Obstacle avoidance method, apparatus, and vehicle

Abstract

Embodiments of the present application disclose an obstacle avoidance method and device, and a vehicle. The method comprises: obtaining detection data of an ultrasonic radar of the vehicle; when the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, determining whether to control the vehicle to brake suddenly based on PDC data; and when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determining whether to control the vehicle to brake suddenly based on the PDC data and OBS data. In this way, the distance information obtained by the PDC data and the position information obtained by the OBS data are combined, so that the distance between the obstacle and the vehicle can be determined more accurately, so that the vehicle can be braked suddenly in time, and when the vehicle is controlled to brake suddenly, the driving state of the vehicle is also considered, so that whether the vehicle needs to be braked suddenly can be determined more accurately, thereby improving the safety of the vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, and more particularly, to an obstacle avoidance method and device and vehicle. BACKGROUND

[0002] With the development of technology, more and more vehicles begin to use automatic driving technology, and an important basic function of automatic driving technology is obstacle avoidance, which can be improved. In related manners, image acquisition devices can be arranged on vehicles, and collision avoidance can be performed through images or videos collected. However, due to the low precision of the camera and the quality of the image or video being easily affected by weather and other reasons, the safety of the vehicle still needs to be improved. SUMMARY

[0003] In view of the above problems, the present application provides an obstacle avoidance method, device and vehicle to improve the above problems.

[0004] In a first aspect, the present application provides an obstacle avoidance method, comprising: obtaining detection data of an ultrasonic radar of a vehicle, the detection data comprising PDC data and OBS data, the PDC data representing a distance of a detected obstacle from the vehicle, and the OBS representing a position of the detected obstacle relative to the vehicle; when the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, determining whether to control the vehicle to brake suddenly based on the PDC data, the first ultrasonic radar being an ultrasonic radar installed at a corner position of the vehicle; and when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determining whether to control the vehicle to brake suddenly based on the PDC data and the OBS data.

[0005] In a second aspect, the present application provides an obstacle avoidance device, comprising: a data acquisition unit configured to obtain detection data of an ultrasonic radar of a vehicle, the detection data comprising PDC data and OBS data, the PDC data representing a distance of a detected obstacle from the vehicle, and the OBS representing a position of the detected obstacle relative to the vehicle; and a vehicle control unit configured to, when the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, determine whether to control the vehicle to brake suddenly based on the PDC data, the first ultrasonic radar being an ultrasonic radar installed at a corner position of the vehicle; and when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determine whether to control the vehicle to brake suddenly based on the PDC data and the OBS data.

[0006] In a third aspect, the present application provides a vehicle comprising an ultrasonic radar, one or more processors, and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to perform the method described above.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores program codes, and the program codes perform the method described above when executed.

[0008] The obstacle avoidance method, device, vehicle, and storage medium provided by the present application can obtain the detection data of the ultrasonic radar of the vehicle, and when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, determine whether to control the vehicle to brake suddenly based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determine whether to control the vehicle to brake suddenly based on the PDC data and the OBS data. In this way, the detection data of the ultrasonic radar of the vehicle can be obtained, and when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, whether to control the vehicle to brake suddenly is determined based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, whether to control the vehicle to brake suddenly is determined based on the PDC data and the OBS data. In this way, the distance information obtained by the PDC data and the position information obtained by the OBS data are combined, so that the distance between the obstacle and the vehicle can be determined more accurately, so that the vehicle can be braked suddenly in time, and when the vehicle is braked suddenly, the driving state of the vehicle is also considered, so that whether the vehicle needs to be braked suddenly can be determined more accurately, thereby improving the safety of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0010] Figure 1 A flowchart of an obstacle avoidance method according to an embodiment of the present application is shown;

[0011] Figure 2 A schematic diagram of an ultrasonic radar installation position according to the present application is shown;

[0012] Figure 3 A flowchart of an obstacle avoidance method according to another embodiment of the present application is shown;

[0013] Figure 4 A flow chart of an obstacle avoidance method according to another embodiment of the present application is shown;

[0014] Figure 5 A structural block diagram of an obstacle avoidance device according to an embodiment of the present application is shown;

[0015] Figure 6 A structural block diagram of a vehicle according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0017] In the embodiments of the present application, the inventors propose an obstacle avoidance method, device and vehicle. After obtaining detection data of an ultrasonic radar of a vehicle, the detection data including PDC data and OBS data, when the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, it is determined whether to control the vehicle to brake suddenly based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, it is determined whether to control the vehicle to brake suddenly based on the PDC data and the OBS data. In the above manner, the detection data of the ultrasonic radar of the vehicle can be obtained. When the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, it is determined whether to control the vehicle to brake suddenly based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in the non-straight-in straight-out state, it is determined whether to control the vehicle to brake suddenly based on the PDC data and the OBS data. The distance information obtained by the PDC data and the position information obtained by the OBS data are combined, so that the distance between the obstacle and the vehicle can be determined more accurately, so as to brake the vehicle suddenly in time. Moreover, when the vehicle is controlled to brake suddenly, the driving state of the vehicle is also considered, so that whether the vehicle needs to be braked can be determined more accurately, thereby improving the safety of the vehicle.

[0018] Please refer to Figure 1 The obstacle avoidance method provided in the embodiments of the present application comprises:

[0019] S110: Obtain detection data of an ultrasonic radar of a vehicle, the detection data including PDC data and OBS data, the PDC data representing the distance between a detected obstacle and the vehicle, and the OBS representing the position of the detected obstacle relative to the vehicle.

[0020] Among them, the Ultra Sonic System (USS) can obtain PDC (Parking Distance Control) data and OBS (obstacle coordinates) data within a relatively close distance (such as within 3 meters) to the vehicle, which can then be applied to scenarios such as parking and obstacle avoidance.

[0021] One approach is to acquire initial detection data collected by multiple ultrasonic radars of the vehicle to obtain multiple initial detection data; from the multiple initial detection data, a detection data is determined, in which the distance between the obstacle and the vehicle corresponding to the detection data is the smallest.

[0022] The multiple ultrasonic radars installed on the vehicle can be installed to achieve other functions of the vehicle. In other words, when implementing the obstacle avoidance method proposed in this application, it is not necessary to increase the number of ultrasonic radars, thereby saving costs.

[0023] For example, the installation locations of multiple ultrasonic radars in a vehicle can be as follows: Figure 2 As shown. In Figure 2 There are 12 ultrasonic radars in the vehicle. Among them, 1, 4, 5, and 8 can be the first ultrasonic radars, which are ultrasonic radars installed at the corners of the vehicle; 2, 3, 6, and 7 can be the second ultrasonic radars, which are ultrasonic radars installed at the front of the vehicle or in the middle of the parking space; 9, 10, 11, and 12 can be the third ultrasonic radars, which are ultrasonic radars installed on the side of the vehicle.

[0024] S120: When the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in a straight-in-straight-out state, determine whether to control the vehicle to brake suddenly based on the PDC data. The first ultrasonic radar is an ultrasonic radar installed at the corner of the vehicle.

[0025] In one approach, when the detection data comes from the first ultrasonic radar and the vehicle is in a straight-in / straight-out state, and the distance between the detected obstacle and the vehicle is determined to be greater than or equal to a first threshold based on OBS data, it is determined whether to control the vehicle to brake suddenly based on PDC data; when the detection data comes from the vehicle's first ultrasonic radar and the vehicle is in a straight-in / straight-out state, and the distance between the detected obstacle and the vehicle is determined to be less than a first threshold based on OBS data, it is determined whether to control the vehicle to brake suddenly based on both PDC data and OBS data.

[0026] The first threshold value can be a value obtained based on multiple tests, for example, the first threshold value can be 20 cm. The straight-in straight-out state can refer to a state in which the body posture line of the vehicle is parallel to a coordinate axis representing the longitudinal motion direction of the vehicle in the vehicle coordinate system or the included angle between the two is within a preset range (such as -10°-10°). The determination of the preset range can be affected by test results, sensor accuracy, ultrasonic radar installation position, etc.

[0027] Optionally, whether the vehicle is in the straight-in straight-out state can be determined based on the steering wheel angle of the vehicle. When the steering wheel angle is within a preset angle range, it can be determined that the vehicle is in the straight-in straight-out state. The determination of the preset range can be affected by test results, sensor accuracy, ultrasonic radar installation position, etc.

[0028] Optionally, the coordinates of the closest obstacle to the vehicle can be determined based on the OBS data, so that the distance between the obstacle and the vehicle can be determined based on the coordinates.

[0029] In the embodiments of the present application, the PDC data and the OBS data can correspond to an obstacle avoidance strategy respectively. The obstacle avoidance strategy corresponding to the PDC data can be: when it is determined based on the PDC data that the distance between the closest obstacle to the vehicle and the vehicle is less than a preset PDC threshold value (which can be represented as Supdcm), controlling the vehicle to brake suddenly; when it is determined based on the PDC data that the distance between the closest obstacle to the vehicle and the vehicle is greater than or equal to the preset PDC threshold value, not controlling the vehicle to brake suddenly. The obstacle avoidance strategy corresponding to the OBS data can be: when it is determined based on the OBS data that the distance between the closest obstacle to the vehicle and the vehicle is less than a preset OBS threshold value (which can be represented as Suobsm, and the OBS threshold value can be the same as or different from the first threshold value), controlling the vehicle to brake suddenly; when it is determined based on the OBS data that the distance between the closest obstacle to the vehicle and the vehicle is greater than or equal to the preset OBS threshold value, not controlling the vehicle to brake suddenly.

[0030] Optionally, when the detection data is from the first ultrasonic radar and the vehicle is in the straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is greater than or equal to the first threshold value, whether to control the vehicle to brake suddenly can be determined based on the obstacle avoidance strategy corresponding to the PDC data.

[0031] Optionally, when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is less than the first threshold value, a first reference result is obtained based on the obstacle avoidance strategy corresponding to the PDC data; a second reference result is obtained based on the obstacle avoidance strategy corresponding to the OBS data; if the first reference result and / or the second reference result is to brake suddenly, the vehicle is controlled to brake suddenly.

[0032] In the embodiments of the present application, when the detection data is the first ultrasonic radar from the vehicle and the vehicle is in the straight-in straight-out state, it is also necessary to determine the obstacle avoidance strategy based on the OBS data, because although the accuracy of the OBS is lower than that of the PDC data, when the OBS data detects that the distance between the vehicle and the obstacle is already very close (less than the first threshold value), even if there is a measurement error, it is in a state that the vehicle and the obstacle will soon collide, therefore, in order to further improve the safety of the vehicle, the obstacle avoidance strategy corresponding to the PDC data and the obstacle avoidance strategy corresponding to the OBS data can be combined to determine whether to control the vehicle to brake suddenly. Moreover, based on the detection range of the first ultrasonic radar, it can be determined that the obstacle detected by the first ultrasonic radar is likely to be in front of or behind the vehicle (very likely to be on the path), or it is likely to be around the four corners of the vehicle (i.e. not on the path), therefore, when the detection data is the first ultrasonic radar from the vehicle and the vehicle is in the straight-in straight-out state, and the OBS data detects that the distance between the vehicle and the obstacle is greater than or equal to the first threshold value, only determining whether to control the vehicle to brake suddenly based on the obstacle avoidance strategy corresponding to the PDC data can reduce the amount of data processing, thereby speeding up the generation speed of the strategy on the basis of ensuring the safety of the vehicle.

[0033] S130: When the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determining whether to control the vehicle to brake suddenly based on the PDC data and the OBS data.

[0034] As one way, when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, a third reference result is obtained based on the obstacle avoidance strategy corresponding to the PDC data, a fourth reference result is obtained based on the obstacle avoidance strategy corresponding to the OBS data, and if the third reference result and the fourth reference result are both sudden braking, the vehicle is controlled to brake suddenly.

[0035] In the embodiments of the present application, when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, if only the obstacle avoidance strategy corresponding to the PDC data is used, it may lead to false braking of the vehicle. For example, in an automatic parking scenario, if the vehicle is controlled to brake suddenly based on the PDC data (i.e. only according to the distance), and the obstacle is actually not on the parking path of the vehicle, this obviously affects the user experience. If only the obstacle avoidance strategy corresponding to the OBS data is used, since the accuracy of the OBS data is not as good as that of the PDC data, distance perception errors may occur, thereby reducing the accuracy of the obstacle avoidance strategy. Therefore, when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, if the third reference result and the fourth reference result are both sudden braking, the vehicle is controlled to brake suddenly, which can improve the accuracy of the obstacle avoidance strategy, improve the safety of the vehicle and the user experience.

[0036] Further, in the embodiment of the present application, when it is confirmed through the PDC data and the OBS data that the vehicle is about to collide with the obstacle, the vehicle is controlled to make an emergency stop, so that the speed of the vehicle can be quickly reduced to 0, and the distance between the vehicle and the obstacle in the current scenario is as large as possible, thereby greatly reducing the possibility of collision.

[0037] The obstacle avoidance method provided in the embodiment can obtain the detection data of the ultrasonic radar of the vehicle, and when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, it is determined whether to control the vehicle to make an emergency stop based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in the non-straight-in straight-out state, it is determined whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data. In this way, the detection data of the ultrasonic radar of the vehicle can be obtained, and when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, it is determined whether to control the vehicle to make an emergency stop based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in the non-straight-in straight-out state, it is determined whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data. The distance information obtained by the PDC data and the position information obtained by the OBS data are combined, so that the distance between the obstacle and the vehicle can be more accurately determined, so that the vehicle can be timely stopped, and when the vehicle is controlled to make an emergency stop, the driving state of the vehicle is also considered, so that whether the vehicle needs to be stopped can be more accurately determined, thereby improving the safety of the vehicle.

[0038] Please refer to Figure 3 The obstacle avoidance method provided in the embodiment includes the following steps.

[0039] S210: Obtain detection data of an ultrasonic radar of a vehicle, the detection data including PDC data and OBS data, the PDC data representing the distance between a detected obstacle and the vehicle, and the OBS representing the position of the detected obstacle relative to the vehicle.

[0040] S220: When the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, it is determined whether to control the vehicle to make an emergency stop based on the PDC data, the first ultrasonic radar being an ultrasonic radar installed at a corner position of the vehicle.

[0041] S230: When the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, it is determined whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data.

[0042] S240: When the detection data is from the second ultrasonic radar of the vehicle, determining whether to control the vehicle to emergency brake based on the PDC data and the OBS data, the second ultrasonic radar is an ultrasonic radar installed at the front of the vehicle or the middle of the vehicle.

[0043] As a way, if the detection data is from the second ultrasonic radar, a fifth reference result can be obtained based on the obstacle avoidance strategy corresponding to the PDC data, and a sixth reference result can be obtained based on the obstacle avoidance strategy corresponding to the OBS data; if the fifth reference result and / or the sixth reference result is emergency brake, the vehicle is controlled to emergency brake.

[0044] In the embodiments of the present application, since the second ultrasonic radar is located at the front and rear of the vehicle, the distance between the obstacle detected by the second ultrasonic radar and the driving path of the vehicle is very close or basically on the driving path, therefore, in order to improve the safety of the vehicle, when at least one of the fifth reference result and the sixth reference result is emergency brake, the vehicle is controlled to emergency brake.

[0045] S250: When the detection data is from the third ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, determining whether to control the vehicle to emergency brake based on the PDC data, the third ultrasonic radar is an ultrasonic radar installed at the side of the vehicle body.

[0046] As a way, when the detection data is from the third ultrasonic radar and the vehicle is in a straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is greater than or equal to the second threshold value, it is determined based on the PDC data whether to control the vehicle to emergency brake; when the detection data is from the third ultrasonic radar and the vehicle is in a straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is less than the second threshold value, it is determined based on the PDC data and the OBS data whether to control the vehicle to emergency brake.

[0047] Optionally, when the detection data is from the third ultrasonic radar and the vehicle is in a straight-in straight-out state, it can be determined whether to control the vehicle to emergency brake based on the method when the detection data is from the first ultrasonic radar and the vehicle is in a straight-in straight-out state.

[0048] Optionally, since the third ultrasonic radar is located at both sides of the vehicle body, the relevance between the obstacle detected by the third ultrasonic radar and the driving path of the vehicle is not great, therefore, in order to expand the drivable area of the vehicle and improve the possibility of driving path planning, the second threshold value can be set to be less than or equal to the first threshold value.

[0049] S260: When the detection data is from the third ultrasonic radar of the vehicle and the vehicle is in a non-straight-in straight-out state, determining whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

[0050] As a manner, when the detection data is from the third ultrasonic radar and the vehicle is in the non-straight-in-and-out state, it is determined whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

[0051] Optionally, when the detection data is from the third ultrasonic radar and the vehicle is in the non-straight-in-and-out state, it can be determined whether to control the vehicle to emergency brake based on the method when the detection data is from the first ultrasonic radar and the vehicle is in the non-straight-in-and-out state.

[0052] The obstacle avoidance method provided by the embodiment can obtain the detection data of the ultrasonic radar of the vehicle, and when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in-and-out state, it is determined whether to control the vehicle to emergency brake based on the PDC data. When the detection data is from the first ultrasonic radar and the vehicle is in the non-straight-in-and-out state, it is determined whether to control the vehicle to emergency brake based on the PDC data and the OBS data. The distance information obtained by the PDC data and the position information obtained by the OBS data are combined, so that the distance between the obstacle and the vehicle can be more accurately determined, so that the vehicle can be timely emergency braked, and when the vehicle is controlled to emergency brake, the driving state of the vehicle is also considered, so that whether the vehicle needs to be emergency braked can be more accurately determined, thereby improving the safety of the vehicle. In the embodiment, different obstacle avoidance strategies are implemented when the obstacles are detected by the ultrasonic radars at different positions, so that the flexibility and safety of obstacle avoidance can be improved. At the same time, since the distance between the obstacle and the vehicle can be more accurately determined, the vehicle can be more easily and safely parked in an extremely narrow parking space in an automatic parking scenario.

[0053] Please refer to Figure 4 The obstacle avoidance method provided by the embodiment includes:

[0054] S310: Obtain detection data of an ultrasonic radar of a vehicle, the detection data including PDC data and OBS data, the PDC data representing a distance between a detected obstacle and the vehicle, and the OBS representing a position of the detected obstacle relative to the vehicle.

[0055] S320: When the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in-and-out state, it is determined whether to control the vehicle to emergency brake based on the PDC data, the first ultrasonic radar being an ultrasonic radar installed at a corner position of the vehicle.

[0056] S330: When the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in-and-out state, it is determined whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

[0057] S340: acquire visual OBS data, the visual OBS data representing obstacle information acquired by an image acquisition device of the vehicle.

[0058] The visual OBS data can refer to data containing obstacle position information acquired by an image acquisition device (such as a camera, a depth camera, etc.) of the vehicle. The visual OBS data can acquire obstacles farther than the detection range of an ultrasonic radar, thereby increasing the reaction time of the vehicle to road conditions and the surrounding environment.

[0059] As a manner, the image acquisition device can be controlled to acquire the visual OBS data in real time during driving of the vehicle.

[0060] S350: when it is determined based on the visual OBS data that the distance between the obstacle and the preset driving trajectory of the vehicle is less than a preset distance, control the speed of the vehicle to be a preset speed.

[0061] The preset driving trajectory can refer to a driving path planned by the vehicle based on various sensor data and driving scenarios (such as an automatic parking scenario, a highway driving scenario, etc.).

[0062] As a manner, when it is determined based on the visual OBS data that the distance between the obstacle and the preset driving trajectory of the vehicle is less than a preset distance, the speed of the vehicle is controlled to be a preset speed.

[0063] Optionally, there can be multiple preset distances, each preset distance can correspond to a preset speed, and the closer the preset distance, the smaller the corresponding preset speed, but the preset speed is always greater than 0. Through the mapping relationship between multiple preset distances and preset speeds, multiple distance ranges can each correspond to a preset speed.

[0064] The obstacle avoidance method provided in the embodiment can obtain the detection data of the ultrasonic radar of the vehicle. When the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, whether to control the vehicle to make an emergency stop is determined based on the PDC data. When the detection data is from the first ultrasonic radar and the vehicle is in the non-straight-in straight-out state, whether to control the vehicle to make an emergency stop is determined based on the PDC data and the OBS data. The distance information obtained by the PDC data and the position information obtained by the OBS data are combined, so that the distance between the obstacle and the vehicle can be more accurately determined, so that the vehicle can be timely stopped, and when the emergency stop control of the vehicle is performed, the driving state of the vehicle is also considered, so that whether the vehicle needs to be stopped can be more accurately determined, and the safety of the vehicle is improved. In the embodiment, the speed of the vehicle is controlled in real time through the visual OBS data, so that the speed of the vehicle can be reduced, thereby providing more sufficient calculation time for the obstacle avoidance strategy. At the same time, the emergency stop of the vehicle in the low-speed state can also improve the stability of the vehicle, and the vehicle can be stopped faster, thereby improving the safety of the vehicle.

[0065] Please refer to Figure 5 The application provides an obstacle avoidance device 600, which comprises:

[0066] The data acquisition unit 610 is configured to acquire detection data of an ultrasonic radar of a vehicle, wherein the detection data comprises PDC data and OBS data, the PDC data represents the distance between a detected obstacle and the vehicle, and the OBS represents the position of the detected obstacle relative to the vehicle.

[0067] The vehicle control unit 620 is configured to, when the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, determine whether to control the vehicle to make an emergency stop based on the PDC data, wherein the first ultrasonic radar is an ultrasonic radar installed at a corner position of the vehicle; and when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determine whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data.

[0068] As one way, the data acquisition unit 610 is specifically configured to acquire visual OBS data, wherein the visual OBS data represents the obstacle information collected by an image collection device of the vehicle; and when it is determined based on the visual OBS data that the distance between the obstacle and a preset driving track of the vehicle is less than a preset distance, the speed of the vehicle is controlled to be reduced to a preset speed.

[0069] As a manner, the data acquisition unit 610 is specifically configured to acquire initial detection data collected by each of the plurality of ultrasonic radars of the vehicle to obtain a plurality of initial detection data; and determine the detection data from the plurality of initial detection data, wherein the obstacle corresponding to the detection data has the smallest distance to the vehicle.

[0070] As a manner, the vehicle control unit 620 is specifically configured to, when the detection data is from the first ultrasonic radar and the vehicle is in the straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is greater than or equal to a first threshold, determine whether to control the vehicle to emergency brake based on the PDC data; and when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is less than the first threshold, determine whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

[0071] Optionally, the vehicle control unit 620 is specifically configured to, when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is less than the first threshold, obtain a first reference result based on the obstacle avoidance strategy corresponding to the PDC data; obtain a second reference result based on the obstacle avoidance strategy corresponding to the OBS data; and if the first reference result and / or the second reference result is emergency brake, control the vehicle to emergency brake.

[0072] As a manner, the vehicle control unit 620 is specifically configured to, when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, obtain a third reference result based on the obstacle avoidance strategy corresponding to the PDC data; obtain a fourth reference result based on the obstacle avoidance strategy corresponding to the OBS data; and if the third reference result and the fourth reference result are both emergency brake, control the vehicle to emergency brake.

[0073] As a manner, the vehicle control unit 620 is specifically configured to, when the detection data is from the second ultrasonic radar of the vehicle, determine whether to control the vehicle to emergency brake based on the PDC data and the OBS data, the second ultrasonic radar being an ultrasonic radar installed at the front of the vehicle or at a position between the vehicle positions.

[0074] Optionally, the vehicle control unit 620 is specifically configured to, if the detection data is from the second ultrasonic radar, obtain a fifth reference result based on an obstacle avoidance strategy corresponding to the PDC data; obtain a sixth reference result based on an obstacle avoidance strategy corresponding to the OBS data; and if the fifth reference result and / or the sixth reference result is emergency braking, control the vehicle to stop to avoid the obstacle.

[0075] As a manner, the vehicle control unit 620 is specifically configured to, if the detection data is from the third ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, determine whether to control the vehicle to emergency brake based on the PDC data, the third ultrasonic radar being an ultrasonic radar installed at a side position of the vehicle body; and if the detection data is from the third ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determine whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

[0076] Optionally, the vehicle control unit 620 is specifically configured to, if the detection data is from the third ultrasonic radar and the vehicle is in a straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is greater than or equal to a second threshold, determine whether to control the vehicle to emergency brake based on the PDC data; and if the detection data is from the third ultrasonic radar and the vehicle is in a straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is less than the second threshold, determine whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

[0077] The following will be described in combination with Figure 6 A vehicle provided by the present application is described.

[0078] Please refer to Figure 6 Based on the above obstacle avoidance method and device, the present application further provides another vehicle 100 that can execute the foregoing obstacle avoidance method. The vehicle 100 comprises a processor 102, a memory 104, and a data acquisition module 106. The memory 104 stores a program that can execute the contents of the foregoing embodiments, and the backup processor 102 can execute the program stored in the memory 104.

[0079] The processor 102 can include one or more processing cores. The processor 102 connects various parts within the vehicle 100 by various interfaces and lines, executes various functions of the vehicle 100 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 104, and calling data stored in the memory 104. Optionally, the processor 102 can be implemented in at least one of a hardware form of a neural network processing unit (NPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 102 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), a neural network processing unit (NPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; the NPU is responsible for processing multimedia data such as video and images; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 102, but can be implemented separately by a communication chip.

[0080] The memory 104 can include a random access memory (RAM), and can also include a read-only memory (ROM) and a double data rate (DDR). The memory 104 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 104 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing each of the following method embodiments, etc. The data storage area can also store data created by the vehicle 100 in use (such as a phone book, audio and video data, chat record data), etc.

[0081] The data collection module 106 can include, but is not limited to, ultrasonic radar, camera, level meter, light sensor, motion sensor, pressure sensor, infrared thermal sensor, distance sensor, acceleration sensor, and other sensors. Among them, the ultrasonic radar can obtain PDC information and OBS information of obstacles around the vehicle 100. The camera can collect OBS information of obstacles on the preset driving track of the vehicle 100.

[0082] Among them, the pressure sensor can detect the pressure generated by pressing on the vehicle 100. That is, the pressure sensor detects the pressure generated by the contact or pressing between the user and the vehicle 100, for example, the pressure generated by the contact or pressing between the user's hand and the vehicle 100. Therefore, the pressure sensor can be used to determine whether contact or pressing occurs between the user and the vehicle 100, and the size of the pressure.

[0083] Among them, the acceleration sensor can detect the size of acceleration in each direction (generally three axes), and can detect the size and direction of gravity when at rest, which can be used for applications such as vehicle 100 posture calibration (such as a magnetometer), vibration recognition related functions (such as a pedometer, tapping), etc. In addition, the vehicle 100 can also be configured with a gyroscope, barometer, hygrometer, thermometer and other sensors, which will not be described here.

[0084] The embodiment of the present application provides a computer readable storage medium. The computer readable storage medium stores program code, and the program code can be called and executed by a processor to execute the method described in the above method embodiment.

[0085] The computer readable storage medium can be an electronic storage such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer readable storage medium includes a non-volatile computer readable storage medium. The computer readable storage medium has a storage space for program code for executing any method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code can be compressed in an appropriate form, for example.

[0086] In summary, the application provides an obstacle avoidance method, device and vehicle. After obtaining the detection data of the ultrasonic radar of the vehicle, including PDC data and OBS data, when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, it is determined whether to control the vehicle to brake sharply based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, it is determined whether to control the vehicle to brake sharply based on the PDC data and the OBS data. In this way, the detection data of the ultrasonic radar of the vehicle can be obtained. When the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, it is determined whether to control the vehicle to brake sharply based on the PDC data; when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, it is determined whether to control the vehicle to brake sharply based on the PDC data and the OBS data. The distance information obtained by the PDC data and the position information obtained by the OBS data are combined to more accurately determine the distance between the obstacle and the vehicle, so that the vehicle can be braked in time. In addition, the driving state of the vehicle is also considered when the vehicle is braked, so that whether the vehicle needs to be braked can be more accurately determined, thereby improving the safety of the vehicle.

[0087] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the application, and not to limit them; although the application has been described in detail with reference to the foregoing examples, those skilled in the art will understand that they can still modify the technical solutions described in the foregoing examples, or make equivalent replacements for part of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. An obstacle avoidance method characterized by, The method comprises: obtaining detection data of an ultrasonic radar of a vehicle, the detection data comprising PDC data and OBS data, the PDC data representing a distance of a detected obstacle from the vehicle, and the OBS data representing a position of the detected obstacle relative to the vehicle; when the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, and based on the OBS data, it is determined that the distance of the detected obstacle from the vehicle is greater than or equal to a first threshold value, determining whether to control the vehicle to make an emergency stop based on the PDC data, the first ultrasonic radar being an ultrasonic radar installed at a corner position of the vehicle; when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, and based on the OBS data, it is determined that the distance of the detected obstacle from the vehicle is less than the first threshold value, determining whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data; when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state, determining whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data.

2. The method of claim 1, wherein, The method further comprises: when the detection data is from a second ultrasonic radar of the vehicle, determining whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data, the second ultrasonic radar being an ultrasonic radar installed at a front or rear position of the vehicle. The method further comprises: when the detection data is from a second ultrasonic radar of the vehicle, determining whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data, the second ultrasonic radar being an ultrasonic radar installed at a front or rear position of the vehicle.

3. The method of claim 1, wherein, ​ ​ ​ ​ 4. The method of claim 1, wherein, ​ ​ 5. The method of claim 4, wherein, ​ If the detection data is from the second ultrasonic radar, a fifth reference result is obtained based on an obstacle avoidance strategy corresponding to the PDC data; A sixth reference result is obtained based on an obstacle avoidance strategy corresponding to the OBS data; If the fifth reference result and / or the sixth reference result is emergency braking, the vehicle is controlled to stop to avoid the obstacle.

6. The method of claim 1, wherein, The method further comprises: When the detection data is from a third ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, it is determined whether to control the vehicle to emergency brake based on the PDC data, the third ultrasonic radar being an ultrasonic radar installed at a side position of the vehicle body; When the detection data is from the third ultrasonic radar and the vehicle is in a non-straight-in straight-out state, it is determined whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

7. The method of claim 6, wherein, The determination whether to control the vehicle to emergency brake based on the PDC data when the detection data is from the third ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state comprises: When the detection data is from the third ultrasonic radar and the vehicle is in a straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is greater than or equal to a second threshold value, it is determined whether to control the vehicle to emergency brake based on the PDC data; When the detection data is from the third ultrasonic radar and the vehicle is in a straight-in straight-out state, and it is determined based on the OBS data that the distance between the detected obstacle and the vehicle is less than the second threshold value, it is determined whether to control the vehicle to emergency brake based on the PDC data and the OBS data.

8. The method according to any one of claims 1 to 7, characterized in that, The method further comprises: Obtaining visual OBS data representing obstacle information collected by an image collection device of the vehicle; When it is determined based on the visual OBS data that the distance between the obstacle and the predetermined driving track of the vehicle is less than a predetermined distance, the speed of the vehicle is controlled to decrease to a predetermined speed.

9. The method according to any of claims 1 to 7, characterized in that The method further comprises: Obtaining initial detection data collected by each of the plurality of ultrasonic radars of the vehicle to obtain a plurality of initial detection data; Determining the detection data from the plurality of initial detection data, wherein the distance between the obstacle corresponding to the detection data and the vehicle is the smallest.

10. An obstacle avoidance device characterized by, The apparatus comprises: A data acquisition unit configured to acquire detection data of an ultrasonic radar of a vehicle, the detection data comprising PDC data and OBS data, the PDC data representing the distance between a detected obstacle and the vehicle, and the OBS data representing the position of the detected obstacle relative to the vehicle; A vehicle control unit is configured to determine whether to control the vehicle to make an emergency stop based on the PDC data when the detection data is from a first ultrasonic radar of the vehicle and the vehicle is in a straight-in straight-out state, and based on the OBS data determining that a distance between a detected obstacle and the vehicle is greater than or equal to a first threshold value; determine whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data when the detection data is from the first ultrasonic radar of the vehicle and the vehicle is in the straight-in straight-out state, and based on the OBS data determining that the distance between the detected obstacle and the vehicle is less than the first threshold value; and determine whether to control the vehicle to make an emergency stop based on the PDC data and the OBS data when the detection data is from the first ultrasonic radar and the vehicle is in a non-straight-in straight-out state.

11. A vehicle characterized by comprising: The vehicle control unit includes an ultrasonic radar, one or more processors, and a memory. One or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method of any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, A computer readable storage medium stores program code, wherein the program code performs the method of any one of claims 1-9 when executed.

Images