Vehicle obstacle avoidance method and device in parking scenario, and storage medium
By filtering collision risk areas around the vehicle and obstacle collision angles, and dynamically adjusting the obstacle avoidance distance threshold, the problem of high false alarm rate of ultrasonic obstacle avoidance solutions under external interference is solved, achieving more accurate and intelligent obstacle avoidance and improving the parking experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- VOYAH AUTOMOBILE TECH CO LTD
- Filing Date
- 2026-02-11
- Publication Date
- 2026-06-12
AI Technical Summary
Existing ultrasonic obstacle avoidance solutions have a high false alarm rate under external interference, resulting in low vehicle obstacle avoidance accuracy and affecting the user's parking experience. In particular, they are difficult to identify key obstacles in multi-obstacle scenarios, causing the obstacle avoidance strategy to fail.
By identifying collision risk zones around the vehicle and the collision angles between the vehicle and obstacles, effective obstacles requiring avoidance are repeatedly screened. Combined with vehicle status data and ultrasonic sensor information, the obstacle avoidance distance threshold is dynamically adjusted to achieve precise obstacle avoidance.
It improves the accuracy and intelligence of vehicle obstacle avoidance, reduces the frequency of accidental obstacle avoidance, and enhances the driving experience for users in parking scenarios.
Smart Images
Figure CN122186141A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle technology, and in particular to a vehicle obstacle avoidance method, device and storage medium in a parking scenario. Background Technology
[0002] As parking environments become increasingly complex, the risk of collisions during parking also rises. Ultrasonic radar, also known as ultrasonic sensors, is widely used in obstacle avoidance solutions during parking due to its advantages such as low cost, mature technology, and accurate ranging within a certain range.
[0003] Currently, ultrasonic obstacle avoidance solutions based on ultrasonic sensors generally determine the distance information of obstacles around the vehicle by using ultrasonic sensors to identify the set of obstacles around the vehicle, and trigger obstacle avoidance operation when the distance between the vehicle and an obstacle in the set of obstacles is less than a preset fixed threshold.
[0004] This implementation method is prone to a high false alarm rate when the ultrasonic sensor is interfered with by external factors, which in turn affects the accuracy of vehicle obstacle avoidance and the user's parking experience. Summary of the Invention
[0005] This application provides a vehicle obstacle avoidance method, device, and storage medium for parking scenarios, which can improve the accuracy and intelligence of vehicle obstacle avoidance, reduce the triggering frequency of accidental obstacle avoidance operations, and thus enhance the user's driving experience in parking scenarios.
[0006] In a first aspect, embodiments of this application provide a vehicle obstacle avoidance method in a parking scenario, including:
[0007] Based on the obstacle information collected by the vehicle's ultrasonic sensors, the first obstacle that the vehicle needs to avoid is determined.
[0008] Based on the vehicle status data, the predicted driving trajectory of the vehicle is determined, and based on the predicted driving trajectory of the vehicle, the collision risk area in the area surrounding the vehicle is determined.
[0009] The second obstacle is determined based on the intersection of the first obstacle and the collision risk area;
[0010] Based on the collision angle between each of the second obstacles and the vehicle, a third obstacle is determined, and based on the obstacle avoidance state corresponding to the third obstacle, the vehicle is controlled to avoid the obstacle.
[0011] In one possible implementation, the vehicle status data includes at least the vehicle gear position and the vehicle steering wheel position; determining the predicted driving trajectory of the vehicle based on the vehicle status data includes:
[0012] Based on the vehicle gear position and the vehicle steering wheel position, determine the matching vehicle contour point and the vehicle's direction of movement.
[0013] Based on the vehicle's direction of movement, the motion trajectory of each matched vehicle contour point is determined, and based on the motion trajectory of the matched vehicle contour points, the predicted driving trajectory is determined.
[0014] In one possible implementation, determining a collision risk zone in the area surrounding the vehicle based on the vehicle's predicted driving trajectory includes:
[0015] Based on the movement trajectory of the matched vehicle contour points, the area around the vehicle is divided into multiple regions to obtain the vehicle surrounding area.
[0016] Based on the maximum driving range corresponding to the predicted driving trajectory of the vehicle, the collision risk area in the area surrounding the vehicle is determined.
[0017] In one possible implementation, the method further includes:
[0018] The collision angle between the second obstacle and the vehicle is determined based on a first endpoint in the second obstacle and a second endpoint in the vehicle; wherein the first endpoint indicates the endpoint in the second obstacle that is closest to the vehicle; and the second endpoint indicates the endpoint in the vehicle profile that has a collision risk with the first endpoint.
[0019] Determining the third obstacle based on the collision angle between each of the second obstacles and the vehicle includes:
[0020] The second obstacle whose collision angle meets the collision requirements is identified as the third obstacle.
[0021] In one possible implementation, the second obstacle whose collision angle meets the collision requirements is identified as the third obstacle, including:
[0022] If the collision requirement indicates a minimum angle requirement, then the second obstacle at the minimum collision angle is identified as the third obstacle.
[0023] If the collision requirement indicates an angle difference requirement, then the second obstacle whose difference with the minimum collision angle meets the angle difference requirement, and the second obstacle at the minimum collision angle, are identified as the third obstacle.
[0024] In one possible implementation, the obstacle information is used to indicate at least one initial obstacle; the obstacle information includes at least the obstacle attributes and obstacle confidence level of each initial obstacle; based on the obstacle information collected by the vehicle's ultrasonic sensors, determining the first obstacle that the vehicle needs to avoid includes:
[0025] An initial obstacle whose obstacle attribute is the target attribute and whose obstacle confidence level meets the confidence level requirement is identified as the first obstacle.
[0026] In one possible implementation, the method further includes:
[0027] Determine the real-time obstacle avoidance distance between the third obstacle and the vehicle;
[0028] The obstacle avoidance state corresponding to the third obstacle is determined based on the real-time obstacle avoidance distance, the obstacle avoidance distance threshold in each preset state, and the duration requirement in each preset state.
[0029] In one possible implementation, the method further includes:
[0030] Obtain the vehicle speed information and determine the speed correction value under the vehicle speed information;
[0031] Based on the maximum safe distance and the speed correction value under each preset state, the obstacle avoidance distance threshold under each preset state is determined.
[0032] Secondly, embodiments of this application provide a vehicle obstacle avoidance device for parking scenarios, comprising:
[0033] The first determining unit is used to determine the first obstacle that the vehicle needs to avoid based on the obstacle information collected by the vehicle's ultrasonic sensors.
[0034] The second determining unit is used to determine the predicted driving trajectory of the vehicle based on the vehicle status data of the vehicle, and to determine the collision risk area in the area surrounding the vehicle based on the predicted driving trajectory of the vehicle.
[0035] The third determining unit is used to determine the second obstacle based on the intersection of the first obstacle and the collision risk area;
[0036] The obstacle avoidance processing unit is used to determine a third obstacle based on the collision angle between each second obstacle and the vehicle, and to control the vehicle to avoid the obstacle based on the obstacle avoidance state corresponding to the third obstacle.
[0037] In one possible implementation, the vehicle status data includes at least the vehicle gear position and the vehicle steering wheel position; in this case, the second determining unit is configured to:
[0038] Based on the vehicle gear position and the vehicle steering wheel position, determine the matching vehicle contour point and the vehicle's direction of movement.
[0039] Based on the vehicle's direction of movement, the motion trajectory of each matched vehicle contour point is determined, and based on the motion trajectory of the matched vehicle contour points, the predicted driving trajectory is determined.
[0040] In one possible implementation, the second determining unit is configured to:
[0041] Based on the movement trajectory of the matched vehicle contour points, the area around the vehicle is divided into multiple regions to obtain the vehicle surrounding area.
[0042] Based on the maximum driving range corresponding to the predicted driving trajectory of the vehicle, the collision risk area in the area surrounding the vehicle is determined.
[0043] In one possible implementation, the device is also used for:
[0044] The collision angle between the second obstacle and the vehicle is determined based on a first endpoint in the second obstacle and a second endpoint in the vehicle; wherein the first endpoint indicates the endpoint in the second obstacle that is closest to the vehicle; and the second endpoint indicates the endpoint in the vehicle profile that has a collision risk with the first endpoint.
[0045] Determining the third obstacle based on the collision angle between each of the second obstacles and the vehicle includes:
[0046] The second obstacle whose collision angle meets the collision requirements is identified as the third obstacle.
[0047] In one possible implementation, the obstacle avoidance processing unit is used for:
[0048] If the collision requirement indicates a minimum angle requirement, then the second obstacle at the minimum collision angle is identified as the third obstacle.
[0049] If the collision requirement indicates an angle difference requirement, then the second obstacle whose difference with the minimum collision angle meets the angle difference requirement, and the second obstacle at the minimum collision angle, are identified as the third obstacle.
[0050] In one possible implementation, the obstacle information is used to indicate at least one initial obstacle; the obstacle information includes at least the obstacle attributes and obstacle confidence level of each initial obstacle; in this case, the first determining unit is configured to:
[0051] An initial obstacle whose obstacle attribute is the target attribute and whose obstacle confidence level meets the confidence level requirement is identified as the first obstacle.
[0052] In one possible implementation, the device is also used for:
[0053] Determine the real-time obstacle avoidance distance between the third obstacle and the vehicle;
[0054] The obstacle avoidance state corresponding to the third obstacle is determined based on the real-time obstacle avoidance distance, the obstacle avoidance distance threshold in each preset state, and the duration requirement in each preset state.
[0055] In one possible implementation, the device is also used for:
[0056] Obtain the vehicle speed information and determine the speed correction value under the vehicle speed information;
[0057] Based on the maximum safe distance and the speed correction value under each preset state, the obstacle avoidance distance threshold under each preset state is determined.
[0058] Thirdly, embodiments of this application provide a computer device, including: a memory and a processor;
[0059] The memory stores computer-executed instructions;
[0060] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.
[0061] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.
[0062] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.
[0063] The vehicle obstacle avoidance method, device, and storage medium provided in this application for parking scenarios can determine the first obstacle that the vehicle needs to avoid based on obstacle information collected by the vehicle's ultrasonic sensors, thereby achieving preliminary screening of obstacles around the vehicle. Then, based on the vehicle's state data, the predicted driving trajectory of the vehicle can be determined, and based on the predicted driving trajectory, a collision risk area in the area surrounding the vehicle can be determined. At this point, the intersection of the first obstacle and the collision risk area can be determined as the second obstacle. Next, the collision risk area in the area surrounding the vehicle can be determined by predicting the vehicle's driving trajectory, thereby achieving a second screening of the first obstacle based on the collision risk area, resulting in the second obstacle. Then, the collision angle between the second obstacle and the vehicle can be used to determine the third obstacle. Finally, the collision angle can be used to achieve a third screening of the obstacles, resulting in the third obstacle. In the above process, through multiple screenings, the effective obstacles that the vehicle needs to avoid, namely the third obstacle, can be determined. At this time, when controlling the vehicle to avoid obstacles according to the obstacle avoidance status corresponding to the third obstacle, the accuracy of vehicle obstacle avoidance can be improved, the triggering frequency of accidental obstacle avoidance operations can be reduced, and the probability of accidental obstacle avoidance can be reduced. This not only improves the intelligence of vehicle obstacle avoidance, but also improves the user's driving experience in parking scenarios. Attached Figure Description
[0064] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0065] Figure 1 A flowchart illustrating a vehicle obstacle avoidance method in a parking scenario provided in this application embodiment;
[0066] Figure 2 A flowchart illustrating another vehicle obstacle avoidance method in a parking scenario provided in this application embodiment;
[0067] Figure 3 A schematic diagram of the area surrounding a vehicle provided in an embodiment of this application;
[0068] Figure 4 A schematic diagram illustrating the determination of the collision angle between a second obstacle and a vehicle, provided as an embodiment of this application;
[0069] Figure 5 This application provides a schematic diagram of the structure of a vehicle obstacle avoidance device in a parking scenario.
[0070] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.
[0071] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0072] 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 numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0073] The term "and / or" in this article merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone.
[0074] In addition, the term "at least one" in this document means any combination of at least two of any one or more of a plurality of elements, such as including at least one of A, B, and C, and may mean including any one or more elements selected from the set consisting of A, B, and C.
[0075] As parking environments become increasingly complex, the risk of collisions during parking also rises. Ultrasonic radar, also known as ultrasonic sensors, is widely used in obstacle avoidance solutions during parking due to its advantages such as low cost, mature technology, and accurate ranging within a certain range.
[0076] Currently, ultrasonic obstacle avoidance solutions based on ultrasonic sensors generally determine the distance information of obstacles around the vehicle by using ultrasonic sensors to identify the set of obstacles around the vehicle, and trigger obstacle avoidance operation when the distance between the vehicle and an obstacle in the set of obstacles is less than a preset fixed threshold.
[0077] However, ultrasonic sensors are susceptible to interference from external factors (such as ground conditions, ambient temperature, rain, snow, etc.). When ultrasonic sensors are interfered with by external factors, they are prone to a high false alarm rate, which can lead to the triggering of false obstacle avoidance operations, thereby affecting the accuracy of vehicle obstacle avoidance and also affecting the user's parking experience.
[0078] Furthermore, existing ultrasonic obstacle avoidance solutions may fail to effectively identify critical obstacles on the current path (e.g., the obstacle closest to the vehicle's direction of movement) when multiple obstacles are present simultaneously. For example, they may respond to obstacles far from the vehicle's direction of movement, thus ignoring obstacles with greater actual risks, which leads to the failure of the obstacle avoidance strategy and further affects the accuracy of the obstacle avoidance operation.
[0079] The vehicle obstacle avoidance method provided in this application for parking scenarios can filter out effective obstacles that need to be avoided by considering the collision risk area in the area surrounding the vehicle and the collision angle between the obstacle and the vehicle, and then avoid the selected effective obstacles. This can improve the accuracy and intelligence of vehicle obstacle avoidance, reduce the frequency of accidental obstacle avoidance operations, and thus improve the user's driving experience in parking scenarios.
[0080] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0081] Figure 1 This is a flowchart illustrating a vehicle obstacle avoidance method in a parking scenario provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes:
[0082] S101. Based on the obstacle information collected by the vehicle's ultrasonic sensors, determine the first obstacle that the vehicle needs to avoid.
[0083] In one example, obstacles around the vehicle (e.g., initial obstacles) can be detected in real time using ultrasonic sensors to obtain obstacle information. This obstacle information may include, but is not limited to, the obstacle type, obstacle attributes, and obstacle coordinates of the initial obstacles.
[0084] In one example, the obstacle type can indicate the shape of the initial obstacle; for example, the obstacle type can be a point obstacle type or a line obstacle type.
[0085] In one example, obstacle attributes can be used to indicate whether the initial obstacle is one that needs to be avoided. For example, obstacle attributes can be high or low. High attributes indicate that the initial obstacle needs to be avoided, while low attributes indicate that the initial obstacle does not need to be avoided.
[0086] In one possible implementation, the obstacle attribute can also be an unknown attribute. In this case, the initial obstacle with the unknown attribute can be used to characterize obstacles that need to be avoided or obstacles that do not need to be avoided, thereby covering the obstacle attributes of all obstacles around the vehicle.
[0087] In practical applications, an obstacle dataset can be determined based on the obstacle information of each initial obstacle. The number of obstacles included in the obstacle dataset can then be set to determine its specific content. For example, the number of obstacles in the obstacle dataset could be 20, 10, or 30, etc. The size of the obstacle dataset is not limited here; it is determined by the specific needs of the parking scenario.
[0088] In one example, the first obstacle can be used to indicate at least part of the initial obstacles, in which case the first obstacle can be used to indicate the set of obstacles that need to be avoided.
[0089] S102. Based on the vehicle's status data, determine the vehicle's predicted driving trajectory, and based on the vehicle's predicted driving trajectory, determine the collision risk area in the area surrounding the vehicle.
[0090] In one example, vehicle status data can be used to indicate the real-time status of the vehicle. For example, vehicle status data may include, but is not limited to, vehicle speed, steering angle / steering wheel angle, and gear position.
[0091] In one example, the predicted trajectory of a vehicle can be determined based on vehicle state data and a second-order inertial system model.
[0092] In one example, the area surrounding a vehicle can include the area to the left of the vehicle, the area in front of the vehicle, and the area to the right of the vehicle. In this case, the collision risk area within the vehicle's surrounding area can be understood as the area where a collision is at risk.
[0093] S103. Determine the second obstacle based on the intersection of the first obstacle and the collision risk area.
[0094] In one example, if the first obstacle is located within the collision risk area, then the first obstacle is identified as the second obstacle; if a portion of the first obstacle is located within the collision risk area, then that portion of the first obstacle is identified as the second obstacle.
[0095] S104. Based on the collision angle between each second obstacle and the vehicle, determine the third obstacle, and control the vehicle to avoid the obstacle according to the obstacle avoidance state corresponding to the third obstacle.
[0096] In one example, the collision angle between the second obstacle and the vehicle can be used to indicate the distance between the second obstacle and the vehicle. In this case, obstacles that are closer to the vehicle, i.e., the third obstacle, can be selected based on the collision angle.
[0097] In one example, the obstacle avoidance state can be used to indicate the corresponding obstacle avoidance logic. In this case, the vehicle can be controlled to avoid obstacles based on the obstacle avoidance logic indicated by the obstacle avoidance state corresponding to the third obstacle.
[0098] As described above, in this embodiment, the vehicle's ultrasonic sensors can be used to identify the first obstacle that the vehicle needs to avoid, thus achieving initial screening of obstacles around the vehicle. Next, the vehicle's predicted trajectory can be determined based on its vehicle status data, and a collision risk zone can be identified within the vehicle's surrounding area based on this trajectory. Then, the intersection of the first obstacle and the collision risk zone can be used to identify the second obstacle. Furthermore, by predicting the vehicle's trajectory, the collision risk zone can be identified within the vehicle's surrounding area, allowing for a second screening of the first obstacle and obtaining the second obstacle. Finally, the collision angle between the second obstacle and the vehicle can be used to identify the third obstacle. Finally, the collision angle can be used to perform a third screening of the obstacles, obtaining the third obstacle. In the above process, through multiple screenings, the effective obstacles that the vehicle needs to avoid, namely the third obstacle, can be determined. At this time, when controlling the vehicle to avoid obstacles according to the obstacle avoidance status corresponding to the third obstacle, the accuracy of vehicle obstacle avoidance can be improved, the triggering frequency of accidental obstacle avoidance operations can be reduced, and the probability of accidental obstacle avoidance can be reduced. This not only improves the intelligence of vehicle obstacle avoidance, but also improves the user's driving experience in parking scenarios.
[0099] Figure 2 A flowchart illustrating another vehicle obstacle avoidance method in a parking scenario provided in this application embodiment is shown below. Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, a vehicle obstacle avoidance method in parking scenarios is described in detail. The method includes:
[0100] S201. Based on the obstacle information collected by the vehicle's ultrasonic sensors, determine the first obstacle that the vehicle needs to avoid.
[0101] Optionally, obstacle information can be used to indicate at least one initial obstacle; the obstacle information includes at least the obstacle attributes and obstacle confidence of each initial obstacle.
[0102] Based on this, an initial obstacle whose obstacle attribute is the target attribute and whose obstacle confidence meets the confidence requirement can be identified as the first obstacle.
[0103] In one example, the target attribute can be understood as the aforementioned high attribute.
[0104] In one example, the confidence requirement can be used to indicate a preset confidence threshold. For example, the confidence requirement can be: greater than or equal to the preset confidence threshold.
[0105] For example, if the preset confidence threshold is 60%, then an initial obstacle with a high attribute and an obstacle confidence greater than or equal to 60% can be identified as the first obstacle.
[0106] In the above implementation, the first obstacle that requires avoidance and has high confidence can be selected for subsequent vehicle obstacle avoidance processing, thereby reducing false alarms caused by external environmental interference.
[0107] In one possible implementation, the vehicle status data in S102 includes at least the vehicle gear position and the vehicle steering wheel position. In this case, when determining the predicted driving trajectory of the vehicle based on the vehicle status data, the process described below can be referred to.
[0108] S202. Based on the vehicle's gear position and steering wheel position, determine the matching vehicle profile point and the vehicle's direction of movement.
[0109] In one example, the vehicle's gear position can be either forward or reverse.
[0110] In one example, the vehicle's steering wheel status can indicate the steering wheel angle.
[0111] In one example, the number of vehicle outline points can be multiple, such as the left front endpoint, front midpoint, right front endpoint, left midpoint, left rear endpoint, rear midpoint, right rear endpoint, and right midpoint. The number and position of vehicle outline points are not limited here, and the actual needs shall be met.
[0112] In one example, at least some vehicle profile points can be identified as matching vehicle profile points based on the vehicle's gear position and steering wheel position. For instance, if the vehicle is in drive and the steering wheel is turned 5 degrees to the left, then the left front endpoint, front midpoint, right front endpoint, and left midpoint can be identified as matching vehicle profile points.
[0113] In one example, the vehicle's direction of movement can also be determined based on the vehicle's gear position and steering wheel position. The direction of movement can indicate the steering angle of the vehicle's front wheels.
[0114] S203. Based on the vehicle's direction of movement, determine the motion trajectory of each matched vehicle contour point, and based on the motion trajectory of the matched vehicle contour points, determine the predicted driving trajectory.
[0115] In one example, the trajectory of each matched vehicle profile point can be determined based on the vehicle's direction of movement and a second-order inertial system model.
[0116] It should be noted that, in addition to the aforementioned second-order inertial system model, the predicted driving trajectory / motion trajectory of the vehicle can also be determined based on a bicycle model or a learning model, etc. The method of determining the predicted driving trajectory of the vehicle is not limited here, as long as it is feasible.
[0117] In one example, the predicted driving trajectory of the vehicle can be determined by combining the trajectories of each matched vehicle contour point.
[0118] In the above embodiments, the predicted driving trajectory of a vehicle can be determined based on the motion trajectory of the vehicle contour points in the vehicle, which can reduce the computational complexity and computational load, thereby improving the speed and efficiency of the determined predicted driving trajectory of the vehicle.
[0119] Then, based on the predicted driving trajectory of the vehicle determined in the aforementioned steps, the collision risk area in the area surrounding the vehicle can be determined, as detailed in the process described below.
[0120] S204. Based on the movement trajectory of the matched vehicle contour points, divide the area around the vehicle into multiple regions to obtain the vehicle surrounding area.
[0121] In one example, the movement trajectory of the matched vehicle contour points can be used as a boundary line to divide the area around the vehicle, resulting in multiple regions, namely the vehicle perimeter area.
[0122] The area surrounding the vehicle may include, but is not limited to: the area directly in front of the vehicle, the area to the left of the vehicle, the area to the right of the vehicle, the inner area of the vehicle (i.e., the smallest area), and the outer area of the vehicle.
[0123] For example, see Figure 3 , Figure 3 This is a schematic diagram of the area surrounding a vehicle, provided as an embodiment of this application. Figure 3 As shown, assuming the matched vehicle contour points include the aforementioned left front endpoint, front midpoint, right front endpoint, and left midpoint, then the number of motion trajectories of the matched vehicle contour points can be determined to be 4 (e.g., Figure 3 (As shown by the dotted lines), then it can be determined that the area surrounding the vehicle includes the area directly in front of the vehicle (such as...). Figure 3 Area 3 shown) The area on the left side of the vehicle (such as...) Figure 3Area 2 shown), the inner area of the vehicle (such as...) Figure 3 Area 1 shown), and the outer area of the vehicle (such as...) Figure 3 Area 4 is shown.
[0124] S205. Based on the maximum driving range corresponding to the predicted driving trajectory of the vehicle, determine the collision risk area in the area surrounding the vehicle.
[0125] For example, the maximum driving range corresponding to the predicted driving trajectory of the vehicle may include Figure 3 Regions 2 and 3 are shown. At this point, it can be... Figure 3 Areas 2 and 3 in the area surrounding the vehicle were identified as collision risk areas.
[0126] In the above implementation, the vehicle's perimeter can be divided into multiple surrounding areas based on the movement trajectory of the vehicle's contour points. Then, based on the maximum travel range corresponding to the vehicle's predicted trajectory, collision risk areas within these surrounding areas can be determined. This allows for the selection of obstacle avoidance zones, thereby reducing the computational complexity of obstacle avoidance processing and improving efficiency. Furthermore, this implementation can also match the vehicle's kinematic constraints, thus enhancing the safety and accuracy of obstacle avoidance.
[0127] S206. Determine the second obstacle based on the intersection of the first obstacle and the collision risk area.
[0128] S207. Determine the collision angle between the second obstacle and the vehicle based on the first endpoint in the second obstacle and the second endpoint in the vehicle.
[0129] The first endpoint refers to the endpoint of the second obstacle that is closest to the vehicle; the second endpoint refers to the endpoint of the vehicle profile that has a collision risk with the first endpoint.
[0130] For example, see Figure 4 , Figure 4 A schematic diagram illustrating the determination of the collision angle between a second obstacle and a vehicle, provided as an embodiment of this application, is shown below. Figure 4 As shown, the angle formed by the lines connecting the center of the motion circle corresponding to the motion trajectory / predicted driving trajectory to the first endpoint in the second obstacle and the second endpoint in the vehicle can be determined as the collision angle between the second obstacle and the vehicle.
[0131] In one example, after determining the first and second endpoints, the coordinates corresponding to the first endpoint can be inverted to unify the second obstacle into the vehicle coordinate system. Then, the coordinates corresponding to the first and second endpoints can be converted into polar coordinates to facilitate the calculation of the collision angle.
[0132] according to Figure 4 It can be seen that the arc length corresponding to the collision angle (where the arc length corresponding to the collision angle can be determined by the product of the radius and the collision angle) is the distance between the vehicle and the second obstacle. At this time, the distance between the second obstacle and the vehicle can be quantified simply and accurately by the collision angle, so as to accurately filter out the third obstacle that is close to the vehicle, thereby achieving precise obstacle avoidance.
[0133] Then, a third obstacle that is close to the vehicle can be selected by the collision angle, as described in the process below.
[0134] S208. The second obstacle whose collision angle meets the collision requirements is identified as the third obstacle.
[0135] In one example, the distance between the second obstacle and the vehicle can be limited based on the collision angle requirement.
[0136] Optionally, if the collision requirement indicates a minimum angle requirement, then the second obstacle at the minimum collision angle can be identified as the third obstacle.
[0137] In one example, the number of second obstacles (i.e., third obstacles) at the minimum collision angle can be one or more. The number of third obstacles is not limited here, depending on what is feasible. In this case, if there is only one third obstacle, obstacle avoidance is performed based on one obstacle. If there are multiple third obstacles, obstacle avoidance needs to be performed on multiple obstacles simultaneously.
[0138] In this embodiment of the application, the second obstacle at the minimum collision angle can be determined from all collision risk areas based on the minimum angle requirement, and then designated as the third obstacle.
[0139] Alternatively, different minimum angle requirements can be set for each collision risk area, thereby identifying the third obstacle closest to the vehicle within each collision risk area, thus identifying multiple third obstacles.
[0140] This implementation method can avoid obstacles by selecting the closest obstacles to the vehicle, which not only improves the accuracy of obstacle avoidance but also reduces the frequency of accidental obstacle avoidance and missed obstacle avoidance.
[0141] In one possible implementation, when the obstacle is close, obstacle avoidance is performed based on the second obstacle with the smallest collision angle. This approach lacks comprehensiveness and therefore fails to meet the obstacle avoidance requirements.
[0142] Based on this, embodiments of this application can also perform obstacle avoidance by selecting the few obstacles closest to the vehicle.
[0143] At this point, the collision angle requirement can indicate the angle difference requirement. If the collision requirement indicates the angle difference requirement, then the second obstacle whose difference with the minimum collision angle meets the angle difference requirement, and the second obstacle at the minimum collision angle, are identified as the third obstacle.
[0144] This implementation method can avoid obstacles by selecting those closest to the vehicle within each collision risk area, which not only improves the effectiveness and accuracy of vehicle obstacle avoidance but also enhances the comprehensiveness and safety of vehicle obstacle avoidance.
[0145] S209. Control the vehicle to avoid the obstacle according to the obstacle avoidance state corresponding to the third obstacle.
[0146] In one possible implementation, the obstacle avoidance state corresponding to the third obstacle can be determined through the following process:
[0147] First, determine the real-time obstacle avoidance distance between the third obstacle and the vehicle.
[0148] In one example, real-time obstacle avoidance distance can be used to indicate the distance the vehicle's rear axle has traveled.
[0149] For example, see Figure 4 Based on the distance the rear axle of the vehicle moves at the collision angle, the real-time obstacle avoidance distance between the third obstacle and the vehicle can be determined.
[0150] Then, based on the real-time obstacle avoidance distance, the obstacle avoidance distance threshold in each preset state, and the duration requirement in each preset state, the obstacle avoidance state corresponding to the third obstacle is determined.
[0151] In this embodiment of the application, multiple obstacle avoidance states, also known as preset states, can be preset. For example, preset states may include, but are not limited to: Safe state, Dangerous state, Verdangerous state, and Stopped state.
[0152] In related technologies, obstacle avoidance mainly uses fixed thresholds, meaning that the obstacle avoidance distance threshold is a fixed value for each preset state. This results in a lack of flexibility and diversity in obstacle avoidance solutions, making them unsuitable for complex parking scenarios (such as multiple obstacles coexisting or narrow parking spaces).
[0153] In the embodiments of this application, the obstacle avoidance distance threshold under each preset state can be dynamically adjusted to improve the flexibility of the obstacle avoidance scheme and thus improve the accuracy of obstacle avoidance.
[0154] In one possible implementation, the obstacle avoidance distance for each preset state can be determined according to the following process:
[0155] First, obtain the vehicle's speed information and determine the speed correction value based on that speed information.
[0156] Then, based on the maximum safe distance and speed correction value under each preset state, the obstacle avoidance distance threshold under each preset state is determined.
[0157] At this point, the obstacle avoidance distance threshold for each preset state can be dynamically adjusted using the maximum safe distance and speed correction value. For example, in low-speed scenarios, the obstacle avoidance distance threshold can be relaxed to avoid premature braking, while in high-speed scenarios, the threshold can be tightened to mitigate risks in advance. Compared to traditional fixed threshold methods, this approach allows the obstacle avoidance distance threshold to adaptively adjust based on vehicle speed and scenario, improving the flexibility, versatility, and intelligence of obstacle avoidance states. Furthermore, it enhances the flexibility and versatility of obstacle avoidance strategies, enabling adaptation to complex vehicle obstacle avoidance scenarios.
[0158] In one example, the maximum safe distance and speed correction value for each preset state can be determined through actual vehicle calibration.
[0159] In one example, the duration requirement can be understood as the frame count requirement for continuously acquired real-time obstacle avoidance distance. In this case, the continuous frame count requirement can be used to distinguish between transient interference and real collision risks, thereby improving the accuracy of obstacle avoidance state determination and reducing the probability of false responses.
[0160] Based on this, the obstacle avoidance distance threshold and duration requirement for each preset state can be:
[0161] Safe state: When the obstacle avoidance distance is >65cm + speed correction value (13cm~60cm) for 50 consecutive frames, the obstacle avoidance state is Safe.
[0162] Dangerous state: When the obstacle avoidance distance is <65cm + speed correction value (13cm~60cm) for 10 consecutive frames, the obstacle avoidance state is Dangerous; when the obstacle avoidance distance is >65cm + speed correction value (13cm~60cm) for 50 consecutive frames, the obstacle avoidance state is Safe.
[0163] Verdangerous state: When the obstacle avoidance distance is <40cm + speed correction value (13cm~60cm) for 10 consecutive frames, the obstacle avoidance state is Verdangerous; when the obstacle avoidance distance is >40cm + speed correction value (13cm~60cm) for 50 consecutive frames, the obstacle avoidance state is Dangerous.
[0164] Stopped state: When the obstacle avoidance distance is less than 20cm + speed correction value (13cm~60cm) for 10 consecutive frames, the obstacle avoidance state is Stopped; when the obstacle avoidance distance is greater than 20cm + speed correction value (13cm~60cm) for 25 consecutive frames, the obstacle avoidance state is Verdangerous.
[0165] In one example, when controlling the vehicle to avoid obstacles based on the obstacle avoidance state corresponding to the third obstacle, the vehicle can execute the corresponding obstacle avoidance strategy based on the obstacle avoidance state corresponding to the third obstacle.
[0166] For example, obstacle avoidance strategies may include, but are not limited to, a first-level warning strategy, a second-level deceleration strategy, and a third-level braking strategy. In this case, when the obstacle avoidance state corresponding to the third obstacle is Dangerous, the first-level warning strategy is executed: a voice prompt alerts the driver to the approaching obstacle, without interfering with the parking system; when the obstacle avoidance state corresponding to the third obstacle is Verdangerous, the second-level deceleration strategy is executed: the vehicle speed is adjusted to match the current distance; when the obstacle avoidance state corresponding to the third obstacle is Stopped, the third-level braking strategy is executed: the vehicle is braked to safely stop in front of the obstacle.
[0167] In the above implementation, a multi-level obstacle avoidance strategy can be used to achieve a smooth transition from warning to braking, which not only ensures the safety of the vehicle during obstacle avoidance but also improves the smoothness of the parking process, thereby enhancing the user's parking and driving experience.
[0168] Figure 5 This is a structural schematic diagram of a vehicle obstacle avoidance device in a parking scenario provided in an embodiment of this application, as shown below. Figure 5 As shown, the vehicle obstacle avoidance device 50 for parking scenarios provided in this embodiment includes:
[0169] The first determining unit 501 is used to determine the first obstacle that the vehicle needs to avoid based on the obstacle information collected by the vehicle's ultrasonic sensors.
[0170] The second determining unit 502 is used to determine the predicted driving trajectory of the vehicle based on the vehicle's vehicle status data, and to determine the collision risk area in the area surrounding the vehicle based on the predicted driving trajectory of the vehicle.
[0171] The third determining unit 503 is used to determine the second obstacle based on the intersection of the first obstacle and the collision risk area.
[0172] The obstacle avoidance processing unit 504 is used to determine the third obstacle based on the collision angle between each second obstacle and the vehicle, and to control the vehicle to avoid the obstacle based on the obstacle avoidance state corresponding to the third obstacle.
[0173] In one possible implementation, the vehicle status data includes at least the vehicle gear position and the vehicle steering wheel position; in this case, the second determining unit 502 is used to:
[0174] Based on the vehicle's gear position and steering wheel position, determine the matching vehicle profile point and the vehicle's direction of movement.
[0175] Based on the vehicle's direction of movement, determine the motion trajectory of each matched vehicle contour point, and based on the motion trajectory of the matched vehicle contour points, determine the predicted driving trajectory.
[0176] In one possible implementation, the second determining unit 502 is configured to:
[0177] Based on the movement trajectory of the matched vehicle contour points, the area around the vehicle is divided into multiple regions to obtain the vehicle surrounding area.
[0178] Based on the maximum driving range corresponding to the vehicle's predicted driving trajectory, the collision risk area in the area surrounding the vehicle is determined.
[0179] In one possible implementation, the device is also used for:
[0180] The collision angle between the second obstacle and the vehicle is determined based on the first endpoint in the second obstacle and the second endpoint in the vehicle; wherein the first endpoint indicates the endpoint in the second obstacle that is closest to the vehicle; and the second endpoint indicates the endpoint in the vehicle profile that has a collision risk with the first endpoint.
[0181] The third obstacle is determined based on the collision angle between each second obstacle and the vehicle, including:
[0182] The second obstacle whose collision angle meets the collision requirements is identified as the third obstacle.
[0183] In one possible implementation, the obstacle avoidance processing unit 504 is used for:
[0184] If the collision requirement indicates a minimum angle requirement, then the second obstacle at the minimum collision angle is identified as the third obstacle.
[0185] If the collision requirement indicates an angle difference requirement, then the second obstacle whose difference with the minimum collision angle meets the angle difference requirement, and the second obstacle at the minimum collision angle, are identified as the third obstacle.
[0186] In one possible implementation, obstacle information is used to indicate at least one initial obstacle; the obstacle information includes at least the obstacle attributes and obstacle confidence level of each initial obstacle; in this case, the first determining unit 501 is used to:
[0187] An initial obstacle whose obstacle attribute is the target attribute and whose obstacle confidence level meets the confidence level requirement is identified as the first obstacle.
[0188] In one possible implementation, the device is also used for:
[0189] Determine the real-time obstacle avoidance distance between the third obstacle and the vehicle;
[0190] The obstacle avoidance state corresponding to the third obstacle is determined based on the real-time obstacle avoidance distance, the obstacle avoidance distance threshold in each preset state, and the duration requirement in each preset state.
[0191] In one possible implementation, the device is also used for:
[0192] Obtain the vehicle's speed information and determine the speed correction value based on that speed information;
[0193] Based on the maximum safe distance and speed correction value under each preset state, the obstacle avoidance distance threshold under each preset state is determined.
[0194] The vehicle obstacle avoidance device in the parking scenario provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0195] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 6 As shown, the computer device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the computer device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.
[0196] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.
[0197] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.
[0198] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.
[0199] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.
[0200] The bus can be an Industry Standard Architecture (ISA) bus, 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 illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.
[0201] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0202] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.
[0203] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0204] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.
[0205] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0206] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0207] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0208] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0209] 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.
[0210] Finally, it should be noted that 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, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.
Claims
1. A vehicle obstacle avoidance method in a parking scenario, characterized in that, The method includes: Based on the obstacle information collected by the vehicle's ultrasonic sensors, the first obstacle that the vehicle needs to avoid is determined. Based on the vehicle status data, the predicted driving trajectory of the vehicle is determined, and based on the predicted driving trajectory of the vehicle, the collision risk area in the area surrounding the vehicle is determined. The second obstacle is determined based on the intersection of the first obstacle and the collision risk area; Based on the collision angle between each of the second obstacles and the vehicle, a third obstacle is determined, and based on the obstacle avoidance state corresponding to the third obstacle, the vehicle is controlled to avoid the obstacle.
2. The method according to claim 1, characterized in that, The vehicle status data includes at least the vehicle gear position and the vehicle steering wheel position; based on the vehicle status data, the predicted driving trajectory of the vehicle is determined, including: Based on the vehicle gear position and the vehicle steering wheel position, determine the matching vehicle contour point and the vehicle's direction of movement. Based on the vehicle's direction of movement, the motion trajectory of each matched vehicle contour point is determined, and based on the motion trajectory of the matched vehicle contour points, the predicted driving trajectory is determined.
3. The method according to claim 2, characterized in that, Based on the predicted driving trajectory of the vehicle, the collision risk zone in the area surrounding the vehicle is determined, including: Based on the movement trajectory of the matched vehicle contour points, the area around the vehicle is divided into multiple regions to obtain the vehicle surrounding area. Based on the maximum driving range corresponding to the predicted driving trajectory of the vehicle, the collision risk area in the area surrounding the vehicle is determined.
4. The method according to claim 1, characterized in that, The method further includes: The collision angle between the second obstacle and the vehicle is determined based on a first endpoint in the second obstacle and a second endpoint in the vehicle; wherein the first endpoint indicates the endpoint in the second obstacle that is closest to the vehicle; and the second endpoint indicates the endpoint in the vehicle profile that has a collision risk with the first endpoint. Determining the third obstacle based on the collision angle between each of the second obstacles and the vehicle includes: The second obstacle whose collision angle meets the collision requirements is identified as the third obstacle.
5. The method according to claim 4, characterized in that, The second obstacle whose collision angle meets the collision requirements is identified as the third obstacle, including: If the collision requirement indicates a minimum angle requirement, then the second obstacle at the minimum collision angle is identified as the third obstacle. If the collision requirement indicates an angle difference requirement, then the second obstacle whose difference with the minimum collision angle meets the angle difference requirement, and the second obstacle at the minimum collision angle, are identified as the third obstacle.
6. The method according to claim 1, characterized in that, The obstacle information is used to indicate at least one initial obstacle; the obstacle information includes at least the obstacle attributes and obstacle confidence level of each initial obstacle; based on the obstacle information collected by the vehicle's ultrasonic sensors, the first obstacle that the vehicle needs to avoid is determined, including: An initial obstacle whose obstacle attribute is the target attribute and whose obstacle confidence level meets the confidence level requirement is identified as the first obstacle.
7. The method according to any one of claims 1-6, characterized in that, The method further includes: Determine the real-time obstacle avoidance distance between the third obstacle and the vehicle; The obstacle avoidance state corresponding to the third obstacle is determined based on the real-time obstacle avoidance distance, the obstacle avoidance distance threshold in each preset state, and the duration requirement in each preset state.
8. The method according to claim 7, characterized in that, The method further includes: Obtain the vehicle speed information and determine the speed correction value under the vehicle speed information; Based on the maximum safe distance and the speed correction value under each preset state, the obstacle avoidance distance threshold under each preset state is determined.
9. A computer device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.
10. 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 1-8.