sub-result, or the difference) is determined to be 3, which is greater than the preset distance threshold of 2 in the X direction; similarly, the distance information in the Y direction (i.e., the second comparison sub-result) is determined to be 7, which is less than the preset distance threshold of 8 in the Y direction; similarly, the distance information in the Z direction (i.e., the third comparison sub-result) is determined to be 10, which is greater than the preset distance threshold of 2 in the Z direction. Since the distance information of 7 in the Y direction between the first movable device and the second movable device at the T-th timestamp is less than the preset distance threshold of 8, it is determined that there is an overlapping area between the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp. Further, it is determined that the first movable device and the second movable device will collide at the T-th timestamp. Then, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device will collide at the T-th timestamp.

[0143] S705: If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is less than or equal to the preset distance threshold, perform vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp.

[0144] Based on the particle detection process shown in the foregoing step S704, if the particle detection result for detecting the positions of the first movable device at the T-th timestamp and the second movable device at the T-th timestamp indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is less than or equal to the preset distance threshold, such as the distance information in at least one of the X, Y, and Z directions (i.e., the comparison sub-results mentioned above) is less than or equal to the corresponding preset distance threshold; it indicates that there may be an overlapping area between the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp, that is, the first movable device and the second movable device are very likely to collide at the T-th timestamp. Therefore, the embodiment of the present application also designs an extreme value detection strategy (or called vertex collision detection strategy) to further detect the collision situation between the first movable device and the second movable device at the T-th timestamp.

[0145] In a specific implementation, when the air traffic control device determines that the mass point detection results of the first movable device and the second movable device at the T-th time stamp indicate that the first movable device and the second movable device may collide, it can perform capsule extreme value calculation (where the capsule can immediately be the first spatio-temporal aggregate) on the first spatio-temporal aggregate corresponding to the first movable device at the T-th time stamp to obtain the extreme value vertices of the first spatio-temporal aggregate and the vertex coordinates of the extreme value vertices. Also, obtain the vertex coordinates of the extreme value vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th time stamp.

[0146] Among them: ① The extreme value vertices of a spatio-temporal aggregate (such as the first spatio-temporal aggregate or the second spatio-temporal aggregate) can refer to the points in the spatio-temporal aggregate where the spatial coordinates take extreme values (such as taking the maximum value or the minimum value). Here, the extreme value can mean that the X value, Y value, and Z value of the spatial coordinates are all the minimum coordinates in the spatio-temporal aggregate. In the case where the spatio-temporal aggregate is a cuboid, the points taking extreme values belong to the 8 vertices of the cuboid. At this time, the extreme value vertices of the spatio-temporal aggregate refer to the vertices among the multiple vertices included in the spatio-temporal aggregate where the spatial coordinates are extreme values; therefore, in the embodiments of the present application, the points taking extreme values can be called extreme value vertices. ② The embodiments of the present application do not limit the specific calculation process of performing capsule extreme value calculation on the spatio-temporal aggregate. For example, the process of performing capsule extreme value calculation on the first spatio-temporal aggregate can include but is not limited to: According to the position information of the first movable device at the T-th time stamp, the physical size information of the first movable device, and the attitude information of the first movable device at the T-th time stamp (the attitude information of the first movable device at the T-th time stamp is included in the track information to be detected of the first movable device), calculate the vertex coordinates of the extreme value vertices in the first spatio-temporal aggregate corresponding to the T-th time stamp. More specifically, knowing clearly the coordinates of the mass points in the first spatio-temporal aggregate according to the position information of the first movable device at the T-th time stamp, knowing the length, width, height, etc. of the first spatio-temporal aggregate according to the first spatio-temporal aggregate constructed for the first movable device at the T-th time stamp, and when the attitude information of the first movable device at the T-th time stamp is already included in the track information to be detected of the first movable device, it is supported to put the X values, Y values, and Z values of all points in the first spatio-temporal aggregate into three sets respectively; in this way, the spatial coordinates composed of the maximum values selected from each set are the vertex coordinates of the extreme value vertices taking the maximum value in the first spatio-temporal aggregate. Similarly, the spatial coordinates composed of the minimum values selected from each set are the vertex coordinates of the extreme value vertices taking the minimum value in the first spatio-temporal aggregate, so as to obtain the extreme value vertices of the first spatio-temporal aggregate and the vertex coordinates of the extreme value vertices.

[0147] Based on the above description, after the air traffic control equipment obtains the vertex coordinates of the extreme value vertices of the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the vertex coordinates of the extreme value vertices of the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp, it can calculate the vertex coordinates of the extreme value vertices in the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the vertex coordinates of the extreme value vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp by using the extreme value check rule, and obtain the collision detection result corresponding to the T-th timestamp. Among them, the collision detection result corresponding to the T-th timestamp is used to indicate that: the first movable device and the second movable device collide at the T-th timestamp, or do not collide at the T-th timestamp.

[0148] Among them, the extreme value check rule can be expressed as the following judgment condition:

[0149] (X 0min <X imax ) AND (X imin <X 0max ) AND (Y 0min <Y imax ) AND (Y imin <Y 0max ) AND (Z 0min <Z imax ) AND (Z imin <Z 0mmax )

[0150] Among them, 0 is the first movable device, i is the i-th second movable device, i takes values of 1, 2,..., n, and n is a positive integer. X 0min 、Y 0min and Z 0min are the vertex coordinates of the smallest extreme value vertex in the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp; X 0max 、Y 0max and Z 0mmax are the vertex coordinates of the largest extreme value vertex in the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp. X imin 、Y imin and Z imin are the vertex coordinates of the smallest extreme value vertex in the second spatio-temporal aggregate corresponding to the i-th second movable device at the T-th timestamp; X imax 、Y imax and Z imax are the vertex coordinates of the largest extreme value vertex in the second spatio-temporal aggregate corresponding to the i-th second movable device at the T-th timestamp.

[0151] According to the extreme value checking rules given above, there are multiple judgment expressions in the extreme value detection rules, specifically including 6 judgment expressions. For example, the judgment expression is (X 0min <X imax ). Then, when each judgment expression among multiple judgment expressions is true, that is, when the comparison relationship represented by each judgment expression holds, it indicates that there is an overlapping area (or overlapping phenomenon) between the first spatio-temporal aggregate corresponding to the first movable device at the T-th time stamp and the second spatio-temporal aggregate corresponding to the i-th second movable device at the T-th time stamp. Then, it is determined that the collision detection result corresponding to the T-th time stamp indicates that the first movable device and the i-th second movable device collide at the T-th time stamp. On the contrary, when at least one of the multiple judgment expressions is false, it indicates that there is no overlapping area between the first spatio-temporal aggregate corresponding to the first movable device at the T-th time stamp and the second spatio-temporal aggregate corresponding to the i-th second movable device at the T-th time stamp. Then, it is determined that the collision detection result corresponding to the T-th time stamp indicates that the first movable device and the i-th second movable device do not collide at the T-th time stamp.

[0152] It should be noted that: ① In the process of performing vertex collision detection on the first movable device and the i-th second movable device at the T-th time stamp by using the above extreme value checking rules, if it is detected that a collision will occur, then it is possible to choose to exit the collision judgment process between the first movable device and the i-th second movable device. At this time, the judgment result of the first movable device and the i-th second movable device at the T-th time stamp indicates that the two will collide. It is also possible to choose to continue to execute the judgment of subsequent time stamps, so that all collision points (such as the target time stamps where a collision will occur) where the first movable device and the i-th second movable device may collide can be marked from multiple time stamps, and the result is returned to the object holding the first movable device. ② For the first movable device, it can be determined that the first movable device will not collide when moving along the planned trajectory only when it is judged that it does not collide with each of the n second movable devices; if the first movable device collides with any one of the n second movable devices, it is determined that the first movable device will collide when moving along the planned trajectory.

[0153] S706: If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th time stamp is greater than the preset distance threshold, then the collision detection result corresponding to the T-th time stamp is obtained; the collision detection result corresponding to the T-th time stamp indicates that the first movable device and the second movable device do not collide at the T-th time stamp.

[0154] Based on the particle detection process shown in the foregoing step S704, if the particle detection result of detecting particles for the position of the first movable device at the T-th timestamp and the position of the second movable device at the T-th timestamp indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is greater than a preset distance threshold, such as the distance information in the X, Y, and Z directions (i.e., the comparison sub-results mentioned above) are all greater than the corresponding preset distance thresholds; it indicates that there is no overlapping area between the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp, that is, the first movable device and the second movable device will not collide at the T-th timestamp. Then, it is not necessary to perform the vertex collision detection shown in step S705, but directly generate the collision detection result corresponding to the first movable device at the T-th timestamp, and at this time, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device will not collide at the T-th timestamp.

[0155] From the collision detection strategy shown in steps S704 - S706 above, on the one hand, since the particles in the first spatio-temporal aggregate and the second spatio-temporal aggregate are easily obtained. For example, the particles in the first spatio-temporal aggregate are the position information of the first movable device at the corresponding timestamp, and the calculation amount of the difference between the particles in the X, Y, and Z directions is also very small. Therefore, the embodiment of the present application sets this particle detection method to implement the collision detection of the first movable device, which can reduce the calculation amount of the collision detection while ensuring the accuracy of the collision detection. On the other hand, the embodiment of the present application only triggers the execution of the subsequent vertex collision detection when the particle detection result indicates that the first movable device and the second movable device may collide, reducing the calculation overhead required for the collision detection, and greatly improving the detection efficiency of the collision detection by introducing the vertex collision detection.

[0156] S707: Generate a collision feedback result of the first movable device according to the collision detection results corresponding to each timestamp among multiple timestamps.

[0157] As described above, the track period corresponding to the first movable device includes multiple timestamps. Then, only when the collision detection results corresponding to each timestamp among the multiple timestamps all indicate that the first movable device and the second movable device will not collide at the corresponding timestamp, the generated collision feedback result of the first movable device indicates that the first movable device will not collide when moving according to the planned track. On the contrary, if there is a timestamp (one or more) among the multiple timestamps whose corresponding collision detection result indicates that the first movable device and the second movable device will collide at the corresponding timestamp, a collision feedback result of the first movable device is generated, and at this time, the collision feedback result indicates that the first movable device and the second movable device will collide.

[0158] Further, after the air traffic control device obtains the collision feedback result of the first movable device, if the collision feedback result indicates that the first movable device may collide, then the embodiments of the present application also support feedback of the collision situation to the object holding the first movable device, so that the object can timely correct the track and independently decide whether to initiate a track application again. In a specific implementation, after the air traffic control device determines that the collision feedback result of the first movable device indicates that the first movable device may collide, it can screen out the target timestamps corresponding to the collision detection results indicating a collision from multiple timestamps of the track period corresponding to the first movable device, and generate a correction prompt message based on the target timestamps, and the number of target timestamps is one or more. Then, the air traffic control device outputs the correction prompt message to the first movable device, so that the object holding the first movable device can adjust the track based on the correction prompt message, so that the first movable device after adjusting the track does not collide with other second movable devices that have applied for flight.

[0159] It should be noted that the embodiments of the present application do not limit the specific content indicated by the correction prompt message generated by the air traffic control device. Exemplarily, the correction prompt message can be used to indicate but is not limited to one or more of the following: the first movable device will collide at the target timestamp, the collision component (or collision direction, collision position, etc. information indicating the collision point) when the first movable device collides, and the adjustment information of the track information of the first movable device at the target timestamp (such as the specific adjustment method, so that after the object adjusts the track of the first movable device according to the adjustment information, the first movable device will not collide, etc.).

[0160] In summary, on the one hand, in combination with the physical size of the first movable device and the interference in the surrounding environment, the embodiments of the present application creatively provide a construction logic for a three-layer spatio-temporal aggregate. By constructing a corresponding first spatio-temporal aggregate for the first movable device at each time stamp, it is ensured that the spatio-temporal aggregate used for subsequent collision detection processing can not only completely wrap the physical components of the entire first movable device, but also wrap the interference range of the interference signals generated by the first movable device on the surrounding environment during operation, thereby greatly improving the safety of the first movable device during operation. On the other hand, the traditional use of an elliptical cylinder for spatial collision and overlap between different capsules has defects such as large computational amount, cumbersome process, and long time consumption. However, the air traffic control equipment has relatively high requirements for the timeliness of collision detection of multiple pending track information submitted by multiple operators, and often hopes to obtain the result of whether a collision occurs as soon as possible. In this regard, in combination with the characteristics of the first spatio-temporal aggregate, the embodiments of the present application creatively provide a new collision detection strategy. This strategy supports using simple particle detection for collision detection first, and only when the particle detection result indicates that a collision may occur, further introducing vertex collision detection to achieve more accurate collision detection. It can be seen that this double-layer collision detection method in the embodiments of the present application not only ensures the accuracy of collision detection, but also greatly improves the computational efficiency of collision detection compared with the traditional hundreds or even thousands of detections, which helps the air traffic control equipment to detect multiple pending tracks.

[0161] The method of the embodiments of the present application is described in detail above. To facilitate better implementation of the above solutions of the embodiments of the present application, correspondingly, the device of the embodiments of the present application is provided below. In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of the module or unit.

[0162] Figure 11 The structural schematic diagram of a collision detection device provided by an exemplary embodiment of the present application is shown; this collision detection device can be used to execute Figure 2 and Figure 7 part or all of the steps in the method embodiments shown. Please refer to Figure 11 . The device includes the following units:

[0163] An acquisition unit 1101, configured to acquire the to-be-inspected track information of a first movable device, where the to-be-inspected track information includes: multiple timestamps of a track period corresponding to the first movable device, position information of the first movable device at each timestamp, and physical size information of the first movable device;

[0164] A processing unit 1102, configured to construct a first spatio-temporal aggregate corresponding to a corresponding timestamp based on the position information of the first movable device at each timestamp and the physical size information of the first movable device; the first spatio-temporal aggregate is a cubic space structure constructed based on the physical size information of the first movable device, the interference distance and the operating range of the first movable device at the corresponding timestamp;

[0165] The processing unit 1102 is further configured to acquire the existing track information of a second movable device; the existing track information includes: multiple timestamps of a track period corresponding to the second movable device and a second spatio-temporal aggregate corresponding to each timestamp;

[0166] The processing unit 1102 is further configured to perform a collision detection process on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp by using a collision detection strategy, and obtain a collision detection result corresponding to the same timestamp;

[0167] The processing unit 1102 is further configured to generate a collision feedback result of the first movable device according to the collision detection result corresponding to each timestamp among multiple timestamps.

[0168] In one implementation, the to-be-inspected track information further includes speed information and attitude information of the first movable device at each timestamp; any timestamp among multiple timestamps of a track period corresponding to the first movable device is represented as the T-th timestamp; T is an integer greater than zero;

[0169] When the processing unit 1102 is configured to construct a first spatio-temporal aggregate corresponding to a corresponding timestamp based on the position information of the first movable device at each of the timestamps and the physical size information of the first movable device, it is specifically configured to:

[0170] Regarding the first movable device as a particle, and constructing a core layer corresponding to the T-th timestamp according to the position information and speed information of the particle at the T-th timestamp, and the first time period and the second time period adjacent to the T-th timestamp of the particle;

[0171] Based on the core layer corresponding to the T-th timestamp, the attitude information of the first movable device at the T-th timestamp, and the physical size information of the first movable device, constructing a physical layer corresponding to the T-th timestamp;

[0172] Construct an interference layer corresponding to the T-th timestamp based on the interference distance of the physical layer and the first movable device to the surrounding environment; the interference layer corresponding to the T-th timestamp is the first spatio-temporal aggregate of the first movable device at the T-th timestamp.

[0173] In one implementation, the interference layer includes a physical layer, and the physical layer includes a core layer; where:

[0174] The core layer is a cubic space structure composed of all spatial positions that the first movable device can reach at the T-th timestamp when the first movable device is used as a particle for trajectory planning;

[0175] The physical layer is a cubic space structure that can enclose the outer contour of the first movable device when the first movable device moves to the edge of the core layer;

[0176] The interference layer is a cubic space structure that can enclose the interference distance generated by the first movable device to the surrounding environment when the first movable device moves to the edge of the core layer.

[0177] In one implementation, any timestamp among multiple timestamps of the trajectory period corresponding to the first movable device is denoted as the T-th timestamp; the processing unit 1102, when using a collision detection strategy to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp and obtaining the collision detection result corresponding to the same timestamp, is specifically used for:

[0178] Adopt a collision detection strategy to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp to obtain a particle detection result;

[0179] If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is less than or equal to a preset distance threshold, then perform vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp;

[0180] Among them, the collision detection result corresponding to the T-th timestamp is used to indicate that: the first movable device and the second movable device collide at the T-th timestamp, or do not collide at the T-th timestamp.

[0181] In one implementation, the manifestation form of the position information is in the form of spatial coordinates, and the spatial coordinates include a first coordinate value, a second coordinate value, and a third coordinate value; the processing unit 1102, when using a collision detection strategy to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp and obtaining a particle detection result, is specifically used for:

[0182] Adopt a collision detection strategy to compare the first coordinate value of the first movable device at the T-th timestamp with the first coordinate value of the second movable device at the T-th timestamp to obtain a first comparison sub-result;

[0183] Adopt a collision detection strategy to compare the second coordinate value of the first movable device at the T-th timestamp with the second coordinate value of the second movable device at the T-th timestamp to obtain a second comparison sub-result;

[0184] Adopt a collision detection strategy to compare the third coordinate value of the first movable device at the T-th timestamp with the third coordinate value of the second movable device at the T-th timestamp to obtain a third comparison sub-result;

[0185] Generate a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result.

[0186] In one implementation, each coordinate value in the spatial position corresponds to a preset distance threshold; when the processing unit 1102 generates a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result, it is specifically used for:

[0187] If any one of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is less than the corresponding preset distance threshold, generate a particle detection result; the particle detection result indicates that the first movable device and the second movable device collide at the T-th timestamp; or,

[0188] If each of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is greater than or equal to the corresponding preset distance threshold, generate a particle detection result; the particle detection result indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0189] In one implementation, the track information to be detected of the first movable device further includes the attitude information of the first movable device at the T-th timestamp; when the processing unit 1102 performs vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp, it is specifically used for:

[0190] According to the position information of the first movable device at the T-th timestamp, the physical size information of the first movable device, and the attitude information of the first movable device at the T-th timestamp, calculate the vertex coordinates of the extreme vertices in the first spatio-temporal aggregate corresponding to the T-th timestamp;

[0191] Obtain the vertex coordinates of the extreme value vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp;

[0192] Use the extreme value check rule to calculate the vertex coordinates of the extreme value vertices in the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the vertex coordinates of the extreme value vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp, and obtain the collision detection result corresponding to the T-th timestamp.

[0193] In one implementation, the extreme value vertices of the spatio-temporal aggregate refer to the vertices with extreme spatial coordinates among the multiple vertices included in the spatio-temporal aggregate;

[0194] The extreme value check rule includes multiple judgment expressions; when each judgment expression in the multiple judgment expressions is true, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device collide at the T-th timestamp; when at least one judgment expression in the multiple judgment expressions is false, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0195] In one implementation, the processing unit 1102 is further configured to:

[0196] If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is greater than the preset distance threshold, obtain the collision detection result corresponding to the T-th timestamp; the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0197] In one implementation, when the processing unit 1102 is used to generate the collision feedback result of the first movable device according to the collision detection results corresponding to each timestamp among multiple timestamps, it is specifically configured to:

[0198] If there is a collision detection result corresponding to a timestamp among the multiple timestamps indicating that the first movable device and the second movable device collide at the corresponding timestamp, generate the collision feedback result of the first movable device; the collision feedback result indicates that the first movable device and the second movable device will collide;

[0199] The processing unit 1102 is further configured to:

[0200] Screen out the target timestamps corresponding to the collision detection results indicating collisions from the multiple timestamps, and generate a correction prompt message based on the target timestamps; output the correction prompt message to the first movable device.

[0201] In one implementation, the first movable device or the second movable device includes any one of the following: an aircraft, an intelligent robot, a vehicle, or a ship.

[0202] According to an embodiment of the present application, Figure 11 Each unit in the collision detection device shown can be separately or wholly combined into one or several other units to form, or a certain (some) unit can be further split into multiple smaller units in terms of function to form, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above units are divided based on logical functions. In practical applications, the function of one unit can also be realized by multiple units, or the functions of multiple units can be realized by one unit. In other embodiments of the present application, the collision detection device may also include other units. In practical applications, these functions can also be assisted by other units and can be realized by the cooperation of multiple units. According to another embodiment of the present application, it is possible to construct the collision detection device shown in Figure 2 and Figure 7 by running a computer program (including program code) that can execute the respective steps involved in the corresponding method shown in Figure 11 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), a random access storage medium (RAM), and a read-only storage medium (ROM), and to implement the collision detection method of the embodiments of the present application. The computer program can be recorded on, for example, a computer-readable recording medium, loaded into the above computing device through the computer-readable recording medium, and run therein.

[0203] In the embodiments of the present application, a new collision detection solution for movable devices is provided; on the one hand, fully considering the physical size of the movable device itself and the interference around the movable device during movement, a corresponding first spatio-temporal aggregate is constructed for the movable device at different timestamps. Compared with performing collision detection by treating the first movable device as a mass point, the accuracy of collision detection can be improved based on this first spatio-temporal aggregate that includes the physical size and the interference distance. On the other hand, a new collision detection strategy is designed to perform collision detection on the first spatio-temporal aggregate corresponding to the first movable device and the second spatio-temporal aggregate corresponding to the second movable device. Compared with traditional detection methods, the number of detections is effectively reduced, thereby improving the efficiency of collision detection.

[0204] Figure 12 The structural schematic diagram of a computer device provided by an exemplary embodiment of the present application is shown. Please refer to Figure 12, the computer device includes a processor 1201, a communication interface 1202, and a computer-readable storage medium 1203. Among them, the processor 1201, the communication interface 1202, and the computer-readable storage medium 1203 can be connected through a bus or other means. Among them, the communication interface 1202 is used to receive and send data. The computer-readable storage medium 1203 can be stored in the memory of the electronic device. The computer-readable storage medium 1203 is used to store a computer program, and the computer program includes program instructions. The processor 1201 is used to execute the program instructions stored in the computer-readable storage medium 1203. The processor 1201 (or CPU (Central Processing Unit, central processor)) is the computing core and control core of the computer device, and is adapted to implement one or more instructions, specifically adapted to load and execute one or more instructions to implement the corresponding method flow or corresponding function.

[0205] The embodiment of the present application also provides a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in the computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and the storage space stores the processing system of the computer device. And, one or more instructions suitable for being loaded and executed by the processor 1201 are also stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory; optionally, it can also be at least one computer-readable storage medium located far from the aforementioned processor.

[0206] In one embodiment, one or more instructions are stored in the computer-readable storage medium; the processor 1201 loads and executes one or more instructions stored in the computer-readable storage medium to implement the corresponding steps in the above-mentioned collision detection method embodiment; in a specific implementation, one or more instructions in the computer-readable storage medium are loaded and executed by the processor 1201 as follows:

[0207] Obtain the track information to be detected of the first movable device. The track information to be detected includes: a plurality of timestamps of the track period corresponding to the first movable device, the position information of the first movable device at each timestamp, and the physical size information of the first movable device;

[0208] Based on the position information of the first movable device at each time stamp and the physical size information of the first movable device, construct a first spatio-temporal aggregate corresponding to the corresponding time stamp; the first spatio-temporal aggregate is a cubic space structure constructed based on the physical size information of the first movable device, the interference distance and the operating range of the first movable device at the corresponding time stamp;

[0209] Obtain the existing track information of the second movable device; the existing track information includes: multiple time stamps corresponding to the track period of the second movable device and a second spatio-temporal aggregate corresponding to each time stamp;

[0210] Adopt a collision detection strategy to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same time stamp, and obtain a collision detection result corresponding to the same time stamp;

[0211] Generate a collision feedback result of the first movable device according to the collision detection result corresponding to each time stamp among multiple time stamps.

[0212] In one implementation, the track information to be detected further includes the speed information and attitude information of the first movable device at each time stamp; any time stamp among the multiple time stamps corresponding to the track period of the first movable device is represented as the T-th time stamp; T is an integer greater than zero;

[0213] When one or more instructions in the computer-readable storage medium are loaded by the processor 1201 and execute to construct a first spatio-temporal aggregate corresponding to the corresponding time stamp based on the position information of the first movable device at each of the time stamps and the physical size information of the first movable device, the following steps are specifically executed:

[0214] Regard the first movable device as a mass point, and construct a core layer corresponding to the T-th time stamp according to the position information and speed information of the mass point at the T-th time stamp, and the first time period and the second time period adjacent to the T-th time stamp;

[0215] Based on the core layer corresponding to the T-th time stamp, the attitude information of the first movable device at the T-th time stamp and the physical size information of the first movable device, construct a physical layer corresponding to the T-th time stamp;

[0216] Based on the physical layer and the interference distance of the first movable device to the surrounding environment, construct an interference layer corresponding to the T-th time stamp; the interference layer corresponding to the T-th time stamp is the first spatio-temporal aggregate of the first movable device at the T-th time stamp.

[0217] In one implementation, the interference layer includes the physical layer, and the physical layer includes the core layer; where:

[0218] The core layer is a cubic space structure composed of all the spatial positions that the first movable device can reach at the T-th timestamp when the first movable device is regarded as a particle for trajectory planning;

[0219] The physical layer is a cubic space structure that can enclose the outer contour of the first movable device when the first movable device moves to the edge of the core layer;

[0220] The interference layer is a cubic space structure that can enclose the interference distance generated by the first movable device on the surrounding environment when the first movable device moves to the edge of the core layer.

[0221] In one implementation, any one of the multiple timestamps corresponding to the trajectory period of the first movable device is represented as the T-th timestamp; when one or more instructions in the computer-readable storage medium are loaded by the processor 1201 and executed to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp by adopting a collision detection strategy to obtain the collision detection result corresponding to the same timestamp, the following steps are specifically executed:

[0222] Adopt a collision detection strategy to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp to obtain a particle detection result;

[0223] If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is less than or equal to a preset distance threshold, then perform vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp;

[0224] Among them, the collision detection result corresponding to the T-th timestamp is used to indicate that: the first movable device and the second movable device collide at the T-th timestamp, or do not collide at the T-th timestamp.

[0225] In one implementation, the manifestation form of the position information is in the form of spatial coordinates, and the spatial coordinates include a first coordinate value, a second coordinate value, and a third coordinate value; when one or more instructions in the computer-readable storage medium are loaded by the processor 1201 and executed to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp by adopting a collision detection strategy to obtain a particle detection result, the following steps are specifically executed:

[0226] Adopt a collision detection strategy to compare the first coordinate value of the first movable device at the T-th timestamp with the first coordinate value of the second movable device at the T-th timestamp to obtain a first comparison sub-result;

[0227] Adopt a collision detection strategy to compare the second coordinate value of the first movable device at the T-th timestamp with the second coordinate value of the second movable device at the T-th timestamp, and obtain a second comparison sub-result;

[0228] Adopt a collision detection strategy to compare the third coordinate value of the first movable device at the T-th timestamp with the third coordinate value of the second movable device at the T-th timestamp, and obtain a third comparison sub-result;

[0229] Generate a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result.

[0230] In one implementation, each coordinate value in the spatial position corresponds to a preset distance threshold; when one or more instructions in the computer-readable storage medium are loaded by the processor 1201 and execute to generate a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result, the following steps are specifically executed:

[0231] If any one of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is less than the corresponding preset distance threshold, generate a particle detection result; the particle detection result indicates that the first movable device and the second movable device collide at the T-th timestamp; or,

[0232] If each of the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result is greater than or equal to the corresponding preset distance threshold, generate a particle detection result; the particle detection result indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0233] In one implementation, the to-be-detected track information of the first movable device further includes the attitude information of the first movable device at the T-th timestamp; when one or more instructions in the computer-readable storage medium are loaded by the processor 1201 and execute to perform vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp, and obtain the collision detection result corresponding to the T-th timestamp, the following steps are specifically executed:

[0234] According to the position information of the first movable device at the T-th timestamp, the physical size information of the first movable device, and the attitude information of the first movable device at the T-th timestamp, calculate the vertex coordinates of the extreme vertices in the first spatio-temporal aggregate corresponding to the T-th timestamp;

[0235] Obtain the vertex coordinates of the extreme vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp;

[0236] The vertex coordinates of the extreme value vertices in the first spatio-temporal aggregate corresponding to the first movable device at the T-th timestamp and the vertex coordinates of the extreme value vertices in the second spatio-temporal aggregate corresponding to the second movable device at the T-th timestamp are calculated using the extreme value check rule to obtain the collision detection result corresponding to the T-th timestamp.

[0237] In one implementation, the extreme value vertex of the spatio-temporal aggregate refers to the vertex with extreme spatial coordinates among the multiple vertices included in the spatio-temporal aggregate;

[0238] The extreme value check rule includes multiple judgment expressions; when each judgment expression in the multiple judgment expressions is true, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device collide at the T-th timestamp; when at least one judgment expression in the multiple judgment expressions is false, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0239] In one implementation, one or more instructions in the computer-readable storage medium are loaded by the processor 1201 and further execute the following steps:

[0240] If the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is greater than the preset distance threshold, then the collision detection result corresponding to the T-th timestamp is obtained; the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

[0241] In one implementation, one or more instructions in the computer-readable storage medium are loaded by the processor 1201 and when generating the collision feedback result of the first movable device according to the collision detection result corresponding to each timestamp among multiple timestamps, specifically execute the following steps:

[0242] If the collision detection result corresponding to a timestamp among the multiple timestamps indicates that the first movable device and the second movable device collide at the corresponding timestamp, then the collision feedback result of the first movable device is generated; the collision feedback result indicates that the first movable device and the second movable device will collide;

[0243] One or more instructions in the computer-readable storage medium are loaded by the processor 1201 and further execute the following steps:

[0244] Filter out the target timestamps corresponding to the collision detection results indicating collisions from the multiple timestamps, and generate a correction prompt message based on the target timestamps; output the correction prompt message to the first movable device.

[0245] In one implementation, the first movable device or the second movable device includes any one of the following: an aircraft, an intelligent robot, a vehicle, or a ship.

[0246] Based on the same inventive concept, the principle and beneficial effects of the computer device provided in the embodiments of the present application for solving problems are similar to those of the collision detection method in the method embodiments of the present application. For the principle and beneficial effects of the method implementation, refer to the relevant content. For the sake of brevity, they will not be elaborated here.

[0247] The embodiments of the present application also provide a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned collision detection method.

[0248] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled artisans can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0249] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data processing device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0250] As described above, it is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any person skilled in the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A collision detection method, characterized in that, it includes: Obtain the track information to be detected of the first movable device, and the track information to be detected includes: multiple timestamps of the track period corresponding to the first movable device, the position information of the first movable device at each timestamp, and the physical size information of the first movable device; Based on the position information of the first movable device at each timestamp and the physical size information of the first movable device, construct a first spatio-temporal aggregate corresponding to the corresponding timestamp; the first spatio-temporal aggregate is a cubic space structure constructed based on the physical size information of the first movable device, the interference distance and the operating range of the first movable device at the corresponding timestamp; Obtain the existing track information of the second movable device; the existing track information includes: multiple timestamps of the track period corresponding to the second movable device and the second spatio-temporal aggregate corresponding to each timestamp; Adopt a collision detection strategy to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp, and obtain a collision detection result corresponding to the same timestamp; Generate a collision feedback result of the first movable device according to the collision detection results corresponding to each of the multiple timestamps.

2. The method according to claim 1, characterized in that, the track information to be detected further includes the speed information and attitude information of the first movable device at each timestamp; any one of the multiple timestamps of the track period corresponding to the first movable device is represented as the T-th timestamp; T is an integer greater than zero; The constructing a first spatio-temporal aggregate corresponding to the corresponding timestamp based on the position information of the first movable device at each timestamp and the physical size information of the first movable device includes: Regarding the first movable device as a particle, and constructing a core layer corresponding to the T-th timestamp according to the position information and speed information of the particle at the T-th timestamp, and the first time period and the second time period adjacent to the T-th timestamp of the particle; Based on the core layer corresponding to the T-th timestamp, the attitude information of the first movable device at the T-th timestamp, and the physical size information of the first movable device, construct a physical layer corresponding to the T-th timestamp; Based on the physical layer and the interference distance of the first movable device to the surrounding environment, construct an interference layer corresponding to the T-th timestamp; the interference layer corresponding to the T-th timestamp is the first spatio-temporal aggregate of the first movable device at the T-th timestamp.

3. The method according to claim 2, characterized in that, the interference layer contains the physical layer, and the physical layer contains the core layer; where: The core layer is a cubic space structure composed of all spatial positions that the first movable device can reach at the T-th timestamp when the first movable device is regarded as a particle for track planning; The physical layer is a cubic space structure that can enclose the outer contour of the first movable device when the first movable device moves to the edge of the core layer; The interference layer is a cubic space structure that can enclose the interference distance generated by the first movable device on the surrounding environment when the first movable device moves to the edge of the core layer.

4. The method according to claim 1, wherein, any one of the multiple timestamps corresponding to the track period of the first movable device is represented as the T-th timestamp; the collision detection process of the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp by using the collision detection strategy to obtain the collision detection result corresponding to the same timestamp includes: using the collision detection strategy to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp to obtain a particle detection result; if the particle detection result indicates that the distance information between the first movable device and the second movable device at the T-th timestamp is less than or equal to a preset distance threshold, then perform vertex collision detection on the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp; wherein, the collision detection result corresponding to the T-th timestamp is used to indicate that: the first movable device and the second movable device collide at the T-th timestamp, or do not collide at the T-th timestamp.

5. The method according to claim 4, wherein, the representation form of the position information is in the form of spatial coordinates, and the spatial coordinates include a first coordinate value, a second coordinate value, and a third coordinate value; the using the collision detection strategy to perform particle collision detection on the position information of the first movable device at the T-th timestamp and the position information of the second movable device at the T-th timestamp to obtain a particle detection result includes: using the collision detection strategy to compare the first coordinate value of the first movable device at the T-th timestamp with the first coordinate value of the second movable device at the T-th timestamp to obtain a first comparison sub-result; using the collision detection strategy to compare the second coordinate value of the first movable device at the T-th timestamp with the second coordinate value of the second movable device at the T-th timestamp to obtain a second comparison sub-result; using the collision detection strategy to compare the third coordinate value of the first movable device at the T-th timestamp with the third coordinate value of the second movable device at the T-th timestamp to obtain a third comparison sub-result; generating a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result.

6. The method according to claim 5, wherein, each coordinate value in the spatial position corresponds to a preset distance threshold; the generating a particle detection result based on the first comparison sub-result, the second comparison sub-result, and the third comparison sub-result includes: If any one of the first comparator result, the second comparator result, and the third comparator result is less than the corresponding preset distance threshold, a particle detection result is generated; the particle detection result indicates that the first movable device and the second movable device collide at the T-th timestamp; or, If each of the first comparator result, the second comparator result, and the third comparator result is greater than or equal to the corresponding preset distance threshold, a particle detection result is generated; the particle detection result indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

7. The method according to claim 4 or 6, characterized in that the track information to be detected of the first movable device further includes the attitude information of the first movable device at the T-th timestamp; the vertex collision detection of the vertices of the first spatio-temporal aggregate corresponding to the T-th timestamp and the vertices of the second spatio-temporal aggregate corresponding to the T-th timestamp to obtain the collision detection result corresponding to the T-th timestamp includes: calculating the vertex coordinates of the extreme vertices in the first spatio-temporal aggregate corresponding to the T-th timestamp according to the position information of the first movable device at the T-th timestamp, the physical size information of the first movable device, and the attitude information of the first movable device at the T-th timestamp; obtaining the vertex coordinates of the extreme vertices in the second spatio-temporal aggregate corresponding to the T-th timestamp of the second movable device; using the extreme value checking rule to calculate the vertex coordinates of the extreme vertices in the first spatio-temporal aggregate corresponding to the T-th timestamp of the first movable device and the vertex coordinates of the extreme vertices in the second spatio-temporal aggregate corresponding to the T-th timestamp of the second movable device to obtain the collision detection result corresponding to the T-th timestamp.

8. The method according to claim 7, characterized in that the extreme vertex of the spatio-temporal aggregate refers to the vertex with extreme spatial coordinates among the multiple vertices included in the spatio-temporal aggregate; the extreme value checking rule includes a plurality of judgment expressions; when each of the plurality of judgment expressions is true, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device collide at the T-th timestamp; when at least one of the plurality of judgment expressions is false, the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

9. The method according to claim 4 or 6, characterized in that the method further includes: if the distance information when the particle detection result indicates that the first movable device and the second movable device are at the T-th timestamp is greater than the preset distance threshold, obtaining the collision detection result corresponding to the T-th timestamp; the collision detection result corresponding to the T-th timestamp indicates that the first movable device and the second movable device do not collide at the T-th timestamp.

10. The method according to claim 1 or 4, It is characterized in that generating the collision feedback result of the first movable device according to the collision detection results corresponding to each of the multiple timestamps includes: if there is a collision detection result corresponding to a timestamp among the multiple timestamps indicating that the first movable device and the second movable device will collide at the corresponding timestamp, generating the collision feedback result of the first movable device; the collision feedback result indicates that the first movable device and the second movable device will collide; The method further includes: screening out target timestamps corresponding to the collision detection results indicating collisions from the multiple timestamps, generating correction prompt information based on the target timestamps; and outputting the correction prompt information to the first movable device.

11. The method according to claim 1, It is characterized in that either the first movable device or the second movable device includes any one of the following: an aircraft, an intelligent robot, a vehicle or a ship.

12. A collision detection device, It is characterized in that including: an acquisition unit, configured to acquire the track information to be detected of the first movable device, where the track information to be detected includes: multiple timestamps of the track period corresponding to the first movable device, the position information of the first movable device at each of the timestamps, and the physical size information of the first movable device; a processing unit, configured to construct a first spatio-temporal aggregate corresponding to the corresponding timestamp based on the position information of the first movable device at each of the timestamps and the physical size information of the first movable device; the first spatio-temporal aggregate is a cubic space structure constructed based on the physical size information of the first movable device, the interference distance and the operating range of the first movable device at the corresponding timestamp; The processing unit is further configured to acquire the existing track information of the second movable device; the existing track information includes: multiple timestamps of the track period corresponding to the second movable device and the second spatio-temporal aggregate corresponding to each of the timestamps; The processing unit is further configured to perform collision detection processing on the first spatio-temporal aggregate and the second spatio-temporal aggregate corresponding to the same timestamp by using a collision detection strategy to obtain a collision detection result corresponding to the same timestamp; The processing unit is further configured to generate the collision feedback result of the first movable device according to the collision detection results corresponding to each of the multiple timestamps.

13. A computer device, It is characterized in that including: a processor, adapted to execute a computer program; a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the collision detection method according to any one of claims 1-11 is implemented.

14. A computer-readable storage medium, It is characterized in that the computer-readable storage medium stores a computer application program, and when the computer application program is executed, the collision detection method according to any one of claims 1-11 is implemented.

15. A computer program product, It is characterized in that The computer program product includes computer instructions which, when executed by a processor, implement the collision detection method according to any one of claims 1-11.

Images