Vehicle avoidance method, device, equipment, storage medium and program product

Abstract

The present application relates to a kind of vehicle avoidance method, device, equipment, storage medium and program product, involve vehicle control technical field.The method includes: in response to trigger avoidance determination request, by obtaining the bird's-eye view of ego vehicle in target area and determining the vehicle to be avoided in the bird's-eye view, it can be determined whether to avoid according to the position of ego vehicle and the vehicle to be avoided in the bird's-eye view, if it needs to avoid, then it can confirm the avoidance position in the bird's-eye view and avoid.Utilize bird's-eye view can obtain the top-down perspective around ego vehicle, so that the position and contour information of vehicle and other objects such as ego vehicle and the vehicle to be avoided in target area can be intuitively and clearly confirmed, on this basis, it can be more easily judged whether ego vehicle will hinder the passage of the vehicle to be avoided, and then the decision difficulty of vehicle avoidance can be reduced, and the safety of road driving is improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, specifically to a vehicle avoidance method, device, equipment, storage medium, and program product. Background Technology

[0002] With the development of the automotive industry, the number of private cars is increasing. In daily travel and other traffic scenarios, due to factors such as speed limits or congestion, private cars are sometimes forced to drive at low speeds or even parked. If an emergency vehicle such as an ambulance is on duty at this time, the private car may need to give way.

[0003] Currently, in scenarios involving emergency vehicles or other vehicles requiring the driver to give way, the driver still needs to actively assess and control the vehicle to avoid them. This method relies excessively on the driver's experience and skill level; if the driver lacks sufficient experience and skill, they may make incorrect decisions, which is detrimental to driving safety. Summary of the Invention

[0004] One of the objectives of this invention is to provide a vehicle avoidance method, apparatus, device, storage medium, and program product to solve the problem of high difficulty in vehicle avoidance.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A vehicle avoidance method, the method comprising:

[0007] In response to a trigger avoidance determination request, a bird's-eye view of the vehicle in the target area is obtained, and the vehicle to be avoided is determined in the bird's-eye view;

[0008] Determine whether it is necessary to avoid the vehicle based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view;

[0009] If avoidance is required, the target avoidance position is determined based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view, and the vehicle is controlled to move to the target avoidance position.

[0010] Furthermore, based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view, it is determined whether avoidance is necessary, including:

[0011] Based on the position of the vehicle to be avoided in the bird's-eye view, predict the driving trajectory of the vehicle to be avoided in the bird's-eye view within the next m seconds;

[0012] Based on the vehicle's position and its trajectory within the next m seconds, determine whether the vehicle's outline in the bird's-eye view will overlap with the outline of the vehicle to be avoided in the bird's-eye view. If it will, avoidance is required; otherwise, avoidance is not required.

[0013] Furthermore, based on the position of the vehicle to be avoided in the bird's-eye view, the trajectory of the vehicle to be avoided within the next m seconds in the bird's-eye view is predicted, including:

[0014] Obtain lane line information from the bird's-eye view and / or the driving trajectory of the vehicle to be avoided in the next n seconds, where n < m;

[0015] Based on the lane line information and / or the driving trajectory within the n seconds, predict the driving trajectory of the vehicle to be avoided within the next m seconds.

[0016] Furthermore, determining the target avoidance position based on the positions of the self-vehicle and the vehicle to be avoided in the bird's-eye view includes:

[0017] The vehicle's outline in the bird's-eye view is moved away from the driving trajectory until the vehicle's outline in the bird's-eye view no longer overlaps with the outline of the vehicle to be avoided in the bird's-eye view. Then the movement stops, and a target avoidance position is generated based on the vehicle's outline in the bird's-eye view at this time.

[0018] Furthermore, the triggering conditions for an avoidance decision request include:

[0019] Identify whether there are vehicles around the vehicle that need to be avoided;

[0020] If so, determine whether the vehicle to be avoided is in the same lane or an adjacent lane as the vehicle itself. If so, trigger an avoidance decision request.

[0021] Furthermore, if the vehicle to be avoided is a special vehicle, the step of identifying whether there is a vehicle to be avoided around the vehicle includes:

[0022] Collect sound information from the area around the vehicle and determine whether there are horns from special vehicles in the sound information;

[0023] If a special vehicle is honking its horn, then image information of the direction of the sound source of the horn is acquired;

[0024] The presence of special vehicles can be identified based on the image information.

[0025] A vehicle avoidance device, comprising:

[0026] The acquisition module is used to acquire a bird's-eye view of the vehicle in the target area in response to a trigger avoidance determination request, and to determine the vehicle to be avoided in the bird's-eye view;

[0027] The judgment module is used to determine whether it is necessary to avoid the vehicle based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view;

[0028] The obstacle avoidance module is used to determine the target obstacle avoidance position based on the positions of the self-vehicle and the vehicle to be avoided in the bird's-eye view when obstacle avoidance is required, and to control the self-vehicle to move to the target obstacle avoidance position.

[0029] An electronic device includes: a processor, and a memory communicatively connected to the processor;

[0030] The memory stores computer-executed instructions;

[0031] The processor executes computer execution instructions stored in the memory to implement the vehicle avoidance method as described in any of the above.

[0032] A computer-readable storage medium includes: computer-executable instructions stored therein, which, when executed by a processor, are used to implement the vehicle avoidance method as described in any of the preceding claims.

[0033] A computer program product includes a computer program that, when executed by a processor, implements the vehicle avoidance method as described in any of the above.

[0034] The beneficial effects of this invention are as follows: By using a bird's-eye view, a top-down perspective can be obtained around the vehicle, thereby allowing for a direct and clear confirmation of the position and outline information of the vehicle and other vehicles and objects within the target area, such as the vehicle itself and the vehicle to be avoided. Based on this, it is easier to determine whether the vehicle will obstruct the passage of the vehicle to be avoided, thus reducing the difficulty of vehicle avoidance decisions and improving road driving safety. Attached Figure Description

[0035] Figure 1 A flowchart illustrating a vehicle avoidance method provided as an exemplary embodiment of the present invention. Figure 1 ;

[0036] Figure 2 A schematic diagram of a bird's-eye view of a target area provided for an exemplary embodiment of the present invention;

[0037] Figure 3 A schematic diagram of a vehicle movement process provided as an exemplary embodiment of the present invention;

[0038] Figure 4 A flowchart illustrating a vehicle avoidance method provided as an exemplary embodiment of the present invention. Figure 2 ;

[0039] Figure 5 A schematic diagram illustrating an exemplary embodiment of the present invention for avoiding a vehicle ahead;

[0040] Figure 6 A schematic diagram illustrating an exemplary embodiment of the present invention for avoiding a vehicle behind.

[0041] Figure 7 A schematic diagram illustrating an exemplary embodiment of the present invention for avoiding a vehicle in an adjacent lane;

[0042] Figure 8 A schematic diagram illustrating how to avoid vehicles behind in a congested road section, as provided in an exemplary embodiment of the present invention;

[0043] Figure 9 A schematic diagram of a vehicle avoidance device provided for an exemplary embodiment of the present invention;

[0044] Figure 10 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present invention.

[0045] The accompanying drawings have illustrated specific embodiments of the invention, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0046] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0047] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0049] The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, product, or apparatus. Without further limitation, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., is to denote names and does not indicate any particular order.

[0050] With the development of the automotive industry and the continuous improvement of people's living standards, the number of private cars is constantly increasing, and driving is becoming more and more common. The increase in vehicles will increase the complexity of road conditions, making safe driving increasingly difficult, whether by human or intelligent driving systems. Especially in situations involving emergency vehicles or large, dangerous vehicles, drivers may need to take evasive action to ensure safety.

[0051] When a vehicle encounters a breakdown, speed limits, or traffic congestion, other vehicles may need to pass first. For example, emergency vehicles like ambulances or fire trucks on duty, or large, dangerous vehicles like dump trucks that are too wide, may encroach on the driver's lane. To ensure driving safety, the driver may need to give way to these emergency or dangerous vehicles. Whether to take evasive action and how to do so requires correct decision-making from the driver or the intelligent driving system. This places extremely high demands on the decision-making abilities of both the driver and the intelligent driving system; an incorrect decision can not only affect the safety of the driver but also the safety of other vehicles.

[0052] Based on this, a technical concept is proposed. When a vehicle faces a decision on whether and how to avoid a collision, it acquires a Bird's-Eye View (BEV) of the target area using multi-view fusion technology. The position of vehicles waiting to be avoided, such as emergency vehicles, is confirmed within the BEV view. Based on the positions of the vehicle and the vehicle to be avoided, it is determined whether the vehicle will obstruct the passage of the vehicle to be avoided, thus deciding whether to take evasive action. Furthermore, a safe avoidance position can be determined within the BEV view based on the positions of the vehicle and the vehicle to be avoided. The vehicle is then controlled to move towards this target position to achieve the avoidance. Utilizing the positions of the vehicle and the vehicle to be avoided within the BEV view can assist the driver or intelligent driving system in more intuitively judging the avoidance need and more easily achieving the avoidance target, reducing the decision-making difficulty of vehicle avoidance and improving driving safety.

[0053] The application scenarios mentioned above are only some examples. Those skilled in the art can expand the applications according to specific needs and scenarios. The embodiments of the present invention do not impose specific limitations in this regard. The following references Figures 1 to 5 This describes a test method according to an exemplary embodiment of the present invention.

[0054] Figure 1 This is a flowchart illustrating a vehicle avoidance method provided as an exemplary embodiment of the present invention. Figure 1 As shown, the method may include:

[0055] Step S101: In response to triggering the avoidance determination request, obtain a bird's-eye view of the vehicle in the target area, and determine the vehicle to be avoided in the bird's-eye view.

[0056] The bird's-eye view, also known as the BEV view, refers to the view observed from a BEV perspective. The target area can be customized, for example, a rectangular area extending 5 meters to the left and right of the vehicle, or 10 meters in front and 10 meters behind. It can also be set to other irregularly shaped areas depending on actual needs. Actual needs refer to including the vehicle to be avoided within the display range of the bird's-eye view. If the target area does not contain the vehicle to be avoided, or if no vehicle is found in the bird's-eye view, the coverage area of ​​the target area can be expanded, and the bird's-eye view can be re-acquired until the vehicle to be avoided appears in the bird's-eye view.

[0057] In this embodiment of the invention, the avoidance decision request can be triggered based on a user command. For example, if the driver observes that there are special vehicles such as ambulances or large dangerous vehicles that may need to be avoided, the driver can trigger the avoidance decision request through voice command. In addition, the intelligent driving or vehicle system can also automatically trigger the avoidance decision request based on the perception of the vehicle's surrounding environment. For example, if the vehicle system detects the presence of a vehicle to be avoided in the surrounding area through sensors such as cameras or radar, it can also trigger the avoidance decision request.

[0058] In this embodiment of the invention, the vehicle is a vehicle in which the user rides. The vehicle can be equipped with cameras with multiple perspectives, such as a front camera, a right camera, and a rear camera. Through image projection and stitching technology, a BEV perspective image can be generated based on the images captured by multiple cameras. For example, objects captured by the vehicle-mounted cameras such as the rear camera will be presented as a top-down observation result in the BEV perspective. This observation result includes the position of the object in the BEV view and its outline in the top-down view.

[0059] For example, after obtaining a bird's-eye view, the vehicle can display the view on the central control screen. The user can specify the vehicle to be avoided in the bird's-eye view by clicking on the central control screen or by using voice commands. For instance, if the third vehicle behind the vehicle is an ambulance in the vehicle's lane, the user can specify the vehicle to be avoided by using the voice command "The third vehicle directly behind is the vehicle to be avoided".

[0060] For example, after obtaining the bird's-eye view, the intelligent driving or vehicle system can also automatically identify the vehicle to be avoided in the bird's-eye view. For instance, if the intelligent driving system has already captured an ambulance behind it through the vehicle camera before triggering the avoidance determination request, it can determine the ambulance in the bird's-eye view based on the mapping relationship between the parameters of the vehicle camera and the bird's-eye view.

[0061] Step S102: Determine whether it is necessary to avoid the vehicle based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view.

[0062] In this embodiment of the invention, based on information such as the position and outline of the vehicle and the vehicle to be avoided in the bird's-eye view, a variety of avoidance judgment rules can be set. These avoidance judgment rules can be applied one by one or combined with multiple rules for comprehensive judgment.

[0063] For example, in a bird's-eye view, the width of the vehicle to be avoided can be determined, and then the width of the passable space to the left or right of the vehicle can be determined. If the width of the passable space is greater than the width of the vehicle to be avoided, it can be determined that no avoidance is required; otherwise, avoidance is required. For example, if there is an obstacle such as a wall to the right of the vehicle, the lateral distance between the wall and the vehicle can be used as the width of the passable space.

[0064] For example, if the vehicle is traveling at a low speed, a passing point can be determined based on the speeds of the vehicle and the vehicle to be avoided. If the passing point is wide enough to allow the vehicle and the vehicle to be avoided to pass side by side, it can be determined that no passing is required.

[0065] Step S103: If avoidance is required, the target avoidance position is determined based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view, and the vehicle is controlled to move to the target avoidance position.

[0066] In this embodiment of the invention, based on the position and outline of the vehicle and the vehicle to be avoided in the bird's-eye view, a target avoidance position can be selected in the bird's-eye view that is sufficient for the vehicle to be avoided to pass. After the vehicle moves to the target avoidance position, the width of the passable space on at least one side of the vehicle is greater than the width of the vehicle to be avoided.

[0067] In some possible implementations, multi-source environmental perception data can be acquired through sensors such as radar, and this data can be used for bird's-eye view correction or identification of vehicles to be avoided.

[0068] It should be noted that the target avoidance position can represent the vehicle's posture after moving to that position. For example, if the vehicle's front end is parallel to the lane line before avoiding a collision, and the vehicle's maneuverability is limited, such as in a congested area, the vehicle's front end can be tilted towards one lane line after moving to the target avoidance position. In this case, the vehicle's outline can be drawn at the target avoidance position in the bird's-eye view, and the vehicle can be moved until its projected outline in the bird's-eye view coincides with the drawn outline.

[0069] In the above embodiments, when it is necessary to determine whether to avoid a vehicle, a bird's-eye view of the vehicle in the target area is obtained, and the vehicle to be avoided is identified in the bird's-eye view. The position of the vehicle and the vehicle to be avoided in the bird's-eye view determines whether to avoid the vehicle. If avoidance is necessary, the avoidance position can be confirmed in the bird's-eye view and the avoidance can be performed. The bird's-eye view provides a top-down perspective of the vehicle's surroundings, allowing for a direct and clear confirmation of the position and outline information of the vehicle and other vehicles and objects in the target area. Based on this, it becomes easier to determine whether the vehicle will obstruct the passage of the vehicle to be avoided, thereby reducing the difficulty of decision-making regarding vehicle avoidance and improving road safety.

[0070] In one embodiment, the triggering conditions for an avoidance decision request include:

[0071] Identify whether there are vehicles to be avoided around the vehicle; if so, determine whether the special vehicle is in the same lane or adjacent lane as the vehicle. If so, trigger an avoidance decision request.

[0072] For example, the vehicle can periodically perceive surrounding environmental information through onboard cameras and other devices. This includes capturing images of the surrounding environment and identifying any vehicles in the images whose appearance resembles special or dangerous vehicles in a database. If so, these are identified as vehicles to be avoided, and the vehicle is further judged whether it is in the same lane or an adjacent lane as the vehicle. The database can be deployed on the vehicle's local storage device or on a cloud server.

[0073] In some possible implementations, identifying whether there are vehicles to be avoided around the vehicle includes: collecting sound information around the vehicle and determining whether there is a horn sound from a special vehicle in the sound information; if there is a horn sound from a special vehicle, then acquiring image information of the direction of the sound source; and identifying whether there is a special vehicle based on the image information.

[0074] The process of periodically acquiring images via camera and identifying vehicles to be avoided consumes significant vehicle resources. In the aforementioned implementation, surrounding sounds can be periodically captured, sound segments extracted, and their similarity to the sirens of emergency vehicles such as ambulances and fire trucks calculated. Once the similarity reaches a certain level, an image from the direction of the sound's origin is captured by the vehicle's camera, and the emergency vehicle is identified. By using periodic sound acquisition instead of periodic image acquisition, the resource consumption of frequent image acquisition and recognition is reduced, thus saving software costs.

[0075] In one embodiment, determining whether to avoid a vehicle based on the positions of the vehicle and the vehicle to be avoided in a bird's-eye view includes:

[0076] Based on the position of the vehicle to be avoided in the bird's-eye view, predict the trajectory of the vehicle to be avoided in the bird's-eye view within the next m seconds; based on the position of the own vehicle and the trajectory within the next m seconds, determine whether the outline of the own vehicle in the bird's-eye view will overlap with the outline of the vehicle to be avoided in the bird's-eye view. If it will, then avoidance is required; otherwise, avoidance is not required.

[0077] Figure 2 This is a schematic diagram of a bird's-eye view of a target area provided for an exemplary embodiment of the present invention. Exemplarily, as shown... Figure 2 As shown, the car is parked, and a special vehicle is approaching from its right rear. If the trajectory of this special vehicle in the next 10 seconds is predicted as follows... Figure 2 As shown by the dashed line, it can be determined that the special vehicle may collide with the vehicle when it reaches the location indicated by the arrow. In this case, the outline of the special vehicle can be drawn at this location according to the width of the special vehicle. The outline should at least include the left boundary of the special vehicle. If the drawn outline overlaps with the outline of the vehicle, then it is necessary to avoid collision.

[0078] In some possible implementations, predicting the trajectory of the vehicle to be avoided within the next m seconds in the bird's-eye view, based on the vehicle's position in the bird's-eye view, can be achieved in the following ways.

[0079] For example, lane line information in a bird's-eye view can be obtained, and the trajectory of the vehicle to be avoided within the next m seconds can be predicted based on the lane line information. For instance, the lane selected by the vehicle to be avoided can be determined based on the lane line information, thereby predicting its subsequent trajectory.

[0080] For example, the trajectory of the vehicle to be avoided in a bird's-eye view over the next n seconds can be obtained, and the trajectory of the vehicle to be avoided over the next m seconds can be predicted based on the trajectory over the next n seconds. Where n < m.

[0081] For example, if n is 5 and m is 10, we can first draw the trajectory of the vehicle to be avoided within 5 seconds based on the positional changes of the vehicle in the bird's-eye view, and then further predict its trajectory within 10 seconds based on this trajectory.

[0082] In this embodiment of the invention, the driving trajectory of the vehicle to be avoided can be predicted in a bird's-eye view over a period of time. Based on this driving trajectory, the outline of the vehicle to be avoided approaching the vehicle can be drawn at the point on the trajectory where the vehicle to be avoided is closest to the vehicle. By comparing the outline of the vehicle in the bird's-eye view with the outline of the vehicle to be avoided at the future trajectory point, it can be intuitively determined whether there is an overlap between the two outlines. If so, it is considered that the vehicle will obstruct the driving of the vehicle to be avoided and needs to avoid it. If there is no overlap between the two outlines, then it is not necessary to avoid it.

[0083] In one embodiment, determining the target avoidance location based on the positions of the vehicle and the vehicle to be avoided in a bird's-eye view includes:

[0084] Move the vehicle's outline in the bird's-eye view away from the driving trajectory until the vehicle's outline in the bird's-eye view no longer overlaps with the outline of the vehicle to be avoided. Then stop moving and generate the target avoidance position based on the vehicle's outline in the bird's-eye view at this time.

[0085] Figure 3 This is a schematic diagram of a vehicle movement process provided as an exemplary embodiment of the present invention.

[0086] In this embodiment of the invention, for situations where the vehicle has limited maneuvering space, such as narrow roads, a virtual outline can be drawn in the bird's-eye view according to the vehicle's outline boundary (e.g., ...). Figure 3 (As shown by the dashed box on the left side that matches the vehicle's outline). By moving this virtual outline in the bird's-eye view, it's easier to find a target avoidance position that meets the avoidance requirements, and the target avoidance position can represent the vehicle's frontal orientation after movement. Using the target avoidance position as the movement target, the vehicle can be moved from this point by intelligent driving algorithms or manual control until the vehicle's actual projected outline in the bird's-eye view coincides with the drawn outline. Figure 3 As shown, before the vehicle moves, its front is facing directly forward. The target avoidance position is determined based on the movable space in the bird's-eye view, as follows: Figure 3 As shown in the virtual outline on the left, after the car moves... Figure 3 As shown on the right, the front of the moved vehicle is tilted to the left.

[0087] In the above embodiments, the target avoidance position of the vehicle is determined based on the bird's-eye view. The avoidance effect of the vehicle at the target avoidance position can be seen intuitively in the bird's-eye view, thereby reducing the difficulty of selecting the target avoidance position and improving the selection accuracy, thus reducing the difficulty of avoidance and ensuring vehicle safety.

[0088] Figure 4 A flowchart illustrating a vehicle avoidance method provided as an exemplary embodiment of the present invention. Figure 2 .like Figure 4 As shown, the vehicle can determine the types of surrounding vehicles. If all are ordinary vehicles, no yielding is required, and normal driving is permitted. However, if there are special or dangerous vehicles, different yielding strategies can be adopted when dealing with them.

[0089] Figure 5 This is a schematic diagram illustrating how to avoid a vehicle ahead, as provided in an exemplary embodiment of the present invention. Figure 6 This is a schematic diagram illustrating how to avoid a vehicle behind you, as provided in an exemplary embodiment of the present invention. Figure 7 This is a schematic diagram illustrating an exemplary embodiment of the present invention for avoiding a vehicle in an adjacent lane. Figure 8 This is a schematic diagram illustrating how to avoid vehicles behind you in a congested road section, as provided as an exemplary embodiment of the present invention.

[0090] like Figure 5 , Figure 6 and Figure 7 As shown, when a dangerous vehicle is detected in an adjacent lane, the vehicle adopts a strategy of shifting in the opposite direction of the dangerous vehicle within its own lane and accelerating to avoid it; when a dangerous vehicle is detected in front of the vehicle or approaching quickly from behind in its own lane, the vehicle changes lanes in advance to a passable lane to avoid it.

[0091] like Figure 8 As shown, in some congested road conditions, the preferred strategy for a vehicle is to drift away from its own lane and drive close to the lane line on one side. If a special vehicle behind fails to overtake the vehicle within 5 seconds, the system will issue an alarm to remind the driver to take over and avoid the vehicle behind.

[0092] Figure 9 This is a schematic diagram of a vehicle avoidance device provided as an exemplary embodiment of the present invention. (See diagram below.) Figure 9 As shown, the vehicle avoidance device 900 may include:

[0093] The acquisition module 901 is used to acquire a bird's-eye view of the vehicle in the target area in response to a trigger avoidance determination request, and to determine the vehicle to be avoided in the bird's-eye view;

[0094] The judgment module 902 is used to determine whether it is necessary to avoid the vehicle based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view;

[0095] The obstacle avoidance module 903 is used to determine the target obstacle avoidance position based on the positions of the self-vehicle and the vehicle to be avoided in the bird's-eye view when obstacle avoidance is required, and to control the self-vehicle to move to the target obstacle avoidance position.

[0096] In one embodiment, the determination module 902 is further configured to: predict the driving trajectory of the vehicle to be avoided in the bird's-eye view within the next m seconds based on the position of the vehicle to be avoided in the bird's-eye view; and determine whether the outline of the vehicle in the bird's-eye view will overlap with the outline of the vehicle to be avoided in the bird's-eye view based on the vehicle's position and the driving trajectory within the next m seconds. If so, avoidance is required; otherwise, avoidance is not required.

[0097] In one embodiment, the determination module 902 is further configured to: obtain lane line information in the bird's-eye view and / or the driving trajectory of the vehicle to be avoided in the next n seconds, where n < m; and predict the driving trajectory of the vehicle to be avoided in the next m seconds based on the lane line information and / or the driving trajectory in the next n seconds.

[0098] In one embodiment, the avoidance module 903 is further configured to: move the outline of the vehicle in the bird's-eye view in a direction away from the driving trajectory until the outline of the vehicle in the bird's-eye view no longer overlaps with the outline of the vehicle to be avoided in the bird's-eye view, and then stop moving, and generate a target avoidance position based on the outline of the vehicle in the bird's-eye view at this time.

[0099] In one embodiment, the acquisition module 901 is further configured to: identify whether there is a vehicle to be avoided around the vehicle; if so, determine whether the vehicle to be avoided is in the same lane or adjacent lane as the vehicle; if so, trigger an avoidance determination request.

[0100] In one embodiment, the acquisition module 901 is further configured to: collect sound information around the vehicle and determine whether there is a horn sound of a special vehicle in the sound information; if there is a horn sound of a special vehicle, acquire image information of the direction of the sound source of the horn sound; and identify whether there is a special vehicle based on the image information.

[0101] The vehicle avoidance device provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0102] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present invention can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0103] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of the present invention can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0104] Figure 10 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present invention. For example... Figure 10 As shown, the electronic device 100 includes:

[0105] Processor 101, memory 102, and communication interface 103;

[0106] The memory 102 is used to store the executable instructions of the processor 101; the executable instructions may be computer-executable instructions.

[0107] The processor 101 is configured to execute the technical solutions in any of the foregoing method embodiments by executing the executable instructions.

[0108] Optionally, the memory 102 can be either standalone or integrated with the processor 101.

[0109] Optionally, when the memory 102 is a device independent of the processor 101, the electronic device 100 may further include:

[0110] Bus 104, memory 102 and communication interface 103 are connected to processor 101 through bus 104 and complete mutual communication. Communication interface 103 is used to communicate with other devices.

[0111] Optionally, the communication interface 103 can be implemented using a transceiver. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write databases, and read-only databases). The memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0112] Bus 104 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one line is used in the diagram, but this does not imply that there is only one bus or one type of bus.

[0113] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0114] The electronic device is used to execute the technical solutions in any of the foregoing method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0115] This invention also provides a readable storage medium, which can be a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the technical solution provided in any of the foregoing method embodiments.

[0116] This invention also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the technical solutions provided in any of the foregoing method embodiments.

[0117] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0118] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0119] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0120] The above embodiments are merely preferred embodiments provided to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on the present invention are all within the scope of protection of the present invention.

Claims

1. A method for avoiding a vehicle, characterized in that, include: In response to a trigger avoidance determination request, a bird's-eye view of the vehicle in the target area is obtained, and the vehicle to be avoided is determined in the bird's-eye view; If no vehicle to be avoided is found in the bird's-eye view, the coverage area of ​​the target area is expanded and the bird's-eye view is re-acquired until the vehicle to be avoided appears in the bird's-eye view; Based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view, predict the driving trajectory of the vehicle to be avoided in the bird's-eye view within the next m seconds; Based on the vehicle's position and its trajectory within the next m seconds, determine whether the vehicle's outline in the bird's-eye view will overlap with the outline of the vehicle to be avoided in the bird's-eye view. If it will, avoidance is required; otherwise, avoidance is not required. If avoidance is required, the vehicle's outline in the bird's-eye view is moved away from the driving trajectory until the vehicle's outline in the bird's-eye view no longer overlaps with the outline of the vehicle to be avoided in the bird's-eye view. Then, the movement stops, a target avoidance position is generated based on the vehicle's outline in the bird's-eye view at this time, and the vehicle is controlled to move to the target avoidance position.

2. The vehicle avoidance method according to claim 1, characterized in that, The step of predicting the trajectory of the vehicle to be avoided within the next m seconds in the bird's-eye view based on its position in the bird's-eye view includes: Obtain lane line information from the bird's-eye view and / or the driving trajectory of the vehicle to be avoided in the next n seconds, where n < m; Based on the lane line information and / or the driving trajectory within the n seconds, predict the driving trajectory of the vehicle to be avoided within the next m seconds.

3. The vehicle avoidance method according to claim 1 or 2, characterized in that, The triggering conditions for the avoidance determination request include: Identify whether there are vehicles around the vehicle that need to be avoided; If so, determine whether the vehicle to be avoided is in the same lane or an adjacent lane as the vehicle itself. If so, trigger an avoidance decision request.

4. The vehicle avoidance method according to claim 3, characterized in that, The vehicle to be avoided is a special vehicle. Identifying whether there is a vehicle to be avoided around the vehicle includes: Collect sound information from the area around the vehicle and determine whether there are horns from special vehicles in the sound information; If a special vehicle is honking its horn, then image information of the direction of the sound source of the horn is acquired; The presence of special vehicles can be identified based on the image information.

5. A vehicle avoidance device, characterized in that, include: The acquisition module is used to acquire a bird's-eye view of the vehicle in the target area in response to a trigger avoidance determination request, and to determine the vehicle to be avoided in the bird's-eye view; The judgment module is used to expand the coverage of the target area and re-acquire the bird's-eye view if no vehicle to be avoided is found in the bird's-eye view, until the vehicle to be avoided appears in the bird's-eye view; Based on the positions of the vehicle and the vehicle to be avoided in the bird's-eye view, predict the driving trajectory of the vehicle to be avoided in the bird's-eye view within the next m seconds; Based on the vehicle's position and its trajectory within the next m seconds, determine whether the vehicle's outline in the bird's-eye view will overlap with the outline of the vehicle to be avoided in the bird's-eye view. If it will, avoidance is required; otherwise, avoidance is not required. The obstacle avoidance module is used to move the outline of the vehicle in the bird's-eye view away from the driving trajectory when obstacle avoidance is required, until the outline of the vehicle in the bird's-eye view no longer overlaps with the outline of the vehicle to be avoided in the bird's-eye view, then stop moving, generate a target obstacle avoidance position based on the outline of the vehicle in the bird's-eye view at this time, and control the vehicle to move to the target obstacle avoidance position.

6. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

Images