Vehicle control method and device, computer equipment and readable storage medium

Through real-time monitoring and obstacle prediction of thermal imaging cameras, the vehicle driving path is dynamically adjusted, which solves the safety hazards caused by changes in obstacle positions of autonomous vehicles and improves driving safety.

CN118877014APending Publication Date: 2024-11-01NEOLITHIC HUITONG TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411052819.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

In autonomous vehicles, due to uncontrollable traffic conditions, the driving path formulated before departure may become impassable due to changes in the position of obstacles after departure, resulting in reduced safety hazards and driving safety.

Method used

Thermal imaging images of the target space are collected in real time through the thermal imaging camera, the current and historical positions of the obstacles are determined, and the current and historical positions are classified into stationary and non-stationary obstacles, the future location is predicted, and the vehicle's driving path is dynamically adjusted to avoid obstacles.

Benefits of technology

Improve the safety of the vehicle when driving, avoid traffic accidents caused by changes in the position of obstacles, and ensure that the vehicle can adapt to changing traffic conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118877014A_ABST
    Figure CN118877014A_ABST
Patent Text Reader

Abstract

The invention provides a vehicle control method and device, computer equipment and a readable storage medium, and the method comprises the steps: collecting a thermal imaging image of a target space in real time through a thermal imaging camera; obstacles existing in the target space and the current position of each obstacle at the current moment are determined according to the thermal imaging image collected at the current moment; the obstacles are classified according to the historical positions of the obstacles in the thermal imaging images collected at a plurality of historical moments, and the categories of the obstacles comprise static obstacles and non-static obstacles; based on the type of each obstacle, determining a vehicle driving path in the target space at the future moment according to the current position and the historical position of each obstacle; and controlling the vehicle to run along the vehicle running path at the future moment. By the adoption of the method, potential safety hazards in the vehicle driving process are avoided, and meanwhile the vehicle driving safety is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle driving, and in particular to a vehicle control method, device, computer equipment and readable storage medium. Background Art

[0002] With the development of artificial intelligence technology and the continuous progress of the vehicle industry, the vehicle's autonomous driving technology is becoming more and more mature. Autonomous driving, also known as unmanned driving, means that there is no need for a driver to drive the vehicle. Instead, through the collaborative cooperation of artificial intelligence, visual computing, radar, monitoring devices and global positioning systems, the controller automatically and safely operates the vehicle to drive the car on the road.

[0003] In the prior art, during the process of automatic driving, the management personnel usually formulate a driving route for the vehicle according to the current traffic conditions before the vehicle sets off, so that the vehicle will drive according to the driving route after the vehicle sets off. However, it is found in the research that since the traffic conditions are uncontrollable, they may change before and after the vehicle sets off. For example, some areas may be impassable or the positions of obstacles in the areas may change, which may cause the vehicle to drive into impassable areas or collide with obstacles when driving on the driving route formulated according to the traffic conditions before the vehicle sets off, thereby causing safety hazards during the vehicle driving process and reducing the safety of the vehicle during driving. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a vehicle control method, device, computer equipment and readable storage medium to avoid potential safety hazards during vehicle driving and improve the safety of vehicle driving.

[0005] In a first aspect, an embodiment of the present application provides a vehicle control method, the method comprising:

[0006] Collect thermal imaging images of the target space in real time through a thermal imaging camera;

[0007] Determine obstacles existing in the target space and current positions of each obstacle at the current moment according to the thermal imaging image collected at the current moment;

[0008] Classifying each obstacle according to its historical position in thermal imaging images collected at several historical moments, wherein the categories of obstacles include stationary obstacles and non-stationary obstacles;

[0009] Based on the categories of each obstacle, determining the vehicle driving path in the target space at a future time according to the current position and historical position of each obstacle;

[0010] At a future time, the vehicle is controlled to travel along the vehicle travel path.

[0011] Optionally, determining obstacles existing in the target space and current positions of the obstacles at the current moment according to the thermal imaging image collected at the current moment includes:

[0012] Determine the object temperature of each object in the target space according to the thermal imaging image collected at the current moment;

[0013] Comparing the object temperature of each object with a preset temperature threshold, and determining obstacles in the target space according to the comparison result;

[0014] The current position of each obstacle at the current moment is determined according to the distribution position of each obstacle in the thermal imaging image collected at the current moment.

[0015] Optionally, the classifying each obstacle according to the historical position of each obstacle in the thermal imaging images collected at a number of historical moments includes:

[0016] For each obstacle, obtain the historical position of the obstacle in the thermal imaging images collected at every two historical moments;

[0017] Determine whether the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments exceeds a preset offset threshold;

[0018] If the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments does not exceed the preset offset threshold, the obstacle is determined as a stationary obstacle; otherwise, the obstacle is determined as a non-stationary obstacle.

[0019] Optionally, the determining, based on the category of each obstacle and according to the current position and historical position of each obstacle, a vehicle driving path in the target space at a future moment includes:

[0020] Determine a drivable area within the target space according to the current position of each stationary obstacle;

[0021] Determine the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle;

[0022] The vehicle driving path is determined within the drivable area according to the future positions of the non-stationary obstacles at future times.

[0023] Optionally, determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes:

[0024] For each non-stationary obstacle, obtain the target historical position of the non-stationary obstacle at the target historical moment;

[0025] Determine the offset speed of the non-stationary obstacle according to the position offset between the current position of the non-stationary obstacle and the target historical position and the historical offset duration between the current moment and the target historical moment;

[0026] The future position of the stationary obstacle at the future time is determined according to the future offset duration between the current time and the future time and the offset speed of the non-stationary obstacle.

[0027] Optionally, determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes:

[0028] The current position and historical position of each non-stationary obstacle are input into the trained position prediction model to obtain the future position of each stationary obstacle at the future moment.

[0029] Optionally, determining the vehicle driving path in the drivable area according to the future positions of each non-stationary obstacle at a future time includes:

[0030] In the drivable area, an initial path of the vehicle is generated along the starting point of the vehicle by random sampling;

[0031] Obtaining the path points on the initial path of the vehicle, starting from the first path point in the initial path of the vehicle, traversing each path point in turn, and detecting the collision relationship between the connection line between the path points and the future position of each non-stationary obstacle;

[0032] If a collision occurs, the other path points are traversed in reverse order until a path point without collision is found, and the path points on the line between the first path point and the path point without collision are deleted, and the path points at both ends of the line are retained; if no collision occurs, the path points on the line are deleted, and the path points at both ends of the line are retained;

[0033] The path obtained by traversing the path points on the initial path of the vehicle is used as the vehicle driving path.

[0034] In a second aspect, an embodiment of the present application provides a vehicle control device, the device comprising:

[0035] An image acquisition module, used to acquire thermal imaging images of the target space in real time through a thermal imaging camera;

[0036] An obstacle determination module is used to determine obstacles existing in the target space and the current position of each obstacle at the current moment according to the thermal imaging image collected at the current moment;

[0037] An obstacle classification module is used to classify each obstacle according to its historical position in the thermal imaging images collected at several historical moments, wherein the obstacle categories include stationary obstacles and non-stationary obstacles;

[0038] A vehicle driving path determination module is used to determine the vehicle driving path in the target space at a future time based on the category of each obstacle and the current position and historical position of each obstacle;

[0039] The vehicle control module is used to control the vehicle to travel along the vehicle travel path at a future time.

[0040] Optionally, determining obstacles existing in the target space and current positions of the obstacles at the current moment according to the thermal imaging image collected at the current moment includes:

[0041] Determine the object temperature of each object in the target space according to the thermal imaging image collected at the current moment;

[0042] Comparing the object temperature of each object with a preset temperature threshold, and determining obstacles in the target space according to the comparison result;

[0043] The current position of each obstacle at the current moment is determined according to the distribution position of each obstacle in the thermal imaging image collected at the current moment.

[0044] Optionally, the classifying each obstacle according to the historical position of each obstacle in the thermal imaging images collected at a number of historical moments includes:

[0045] For each obstacle, obtain the historical position of the obstacle in the thermal imaging images collected at every two historical moments;

[0046] Determine whether the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments exceeds a preset offset threshold;

[0047] If the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments does not exceed the preset offset threshold, the obstacle is determined as a stationary obstacle; otherwise, the obstacle is determined as a non-stationary obstacle.

[0048] Optionally, the determining, based on the category of each obstacle and according to the current position and historical position of each obstacle, a vehicle driving path in the target space at a future moment includes:

[0049] Determine a drivable area within the target space according to the current position of each stationary obstacle;

[0050] Determine the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle;

[0051] The vehicle driving path is determined within the drivable area according to the future positions of the non-stationary obstacles at future times.

[0052] Optionally, determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes:

[0053] For each non-stationary obstacle, obtain the target historical position of the non-stationary obstacle at the target historical moment;

[0054] Determine the offset speed of the non-stationary obstacle according to the position offset between the current position of the non-stationary obstacle and the target historical position and the historical offset duration between the current moment and the target historical moment;

[0055] The future position of the stationary obstacle at the future time is determined according to the future offset duration between the current time and the future time and the offset speed of the non-stationary obstacle.

[0056] Optionally, determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes:

[0057] The current position and historical position of each non-stationary obstacle are input into the trained position prediction model to obtain the future position of each stationary obstacle at the future moment.

[0058] Optionally, determining the vehicle driving path in the drivable area according to the future positions of each non-stationary obstacle at a future time includes:

[0059] In the drivable area, an initial path of the vehicle is generated along the starting point of the vehicle by random sampling;

[0060] Obtaining the path points on the initial path of the vehicle, starting from the first path point in the initial path of the vehicle, traversing each path point in turn, and detecting the collision relationship between the connection line between the path points and the future position of each non-stationary obstacle;

[0061] If a collision occurs, the other path points are traversed in reverse order until a path point without collision is found, and the path points on the line between the first path point and the path point without collision are deleted, and the path points at both ends of the line are retained; if no collision occurs, the path points on the line are deleted, and the path points at both ends of the line are retained;

[0062] The path obtained by traversing the path points on the initial path of the vehicle is used as the vehicle driving path.

[0063] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the vehicle control method described in any optional implementation manner of the first aspect are performed.

[0064] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the vehicle control method described in any optional implementation manner in the above-mentioned first aspect are executed.

[0065] The technical solution provided by this application includes but is not limited to the following beneficial effects:

[0066] The present application can monitor the traffic conditions in the vehicle driving space in real time by collecting thermal imaging images of the target space in real time through a thermal imaging camera. Then, according to the thermal imaging images collected at the current moment, the obstacles existing in the target space and the current positions of each obstacle at the current moment are determined, and the obstacles in the vehicle driving space that may cause harm and influence on the driving safety of the vehicle can be determined. Then, each obstacle is classified according to the historical position of each obstacle in the thermal imaging images collected at several historical moments, wherein the categories of obstacles include stationary obstacles and non-stationary obstacles; based on the categories of each obstacle, the vehicle driving path in the target space at the future moment is determined according to the current position and historical position of each obstacle; the position of the obstacle at the future moment can be predicted according to the state attributes of the obstacle and its position at the past moment, and the driving path adapted to the future traffic conditions can be planned for the vehicle according to the position of the obstacle at the future moment. Finally, the vehicle is controlled to drive along the vehicle driving path at the future moment, and the vehicle can be controlled to drive along the driving path adapted to the traffic conditions after its departure, thereby avoiding traffic accidents and safety hazards during its driving process, and further improving the safety of the vehicle when driving.

[0067] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0069] Figure 1 A flow chart of a vehicle control method provided by Embodiment 1 of the present invention is shown;

[0070] Figure 2 A flow chart of a method for determining the current position of a vehicle provided in Embodiment 1 of the present invention is shown;

[0071] Figure 3 A flowchart of an obstacle classification method provided by Embodiment 1 of the present invention is shown;

[0072] Figure 4 A flow chart of a method for determining a vehicle driving path provided by a first embodiment of the present invention is shown;

[0073] Figure 5 A flow chart of a method for determining a future position of a vehicle provided by a first embodiment of the present invention is shown;

[0074] Figure 6 A flowchart of a specific method for determining a vehicle driving path provided by the first embodiment of the present invention is shown;

[0075] Figure 7 A schematic diagram showing the structure of a vehicle control device provided by a second embodiment of the present invention is shown;

[0076] Figure 8 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention is shown. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0078] Embodiment 1

[0079] To facilitate understanding of this application, Figure 1 The flowchart of a vehicle control method provided in the first embodiment of the present invention is shown to describe the contents of the first embodiment of the present application in detail.

[0080] See also Figure 1 As shown, Figure 1 A flow chart of a vehicle control method provided in the first embodiment of the present invention is shown, wherein the method comprises steps S101 to S105:

[0081] S101: Collect a thermal imaging image of the target space in real time through a thermal imaging camera.

[0082] Specifically, a thermal imaging camera or an infrared thermal imager is used to collect images of the target space in real time, and a thermal imaging image with different colors representing different temperatures of the measured object is obtained.

[0083] S102: Determine obstacles existing in the target space and the current position of each obstacle at the current moment according to the thermal imaging image collected at the current moment.

[0084] Specifically, since different objects have different temperatures, the colors they display in the thermal imaging image are different. Based on the appearance of different colors in the thermal imaging image, the existence of obstacles in the target space can be determined. Based on the distribution of different colors in the thermal imaging image, the distribution of obstacles in the target space can be determined. Based on the distribution of obstacles, the current position of each obstacle can be determined.

[0085] S103: Classifying each obstacle according to the historical position of each obstacle in the thermal imaging images collected at a number of historical moments, wherein the categories of obstacles include stationary obstacles and non-stationary obstacles.

[0086] Specifically, since the thermal imaging camera collects thermal imaging images of the target space in real time, there are thermal imaging images at each current moment, and the current position of the obstacle at each current moment can be obtained. For each current moment, the moments before the current moment are all historical moments. For each historical moment, the thermal imaging image collected at the historical moment is currently collected for itself, and the indicated obstacle position is the current position for the historical moment, but it is a historical position for the current moment. Therefore, taking the current moment as the perspective, the movement of each obstacle (including whether it has moved and the range of movement) can be determined based on the changes in the position of each obstacle (i.e., historical position) at several historical moments before the current moment. Based on the movement of each obstacle, each obstacle is classified to determine whether it is a stationary obstacle or a non-stationary obstacle.

[0087] A stationary obstacle is an obstacle that has not moved at certain historical moments, or an obstacle whose movement range at certain historical moments is within a certain range. A non-stationary obstacle is an obstacle other than a stationary obstacle.

[0088] S104: Based on the categories of the obstacles, a vehicle driving path in the target space at a future time is determined according to the current position and the historical position of each obstacle.

[0089] Specifically, for stationary obstacles, since they have not moved on a large scale at several historical moments, it can be predicted that they will not move on a large scale at future moments and can basically be regarded as being in a stationary state. Therefore, the position of the stationary obstacle at a historical moment can be determined as its position at a future moment, and the vehicle's drivable area can be preliminarily planned in space based on the position of each stationary obstacle at future moments.

[0090] For non-stationary obstacles, since they have moved over a large range at several historical moments, it can be predicted that they will also move over a large range at future moments and can basically be regarded as being in a moving state. Therefore, when determining the position of non-stationary obstacles at future moments, it is necessary to analyze and predict their possible positions at future moments based on their current positions and historical positions, and further plan the vehicle's driving path based on the positions of each non-stationary obstacle at future moments within the planned vehicle's drivable area.

[0091] S105: Control the vehicle to travel along the vehicle driving path at a future moment.

[0092] Specifically, since the planning of the vehicle driving path is based on the distribution of obstacles at the future moment, the planned vehicle driving path can avoid various obstacles in the space, so as to better adapt to the spatial state at the future moment, and improve the rationality and passability of the planned vehicle driving path. Therefore, controlling the vehicle to drive along the vehicle driving path at the future moment can ensure that the vehicle can smoothly avoid various obstacles during driving and ensure its driving safety.

[0093] In an alternative embodiment, see Figure 2 As shown, Figure 2 A flow chart of a method for determining the current position of a vehicle provided in the first embodiment of the present invention is shown, wherein the method for determining obstacles existing in the target space and the current position of each obstacle at the current moment according to the thermal imaging image collected at the current moment comprises steps S201 to S203:

[0094] S201: Determine the object temperature of each object in the target space according to the thermal imaging image collected at the current moment.

[0095] Specifically, different colors in the thermal imaging image represent different temperatures. According to the display positions of different colors in the thermal imaging image and their corresponding temperature values, the position of the object indicated by each color and the object temperature of each object can be obtained.

[0096] S202: Compare the object temperature of each object with a preset temperature threshold, and determine obstacles in the target space according to the comparison result.

[0097] Specifically, for each object, it is determined whether the object temperature of the object exceeds a preset temperature threshold (or falls within a preset temperature range); if so, the object is determined to be an obstacle; if not, the object is not determined to be an obstacle.

[0098] S203: Determine the current position of each obstacle at the current moment according to the distribution position of each obstacle in the thermal imaging image collected at the current moment.

[0099] Specifically, the distribution position of each obstacle in the thermal imaging image collected at the current moment is mapped into the target space, so that the current position of each obstacle at the current moment can be determined.

[0100] In an alternative embodiment, see Figure 3 As shown, Figure 3 A flowchart of an obstacle classification method provided by the first embodiment of the present invention is shown, wherein the classification of each obstacle according to the historical position of each obstacle in the thermal imaging images collected at several historical moments includes steps S301 to S303:

[0101] S301: For each obstacle, obtain the historical position of the obstacle in the thermal imaging images collected at every two historical moments.

[0102] S302: Determine whether the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments exceeds a preset offset threshold.

[0103] S303: If the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments does not exceed the preset offset threshold, the obstacle is determined as a stationary obstacle; otherwise, the obstacle is determined as a non-stationary obstacle.

[0104] Specifically, every two historical moments are two consecutive moments or two non-consecutive moments. When calculating the offset of the obstacle between every two historical positions, the offset distance between the center point of the obstacle at different historical moments is used as the offset of the obstacle between every two historical positions.

[0105] In an alternative embodiment, see Figure 4 As shown, Figure 4 A flow chart of a vehicle driving path determination method provided by the first embodiment of the present invention is shown, wherein the vehicle driving path in the target space at a future moment is determined based on the category of each obstacle and the current position and historical position of each obstacle, including steps S401 to S403:

[0106] S401: Determine a drivable area in the target space according to the current position of each stationary obstacle.

[0107] S402: Determine the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle.

[0108] S403: Determine the vehicle driving path within the drivable area according to the future positions of the non-stationary obstacles at future times.

[0109] Specifically, the current positions of each stationary obstacle in the target space are excluded as non-drivable areas, and the remaining areas are taken as drivable areas for preliminary planning of the vehicle's driving path. Then, according to the possible positions of each non-stationary obstacle in the future, further planning of the formal path is carried out in the drivable area to determine the vehicle's driving path.

[0110] In an alternative embodiment, see Figure 5 As shown, Figure 5A flow chart of a method for determining a future position of a vehicle provided in the first embodiment of the present invention is shown, wherein the method for determining the future position of each non-stationary obstacle at a future moment according to the current position and the historical position of each non-stationary obstacle comprises steps S501 to S503:

[0111] S501: For each non-stationary obstacle, obtain a target historical position of the non-stationary obstacle at a target historical moment.

[0112] Specifically, the coordinates of the center point or any corner point of the non-stationary obstacle at the target historical moment are obtained. The target historical moment is any historical moment in the historical moments, which can be selected according to actual needs.

[0113] S502: Determine the offset speed of the non-stationary obstacle according to the position offset between the current position of the non-stationary obstacle and the target historical position and the historical offset duration between the current moment and the target historical moment.

[0114] Specifically, the offset between the center point coordinates of the non-stationary obstacle at the target historical moment and the center point coordinates at the current moment, or the offset between the coordinates of a corner point at the target historical moment and the coordinates of the corner point at the current moment is calculated as the position offset.

[0115] Since distance is the product of time and speed, the offset speed of the non-stationary obstacle is determined based on the historical offset duration and position offset between the current moment and the target historical moment.

[0116] S503: Determine the future position of the stationary obstacle at the future time according to the future offset duration between the current time and the future time and the offset speed of the non-stationary obstacle.

[0117] Specifically, according to the distance being the product of time and speed, the travel distance of the non-stationary obstacle between the current moment and the future moment is obtained by multiplying the offset speed of the non-stationary obstacle by the future offset duration between the current moment and the future moment. The position after the calculated travel distance is extended in the offset direction between the target historical position and the current position is taken as the future position of the non-stationary obstacle.

[0118] In an optional implementation, determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes:

[0119] The current position and historical position of each non-stationary obstacle are input into the trained position prediction model to obtain the future position of each stationary obstacle at the future moment.

[0120] Specifically, a position prediction model that can be used for position prediction is pre-trained, and the future position of each stationary obstacle at a future moment is determined using the position prediction model.

[0121] In an alternative embodiment, see Figure 6 As shown, Figure 6 A flowchart of a specific method for determining a vehicle driving path provided by the first embodiment of the present invention is shown, wherein the method for determining the vehicle driving path in the drivable area according to the future position of each non-stationary obstacle at a future time comprises steps S601 to S604:

[0122] S601: In the drivable area, an initial path of the vehicle is generated along the starting point of the vehicle by random sampling.

[0123] Specifically, the starting point of the vehicle is taken as the starting point of the initial path of the vehicle, and random sampling is performed in the drivable area to obtain multiple sampling points in sequence; a path tree is constructed according to the sampling points, and the path points on the path tree are connected in sequence to generate the initial path of the vehicle.

[0124] S602: Obtain the path points on the initial path of the vehicle, start from the first path point in the initial path of the vehicle, traverse each path point in turn, and detect the collision relationship between the connection line between the path points and the future position of each non-stationary obstacle.

[0125] S603: If a collision occurs, traverse the other path points in reverse order until a path point without collision is found, and delete the path points on the line between the first path point and the path point without collision, and retain the path points at both ends of the line; if no collision occurs, delete the path points on the line, and retain the path points at both ends of the line.

[0126] Specifically, obtain n path points on the initial path of the vehicle and execute the following loop process:

[0127] a) Traverse from the first point, connect the nth point, check whether the line segment collides with the boundary of the drivable area, if not, delete all path points on the line, keep only the first and nth points, and output the path points. b) If there is a collision, skip the nth point, connect the first point with the n-1th point, check whether the line segment collides with the boundary of the drivable area, until the ith point without collision is found, then delete all path points on the line between the first point and the ith point, and keep only the first point and the ith point and subsequent points. c) Continue traversing from the second point, connect the nth point, check whether the line segment collides with the boundary of the drivable area, if not, delete the middle points between the lines, keep only the first point, the second point and the nth point, and output the path points. d) If there is a collision, skip the nth point, connect the second point with the n-1th point, check whether the line segment collides with the boundary of the drivable area, until the jth point without collision is found, then delete all the intermediate points between the second point and the jth point, and only keep the first point, the second point, the jth point and the nj points after the jth point. e) Continue to traverse from the third point until the last point is traversed, so that a series of path key points can be obtained as the path points on the initial path of the vehicle.

[0128] S604: Using a path obtained by traversing the path points on the initial path of the vehicle as the vehicle driving path.

[0129] Specifically, the vehicle driving path is obtained by traversing a series of path key points. By simplifying the vehicle's initial path, the tortuous vehicle initial path can be simplified into a vehicle driving path containing a small number of path key points, thereby reducing the complexity of the vehicle driving path and improving the efficiency of path planning.

[0130] Embodiment 2

[0131] See also Figure 7 As shown, Figure 7 A schematic diagram of the structure of a vehicle control device provided in Embodiment 2 of the present invention is shown, wherein the device comprises:

[0132] An image acquisition module 701 is used to acquire a thermal imaging image of a target space in real time through a thermal imaging camera;

[0133] The obstacle determination module 702 is used to determine the obstacles existing in the target space and the current position of each obstacle at the current moment according to the thermal imaging image collected at the current moment;

[0134] The obstacle classification module 703 is used to classify each obstacle according to the historical position of each obstacle in the thermal imaging images collected at a number of historical moments, wherein the categories of obstacles include stationary obstacles and non-stationary obstacles;

[0135] The vehicle driving path determination module 704 is used to determine the vehicle driving path in the target space at a future time based on the category of each obstacle and the current position and historical position of each obstacle;

[0136] The vehicle control module 705 is used to control the vehicle to travel along the vehicle driving path at a future time.

[0137] In an optional implementation, the determining of obstacles existing in the target space and the current position of each obstacle at the current moment according to the thermal imaging image collected at the current moment includes:

[0138] Determine the object temperature of each object in the target space according to the thermal imaging image collected at the current moment;

[0139] Comparing the object temperature of each object with a preset temperature threshold, and determining obstacles in the target space according to the comparison result;

[0140] The current position of each obstacle at the current moment is determined according to the distribution position of each obstacle in the thermal imaging image collected at the current moment.

[0141] In an optional embodiment, the classifying of each obstacle according to the historical position of each obstacle in the thermal imaging images collected at a number of historical moments includes:

[0142] For each obstacle, obtain the historical position of the obstacle in the thermal imaging images collected at every two historical moments;

[0143] Determine whether the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments exceeds a preset offset threshold;

[0144] If the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments does not exceed the preset offset threshold, the obstacle is determined as a stationary obstacle; otherwise, the obstacle is determined as a non-stationary obstacle.

[0145] In an optional implementation scheme, the determining of the vehicle driving path in the target space at a future time based on the category of each obstacle and the current position and historical position of each obstacle includes:

[0146] Determine a drivable area within the target space according to the current position of each stationary obstacle;

[0147] Determine the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle;

[0148] The vehicle driving path is determined within the drivable area according to the future positions of the non-stationary obstacles at future times.

[0149] In an optional implementation, determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes:

[0150] For each non-stationary obstacle, obtain the target historical position of the non-stationary obstacle at the target historical moment;

[0151] Determine the offset speed of the non-stationary obstacle according to the position offset between the current position of the non-stationary obstacle and the target historical position and the historical offset duration between the current moment and the target historical moment;

[0152] The future position of the stationary obstacle at the future time is determined according to the future offset duration between the current time and the future time and the offset speed of the non-stationary obstacle.

[0153] In an optional implementation, determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes:

[0154] The current position and historical position of each non-stationary obstacle are input into the trained position prediction model to obtain the future position of each stationary obstacle at the future moment.

[0155] In an optional implementation, determining the vehicle driving path in the drivable area according to the future positions of each non-stationary obstacle at a future time includes:

[0156] In the drivable area, an initial path of the vehicle is generated along the starting point of the vehicle by random sampling;

[0157] Obtaining the path points on the initial path of the vehicle, starting from the first path point in the initial path of the vehicle, traversing each path point in turn, and detecting the collision relationship between the connection line between the path points and the future position of each non-stationary obstacle;

[0158] If a collision occurs, the other path points are traversed in reverse order until a path point without collision is found, and the path points on the line between the first path point and the path point without collision are deleted, and the path points at both ends of the line are retained; if no collision occurs, the path points on the line are deleted, and the path points at both ends of the line are retained;

[0159] The path obtained by traversing the path points on the initial path of the vehicle is used as the vehicle driving path.

[0160] Embodiment 3

[0161] Based on the same application concept, see Figure 8 As shown, Figure 8 FIG. 4 shows a schematic diagram of the structure of a computer device provided by Embodiment 3 of the present invention, wherein: Figure 8 As shown, a computer device 800 provided in Embodiment 3 of the present application includes:

[0162] A processor 801, a memory 802 and a bus 803, wherein the memory 802 stores machine-readable instructions executable by the processor 801. When the computer device 800 is running, the processor 801 communicates with the memory 802 via the bus 803, and the machine-readable instructions are executed by the processor 801 to execute the steps of the vehicle control method shown in the above-mentioned embodiment 1.

[0163] Embodiment 4

[0164] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle control method described in any one of the above embodiments are executed.

[0165] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0166] The computer program product for vehicle control provided in the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments and will not be repeated here.

[0167] The vehicle control device provided in the embodiment of the present invention can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. It can be clearly understood by technicians in the relevant field that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0168] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0169] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0171] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0172] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0173] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or perform equivalent replacements on some of the technical features thereof; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. They should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A vehicle control method, characterized in that: The method comprises: Collect thermal imaging images of the target space in real time through a thermal imaging camera; Determine obstacles existing in the target space and current positions of each obstacle at the current moment according to the thermal imaging image collected at the current moment; Classifying each obstacle according to its historical position in thermal imaging images collected at several historical moments, wherein the categories of obstacles include stationary obstacles and non-stationary obstacles; Based on the categories of each obstacle, determining the vehicle driving path in the target space at a future time according to the current position and historical position of each obstacle; At a future time, the vehicle is controlled to travel along the vehicle travel path.

2. The method according to claim 1, characterized in that The step of determining obstacles existing in the target space and the current position of each obstacle at the current moment according to the thermal imaging image collected at the current moment includes: Determine the object temperature of each object in the target space according to the thermal imaging image collected at the current moment; Comparing the object temperature of each object with a preset temperature threshold, and determining obstacles in the target space according to the comparison result; The current position of each obstacle at the current moment is determined according to the distribution position of each obstacle in the thermal imaging image collected at the current moment.

3. The method according to claim 1, characterized in that The classifying of obstacles according to their historical positions in thermal imaging images collected at a number of historical moments includes: For each obstacle, obtain the historical position of the obstacle in the thermal imaging images collected at every two historical moments; Determine whether the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments exceeds a preset offset threshold; If the offset between the historical positions of the obstacle in the thermal imaging images collected at every two historical moments does not exceed the preset offset threshold, the obstacle is determined as a stationary obstacle; otherwise, the obstacle is determined as a non-stationary obstacle.

4. The method according to claim 1, characterized in that The method of determining the vehicle driving path in the target space at a future time based on the category of each obstacle and the current position and historical position of each obstacle includes: Determine a drivable area within the target space according to the current position of each stationary obstacle; Determine the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle; The vehicle driving path is determined within the drivable area according to the future positions of the non-stationary obstacles at future times.

5. The method according to claim 4, characterized in that Determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes: For each non-stationary obstacle, obtain the target historical position of the non-stationary obstacle at the target historical moment; Determine the offset speed of the non-stationary obstacle according to the position offset between the current position of the non-stationary obstacle and the target historical position and the historical offset duration between the current moment and the target historical moment; The future position of the stationary obstacle at the future time is determined according to the future offset duration between the current time and the future time and the offset speed of the non-stationary obstacle.

6. The method according to claim 4, characterized in that Determining the future position of each non-stationary obstacle at a future time according to the current position and the historical position of each non-stationary obstacle includes: The current position and historical position of each non-stationary obstacle are input into the trained position prediction model to obtain the future position of each stationary obstacle at the future moment.

7. The method according to claim 4, characterized in that Determining the vehicle driving path in the drivable area according to the future positions of each non-stationary obstacle at a future time includes: In the drivable area, generating an initial path of the vehicle along the starting point of the vehicle by random sampling; Obtaining the path points on the initial path of the vehicle, starting from the first path point in the initial path of the vehicle, traversing each path point in turn, and detecting the collision relationship between the connection line between the path points and the future position of each non-stationary obstacle; If a collision occurs, the other path points are traversed in reverse order until a path point without collision is found, and the path points on the line between the first path point and the path point without collision are deleted, and the path points at both ends of the line are retained; if no collision occurs, the path points on the line are deleted, and the path points at both ends of the line are retained; The path obtained by traversing the path points on the initial path of the vehicle is used as the vehicle driving path.

8. A vehicle control device, characterized in that: The device comprises: An image acquisition module, used to acquire thermal imaging images of the target space in real time through a thermal imaging camera; An obstacle determination module is used to determine obstacles existing in the target space and the current position of each obstacle at the current moment according to the thermal imaging image collected at the current moment; An obstacle classification module is used to classify each obstacle according to its historical position in the thermal imaging images collected at several historical moments, wherein the obstacle categories include stationary obstacles and non-stationary obstacles; A vehicle driving path determination module is used to determine the vehicle driving path in the target space at a future time based on the category of each obstacle and the current position and historical position of each obstacle; The vehicle control module is used to control the vehicle to travel along the vehicle travel path at a future time.

9. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the vehicle control method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the vehicle control method as claimed in any one of claims 1 to 7.